[Draft] Upload

* 📝 add mechanism for building colab notebook

* 🖍 add notebooks to correct folder

* 🖍 fix folder name

.github/ISSUE_TEMPLATE/config.yml

@@ -1,4 +1,7 @@
 contact_links:
   - name: Blank issue
     url: https://github.com/huggingface/diffusers/issues/new
-    about: General usage questions and community discussions
+    about: Other
+  - name: Forum
+    url: https://discuss.huggingface.co/
+    about: General usage questions and community discussions

.github/workflows/build_documentation.yml

@@ -13,6 +13,7 @@ jobs:
     with:
       commit_sha: ${{ github.sha }}
       package: diffusers
+      notebook_folder: diffusers_doc
       languages: en ko
     secrets:
       token: ${{ secrets.HUGGINGFACE_PUSH }}

.github/workflows/pr_quality.yml

@@ -27,9 +27,8 @@ jobs:
           pip install .[quality]
       - name: Check quality
         run: |
-          black  --check --preview examples tests src utils scripts
-          isort --check-only examples tests src utils scripts
-          flake8 examples tests src utils scripts
+          black --check examples tests src utils scripts
+          ruff examples tests src utils scripts
           doc-builder style src/diffusers docs/source --max_len 119 --check_only --path_to_docs docs/source
 
   check_repository_consistency:
@@ -48,3 +47,4 @@ jobs:
         run: |
           python utils/check_copies.py
           python utils/check_dummies.py
+          make deps_table_check_updated

.github/workflows/pr_tests.yml

@@ -36,6 +36,11 @@ jobs:
             runner: docker-cpu
             image: diffusers/diffusers-onnxruntime-cpu
             report: onnx_cpu
+          - name: PyTorch Example CPU tests on Ubuntu
+            framework: pytorch_examples
+            runner: docker-cpu
+            image: diffusers/diffusers-pytorch-cpu
+            report: torch_cpu
 
     name: ${{ matrix.config.name }}
 
@@ -90,6 +95,13 @@ jobs:
           --make-reports=tests_${{ matrix.config.report }} \
           tests/
 
+    - name: Run example PyTorch CPU tests
+      if: ${{ matrix.config.framework == 'pytorch_examples' }}
+      run: |
+        python -m pytest -n 2 --max-worker-restart=0 --dist=loadfile \
+          --make-reports=tests_${{ matrix.config.report }} \
+          examples/test_examples.py 
+
     - name: Failure short reports
       if: ${{ failure() }}
       run: cat reports/tests_${{ matrix.config.report }}_failures_short.txt

.github/workflows/push_tests_fast.yml

@@ -0,0 +1,165 @@
+name: Slow tests on main
+
+on:
+  push:
+    branches:
+      - main
+
+env:
+  DIFFUSERS_IS_CI: yes
+  HF_HOME: /mnt/cache
+  OMP_NUM_THREADS: 8
+  MKL_NUM_THREADS: 8
+  PYTEST_TIMEOUT: 600
+  RUN_SLOW: no
+
+jobs:
+  run_fast_tests:
+    strategy:
+      fail-fast: false
+      matrix:
+        config:
+          - name: Fast PyTorch CPU tests on Ubuntu
+            framework: pytorch
+            runner: docker-cpu
+            image: diffusers/diffusers-pytorch-cpu
+            report: torch_cpu
+          - name: Fast Flax CPU tests on Ubuntu
+            framework: flax
+            runner: docker-cpu
+            image: diffusers/diffusers-flax-cpu
+            report: flax_cpu
+          - name: Fast ONNXRuntime CPU tests on Ubuntu
+            framework: onnxruntime
+            runner: docker-cpu
+            image: diffusers/diffusers-onnxruntime-cpu
+            report: onnx_cpu
+          - name: PyTorch Example CPU tests on Ubuntu
+            framework: pytorch_examples
+            runner: docker-cpu
+            image: diffusers/diffusers-pytorch-cpu
+            report: torch_cpu
+
+    name: ${{ matrix.config.name }}
+
+    runs-on: ${{ matrix.config.runner }}
+
+    container:
+      image: ${{ matrix.config.image }}
+      options: --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/
+
+    defaults:
+      run:
+        shell: bash
+
+    steps:
+    - name: Checkout diffusers
+      uses: actions/checkout@v3
+      with:
+        fetch-depth: 2
+
+    - name: Install dependencies
+      run: |
+        apt-get update && apt-get install libsndfile1-dev -y
+        python -m pip install -e .[quality,test]
+        python -m pip install -U git+https://github.com/huggingface/transformers
+        python -m pip install git+https://github.com/huggingface/accelerate
+
+    - name: Environment
+      run: |
+        python utils/print_env.py
+
+    - name: Run fast PyTorch CPU tests
+      if: ${{ matrix.config.framework == 'pytorch' }}
+      run: |
+        python -m pytest -n 2 --max-worker-restart=0 --dist=loadfile \
+          -s -v -k "not Flax and not Onnx" \
+          --make-reports=tests_${{ matrix.config.report }} \
+          tests/
+
+    - name: Run fast Flax TPU tests
+      if: ${{ matrix.config.framework == 'flax' }}
+      run: |
+        python -m pytest -n 2 --max-worker-restart=0 --dist=loadfile \
+          -s -v -k "Flax" \
+          --make-reports=tests_${{ matrix.config.report }} \
+          tests/
+
+    - name: Run fast ONNXRuntime CPU tests
+      if: ${{ matrix.config.framework == 'onnxruntime' }}
+      run: |
+        python -m pytest -n 2 --max-worker-restart=0 --dist=loadfile \
+          -s -v -k "Onnx" \
+          --make-reports=tests_${{ matrix.config.report }} \
+          tests/
+
+    - name: Run example PyTorch CPU tests
+      if: ${{ matrix.config.framework == 'pytorch_examples' }}
+      run: |
+        python -m pytest -n 2 --max-worker-restart=0 --dist=loadfile \
+          --make-reports=tests_${{ matrix.config.report }} \
+          examples/test_examples.py 
+
+    - name: Failure short reports
+      if: ${{ failure() }}
+      run: cat reports/tests_${{ matrix.config.report }}_failures_short.txt
+
+    - name: Test suite reports artifacts
+      if: ${{ always() }}
+      uses: actions/upload-artifact@v2
+      with:
+        name: pr_${{ matrix.config.report }}_test_reports
+        path: reports
+
+  run_fast_tests_apple_m1:
+    name: Fast PyTorch MPS tests on MacOS
+    runs-on: [ self-hosted, apple-m1 ]
+
+    steps:
+    - name: Checkout diffusers
+      uses: actions/checkout@v3
+      with:
+        fetch-depth: 2
+
+    - name: Clean checkout
+      shell: arch -arch arm64 bash {0}
+      run: |
+        git clean -fxd
+
+    - name: Setup miniconda
+      uses: ./.github/actions/setup-miniconda
+      with:
+        python-version: 3.9
+
+    - name: Install dependencies
+      shell: arch -arch arm64 bash {0}
+      run: |
+        ${CONDA_RUN} python -m pip install --upgrade pip
+        ${CONDA_RUN} python -m pip install -e .[quality,test]
+        ${CONDA_RUN} python -m pip install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cpu
+        ${CONDA_RUN} python -m pip install git+https://github.com/huggingface/accelerate
+        ${CONDA_RUN} python -m pip install -U git+https://github.com/huggingface/transformers
+
+    - name: Environment
+      shell: arch -arch arm64 bash {0}
+      run: |
+        ${CONDA_RUN} python utils/print_env.py
+
+    - name: Run fast PyTorch tests on M1 (MPS)
+      shell: arch -arch arm64 bash {0}
+      env:
+        HF_HOME: /System/Volumes/Data/mnt/cache
+        HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
+      run: |
+        ${CONDA_RUN} python -m pytest -n 0 -s -v --make-reports=tests_torch_mps tests/
+
+    - name: Failure short reports
+      if: ${{ failure() }}
+      run: cat reports/tests_torch_mps_failures_short.txt
+
+    - name: Test suite reports artifacts
+      if: ${{ always() }}
+      uses: actions/upload-artifact@v2
+      with:
+        name: pr_torch_mps_test_reports
+        path: reports

.gitignore

@@ -169,3 +169,6 @@ tags
 
 # dependencies
 /transformers
+
+# ruff
+.ruff_cache

CONTRIBUTING.md

@@ -1,5 +1,5 @@
 <!---
-Copyright 2022 The HuggingFace Team. All rights reserved.
+Copyright 2023 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License");
 you may not use this file except in compliance with the License.
@@ -177,7 +177,7 @@ Follow these steps to start contributing ([supported Python versions](https://gi
    $ make style
    ```
 
-   🧨 Diffusers also uses `flake8` and a few custom scripts to check for coding mistakes. Quality
+   🧨 Diffusers also uses `ruff` and a few custom scripts to check for coding mistakes. Quality
    control runs in CI, however you can also run the same checks with:
 
    ```bash

Makefile

@@ -9,9 +9,8 @@ modified_only_fixup:
 	$(eval modified_py_files := $(shell python utils/get_modified_files.py $(check_dirs)))
 	@if test -n "$(modified_py_files)"; then \
 		echo "Checking/fixing $(modified_py_files)"; \
-		black --preview $(modified_py_files); \
-		isort $(modified_py_files); \
-		flake8 $(modified_py_files); \
+		black $(modified_py_files); \
+		ruff $(modified_py_files); \
 	else \
 		echo "No library .py files were modified"; \
 	fi
@@ -41,9 +40,8 @@ repo-consistency:
 # this target runs checks on all files
 
 quality:
-	black --check --preview $(check_dirs)
-	isort --check-only $(check_dirs)
-	flake8 $(check_dirs)
+	black --check $(check_dirs)
+	ruff $(check_dirs)
 	doc-builder style src/diffusers docs/source --max_len 119 --check_only --path_to_docs docs/source
 	python utils/check_doc_toc.py
 
@@ -57,8 +55,8 @@ extra_style_checks:
 # this target runs checks on all files and potentially modifies some of them
 
 style:
-	black --preview $(check_dirs)
-	isort $(check_dirs)
+	black $(check_dirs)
+	ruff $(check_dirs) --fix
 	${MAKE} autogenerate_code
 	${MAKE} extra_style_checks
 

README.md

@@ -467,12 +467,12 @@ image.save("ddpm_generated_image.png")
 - [Unconditional Diffusion with continuous scheduler](https://huggingface.co/google/ncsnpp-ffhq-1024)
 
 **Other Image Notebooks**:
-* [image-to-image generation with Stable Diffusion](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/image_2_image_using_diffusers.ipynb) ![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg),
-* [tweak images via repeated Stable Diffusion seeds](https://colab.research.google.com/github/pcuenca/diffusers-examples/blob/main/notebooks/stable-diffusion-seeds.ipynb) ![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg),
+* [image-to-image generation with Stable Diffusion](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/image_2_image_using_diffusers.ipynb) ![Open In Colab](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/image_2_image_using_diffusers.ipynb),
+* [tweak images via repeated Stable Diffusion seeds](https://colab.research.google.com/github/pcuenca/diffusers-examples/blob/main/notebooks/stable-diffusion-seeds.ipynb) ![Open In Colab](https://colab.research.google.com/github/pcuenca/diffusers-examples/blob/main/notebooks/stable-diffusion-seeds.ipynb),
 
 **Diffusers for Other Modalities**:
-* [Molecule conformation generation](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/geodiff_molecule_conformation.ipynb) ![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg),
-* [Model-based reinforcement learning](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/reinforcement_learning_with_diffusers.ipynb) ![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg),
+* [Molecule conformation generation](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/geodiff_molecule_conformation.ipynb) ![Open In Colab](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/geodiff_molecule_conformation.ipynb),
+* [Model-based reinforcement learning](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/reinforcement_learning_with_diffusers.ipynb) ![Open In Colab](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/reinforcement_learning_with_diffusers.ipynb),
 
 ### Web Demos
 If you just want to play around with some web demos, you can try out the following 🚀 Spaces:

docs/README.md

@@ -1,5 +1,5 @@
 <!---
-Copyright 2022- The HuggingFace Team. All rights reserved.
+Copyright 2023- The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License");
 you may not use this file except in compliance with the License.

docs/source/_config.py

@@ -0,0 +1,9 @@
+# docstyle-ignore
+INSTALL_CONTENT = """
+# Diffusers installation
+! pip install diffusers transformers datasets accelerate
+# To install from source instead of the last release, comment the command above and uncomment the following one.
+# ! pip install git+https://github.com/huggingface/diffusers.git
+"""
+
+notebook_first_cells = [{"type": "code", "content": INSTALL_CONTENT}]

docs/source/en/_toctree.yml

@@ -8,6 +8,10 @@
   - local: installation
     title: Installation
   title: Get started
+- sections:
+  - local: tutorials/basic_training
+    title: Train a diffusion model
+  title: Tutorials
 - sections:
   - sections:
     - local: using-diffusers/loading
@@ -32,6 +36,8 @@
       title: Text-Guided Image-Inpainting
     - local: using-diffusers/depth2img
       title: Text-Guided Depth-to-Image
+    - local: using-diffusers/controlling_generation
+      title: Controlling generation
     - local: using-diffusers/reusing_seeds
       title: Reusing seeds for deterministic generation
     - local: using-diffusers/reproducibility
@@ -42,6 +48,8 @@
       title: How to contribute a Pipeline
     - local: using-diffusers/using_safetensors
       title: Using safetensors
+    - local: using-diffusers/weighted_prompts
+      title: Weighting Prompts
     title: Pipelines for Inference
   - sections:
     - local: using-diffusers/rl
@@ -55,6 +63,8 @@
 - sections:
   - local: optimization/fp16
     title: Memory and Speed
+  - local: optimization/torch2.0
+    title: Torch2.0 support
   - local: optimization/xformers
     title: xFormers
   - local: optimization/onnx
@@ -74,17 +84,19 @@
   - local: training/text_inversion
     title: Textual Inversion
   - local: training/dreambooth
-    title: Dreambooth
+    title: DreamBooth
   - local: training/text2image
-    title: Text-to-image fine-tuning
+    title: Text-to-image
   - local: training/lora
-    title: LoRA Support in Diffusers
+    title: Low-Rank Adaptation of Large Language Models (LoRA)
   title: Training
 - sections:
   - local: conceptual/philosophy
     title: Philosophy
   - local: conceptual/contribution
     title: How to contribute?
+  - local: conceptual/ethical_guidelines
+    title: Diffusers' Ethical Guidelines
   title: Conceptual Guides
 - sections:
   - sections:
@@ -130,6 +142,8 @@
       title: Safe Stable Diffusion
     - local: api/pipelines/score_sde_ve
       title: Score SDE VE
+    - local: api/pipelines/semantic_stable_diffusion
+      title: Semantic Guidance
     - sections:
       - local: api/pipelines/stable_diffusion/overview
         title: Overview
@@ -146,12 +160,24 @@
       - local: api/pipelines/stable_diffusion/upscale
         title: Super-Resolution
       - local: api/pipelines/stable_diffusion/latent_upscale
-        title: Stable-Diffusion-Latent-Upscaler  
+        title: Stable-Diffusion-Latent-Upscaler
       - local: api/pipelines/stable_diffusion/pix2pix
         title: InstructPix2Pix
+      - local: api/pipelines/stable_diffusion/attend_and_excite
+        title: Attend and Excite
+      - local: api/pipelines/stable_diffusion/pix2pix_zero
+        title: Pix2Pix Zero
+      - local: api/pipelines/stable_diffusion/self_attention_guidance
+        title: Self-Attention Guidance
+      - local: api/pipelines/stable_diffusion/panorama
+        title: MultiDiffusion Panorama
+      - local: api/pipelines/stable_diffusion/controlnet
+        title: Text-to-Image Generation with ControlNet Conditioning
       title: Stable Diffusion
     - local: api/pipelines/stable_diffusion_2
       title: Stable Diffusion 2
+    - local: api/pipelines/stable_unclip
+      title: Stable unCLIP
     - local: api/pipelines/stochastic_karras_ve
       title: Stochastic Karras VE
     - local: api/pipelines/unclip
@@ -168,6 +194,8 @@
       title: Overview
     - local: api/schedulers/ddim
       title: DDIM
+    - local: api/schedulers/ddim_inverse
+      title: DDIMInverse
     - local: api/schedulers/ddpm
       title: DDPM
     - local: api/schedulers/deis
@@ -196,6 +224,8 @@
       title: Singlestep DPM-Solver
     - local: api/schedulers/stochastic_karras_ve
       title: Stochastic Kerras VE
+    - local: api/schedulers/unipc
+      title: UniPCMultistepScheduler
     - local: api/schedulers/score_sde_ve
       title: VE-SDE
     - local: api/schedulers/score_sde_vp

docs/source/en/api/configuration.mdx

@@ -1,4 +1,4 @@
-<!--Copyright 2022 The HuggingFace Team. All rights reserved.
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at

docs/source/en/api/diffusion_pipeline.mdx

@@ -1,4 +1,4 @@
-<!--Copyright 2022 The HuggingFace Team. All rights reserved.
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at

docs/source/en/api/experimental/rl.mdx

@@ -1,4 +1,4 @@
-<!--Copyright 2022 The HuggingFace Team. All rights reserved.
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at

docs/source/en/api/loaders.mdx

@@ -1,4 +1,4 @@
-<!--Copyright 2022 The HuggingFace Team. All rights reserved.
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at

docs/source/en/api/logging.mdx

@@ -1,4 +1,4 @@
-<!--Copyright 2022 The HuggingFace Team. All rights reserved.
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at

docs/source/en/api/models.mdx

@@ -1,4 +1,4 @@
-<!--Copyright 2022 The HuggingFace Team. All rights reserved.
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at
@@ -64,6 +64,12 @@ The models are built on the base class ['ModelMixin'] that is a `torch.nn.module
 ## PriorTransformerOutput
 [[autodoc]] models.prior_transformer.PriorTransformerOutput
 
+## ControlNetOutput
+[[autodoc]] models.controlnet.ControlNetOutput
+
+## ControlNetModel
+[[autodoc]] ControlNetModel
+
 ## FlaxModelMixin
 [[autodoc]] FlaxModelMixin
 

docs/source/en/api/outputs.mdx

@@ -1,4 +1,4 @@
-<!--Copyright 2022 The HuggingFace Team. All rights reserved.
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at

docs/source/en/api/pipelines/alt_diffusion.mdx

@@ -1,4 +1,4 @@
-<!--Copyright 2022 The HuggingFace Team. All rights reserved.
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at

docs/source/en/api/pipelines/audio_diffusion.mdx

@@ -1,4 +1,4 @@
-<!--Copyright 2022 The HuggingFace Team. All rights reserved.
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at

docs/source/en/api/pipelines/cycle_diffusion.mdx

@@ -1,4 +1,4 @@
-<!--Copyright 2022 The HuggingFace Team. All rights reserved.
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at

docs/source/en/api/pipelines/dance_diffusion.mdx

@@ -1,4 +1,4 @@
-<!--Copyright 2022 The HuggingFace Team. All rights reserved.
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at

docs/source/en/api/pipelines/ddim.mdx

@@ -1,4 +1,4 @@
-<!--Copyright 2022 The HuggingFace Team. All rights reserved.
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at

docs/source/en/api/pipelines/ddpm.mdx

@@ -1,4 +1,4 @@
-<!--Copyright 2022 The HuggingFace Team. All rights reserved.
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at

docs/source/en/api/pipelines/dit.mdx

@@ -1,4 +1,4 @@
-<!--Copyright 2022 The HuggingFace Team. All rights reserved.
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at

docs/source/en/api/pipelines/latent_diffusion.mdx

@@ -1,4 +1,4 @@
-<!--Copyright 2022 The HuggingFace Team. All rights reserved.
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at

docs/source/en/api/pipelines/latent_diffusion_uncond.mdx

@@ -1,4 +1,4 @@
-<!--Copyright 2022 The HuggingFace Team. All rights reserved.
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at

docs/source/en/api/pipelines/overview.mdx

@@ -1,4 +1,4 @@
-<!--Copyright 2022 The HuggingFace Team. All rights reserved.
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at
@@ -46,6 +46,7 @@ available a colab notebook to directly try them out.
 |---|---|:---:|:---:|
 | [alt_diffusion](./alt_diffusion) | [**AltDiffusion**](https://arxiv.org/abs/2211.06679) | Image-to-Image Text-Guided Generation | -
 | [audio_diffusion](./audio_diffusion) | [**Audio Diffusion**](https://github.com/teticio/audio_diffusion.git) | Unconditional Audio Generation |
+| [controlnet](./api/pipelines/stable_diffusion/controlnet) | [**ControlNet with Stable Diffusion**](https://arxiv.org/abs/2302.05543) | Image-to-Image Text-Guided Generation | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/controlnet.ipynb)
 | [cycle_diffusion](./cycle_diffusion) | [**Cycle Diffusion**](https://arxiv.org/abs/2210.05559) | Image-to-Image Text-Guided Generation |
 | [dance_diffusion](./dance_diffusion) | [**Dance Diffusion**](https://github.com/williamberman/diffusers.git) | Unconditional Audio Generation |
 | [ddpm](./ddpm) | [**Denoising Diffusion Probabilistic Models**](https://arxiv.org/abs/2006.11239) | Unconditional Image Generation |
@@ -57,13 +58,24 @@ available a colab notebook to directly try them out.
 | [pndm](./pndm) | [**Pseudo Numerical Methods for Diffusion Models on Manifolds**](https://arxiv.org/abs/2202.09778) | Unconditional Image Generation | 
 | [score_sde_ve](./score_sde_ve) | [**Score-Based Generative Modeling through Stochastic Differential Equations**](https://openreview.net/forum?id=PxTIG12RRHS) | Unconditional Image Generation | 
 | [score_sde_vp](./score_sde_vp) | [**Score-Based Generative Modeling through Stochastic Differential Equations**](https://openreview.net/forum?id=PxTIG12RRHS) | Unconditional Image Generation | 
-| [stable_diffusion](./stable_diffusion) | [**Stable Diffusion**](https://stability.ai/blog/stable-diffusion-public-release) | Text-to-Image Generation | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/training_example.ipynb)
-| [stable_diffusion](./stable_diffusion) | [**Stable Diffusion**](https://stability.ai/blog/stable-diffusion-public-release) | Image-to-Image Text-Guided Generation | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/image_2_image_using_diffusers.ipynb)
-| [stable_diffusion](./stable_diffusion) | [**Stable Diffusion**](https://stability.ai/blog/stable-diffusion-public-release) | Text-Guided Image Inpainting | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/in_painting_with_stable_diffusion_using_diffusers.ipynb)
-| [stable_diffusion_2](./stable_diffusion_2) | [**Stable Diffusion 2**](https://stability.ai/blog/stable-diffusion-v2-release) | Text-to-Image Generation | 
+| [semantic_stable_diffusion](./semantic_stable_diffusion) | [**SEGA: Instructing Diffusion using Semantic Dimensions**](https://arxiv.org/abs/2301.12247) | Text-to-Image Generation |
+| [stable_diffusion_text2img](./stable_diffusion/text2img) | [**Stable Diffusion**](https://stability.ai/blog/stable-diffusion-public-release) | Text-to-Image Generation | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/training_example.ipynb)
+| [stable_diffusion_img2img](./stable_diffusion/img2img) | [**Stable Diffusion**](https://stability.ai/blog/stable-diffusion-public-release) | Image-to-Image Text-Guided Generation | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/image_2_image_using_diffusers.ipynb)
+| [stable_diffusion_inpaint](./stable_diffusion/inpaint) | [**Stable Diffusion**](https://stability.ai/blog/stable-diffusion-public-release) | Text-Guided Image Inpainting | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/in_painting_with_stable_diffusion_using_diffusers.ipynb)
+| [stable_diffusion_panorama](./stable_diffusion/panorama) | [**MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation**](https://arxiv.org/abs/2302.08113) | Text-Guided Panorama View Generation |
+| [stable_diffusion_pix2pix](./stable_diffusion/pix2pix) | [**InstructPix2Pix: Learning to Follow Image Editing Instructions**](https://arxiv.org/abs/2211.09800) | Text-Based Image Editing |
+| [stable_diffusion_pix2pix_zero](./stable_diffusion/pix2pix_zero) | [**Zero-shot Image-to-Image Translation**](https://arxiv.org/abs/2302.03027) | Text-Based Image Editing |
+| [stable_diffusion_attend_and_excite](./stable_diffusion/attend_and_excite) | [**Attend and Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models**](https://arxiv.org/abs/2301.13826) | Text-to-Image Generation |
+| [stable_diffusion_self_attention_guidance](./stable_diffusion/self_attention_guidance) | [**Self-Attention Guidance**](https://arxiv.org/abs/2210.00939) | Text-to-Image Generation |
+| [stable_diffusion_image_variation](./stable_diffusion/image_variation) | [**Stable Diffusion Image Variations**](https://github.com/LambdaLabsML/lambda-diffusers#stable-diffusion-image-variations) | Image-to-Image Generation |
+| [stable_diffusion_latent_upscale](./stable_diffusion/latent_upscale) | [**Stable Diffusion Latent Upscaler**](https://twitter.com/StabilityAI/status/1590531958815064065) | Text-Guided Super Resolution Image-to-Image |
+| [stable_diffusion_2](./stable_diffusion_2/) | [**Stable Diffusion 2**](https://stability.ai/blog/stable-diffusion-v2-release) | Text-to-Image Generation | 
 | [stable_diffusion_2](./stable_diffusion_2) | [**Stable Diffusion 2**](https://stability.ai/blog/stable-diffusion-v2-release) | Text-Guided Image Inpainting | 
+| [stable_diffusion_2](./stable_diffusion_2) | [**Stable Diffusion 2**](https://stability.ai/blog/stable-diffusion-v2-release) | Depth-to-Image Text-Guided Generation |
 | [stable_diffusion_2](./stable_diffusion_2) | [**Stable Diffusion 2**](https://stability.ai/blog/stable-diffusion-v2-release) | Text-Guided Super Resolution Image-to-Image |
 | [stable_diffusion_safe](./stable_diffusion_safe) | [**Safe Stable Diffusion**](https://arxiv.org/abs/2211.05105) | Text-Guided Generation | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/ml-research/safe-latent-diffusion/blob/main/examples/Safe%20Latent%20Diffusion.ipynb)
+| [stable_unclip](./stable_unclip) | **Stable unCLIP** | Text-to-Image Generation |
+| [stable_unclip](./stable_unclip) | **Stable unCLIP** | Image-to-Image Text-Guided Generation |
 | [stochastic_karras_ve](./stochastic_karras_ve) | [**Elucidating the Design Space of Diffusion-Based Generative Models**](https://arxiv.org/abs/2206.00364) | Unconditional Image Generation |
 | [unclip](./unclip) | [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://arxiv.org/abs/2204.06125) | Text-to-Image Generation |
 | [versatile_diffusion](./versatile_diffusion) | [Versatile Diffusion: Text, Images and Variations All in One Diffusion Model](https://arxiv.org/abs/2211.08332) | Text-to-Image Generation | 

docs/source/en/api/pipelines/paint_by_example.mdx

@@ -1,4 +1,4 @@
-<!--Copyright 2022 The HuggingFace Team. All rights reserved.
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at

docs/source/en/api/pipelines/pndm.mdx

@@ -1,4 +1,4 @@
-<!--Copyright 2022 The HuggingFace Team. All rights reserved.
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at

docs/source/en/api/pipelines/repaint.mdx

@@ -1,4 +1,4 @@
-<!--Copyright 2022 The HuggingFace Team. All rights reserved.
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at

docs/source/en/api/pipelines/score_sde_ve.mdx

@@ -1,4 +1,4 @@
-<!--Copyright 2022 The HuggingFace Team. All rights reserved.
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at

docs/source/en/api/pipelines/semantic_stable_diffusion.mdx

@@ -0,0 +1,79 @@
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
+
+Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
+the License. You may obtain a copy of the License at
+
+http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
+an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
+specific language governing permissions and limitations under the License.
+-->
+
+# Semantic Guidance
+
+Semantic Guidance for Diffusion Models was proposed in [SEGA: Instructing Diffusion using Semantic Dimensions](https://arxiv.org/abs/2301.12247) and provides strong semantic control over the image generation.
+Small changes to the text prompt usually result in entirely different output images. However, with SEGA a variety of changes to the image are enabled that can be controlled easily and intuitively, and stay true to the original image composition.
+
+The abstract of the paper is the following:
+
+*Text-to-image diffusion models have recently received a lot of interest for their astonishing ability to produce high-fidelity images from text only. However, achieving one-shot generation that aligns with the user's intent is nearly impossible, yet small changes to the input prompt often result in very different images. This leaves the user with little semantic control. To put the user in control, we show how to interact with the diffusion process to flexibly steer it along semantic directions. This semantic guidance (SEGA) allows for subtle and extensive edits, changes in composition and style, as well as optimizing the overall artistic conception. We demonstrate SEGA's effectiveness on a variety of tasks and provide evidence for its versatility and flexibility.*
+
+
+*Overview*:
+
+| Pipeline | Tasks | Colab | Demo
+|---|---|:---:|:---:|
+| [pipeline_semantic_stable_diffusion.py](https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/semantic_stable_diffusion/pipeline_semantic_stable_diffusion) | *Text-to-Image Generation* |  [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/ml-research/semantic-image-editing/blob/main/examples/SemanticGuidance.ipynb) | [Coming Soon](https://huggingface.co/AIML-TUDA)
+
+## Tips
+
+- The Semantic Guidance pipeline can be used with any [Stable Diffusion](./api/pipelines/stable_diffusion/text2img) checkpoint.
+
+### Run Semantic Guidance
+
+The interface of [`SemanticStableDiffusionPipeline`] provides several additional parameters to influence the image generation.
+Exemplary usage may look like this:
+
+```python
+import torch
+from diffusers import SemanticStableDiffusionPipeline
+
+pipe = SemanticStableDiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16)
+pipe = pipe.to("cuda")
+
+out = pipe(
+    prompt="a photo of the face of a woman",
+    num_images_per_prompt=1,
+    guidance_scale=7,
+    editing_prompt=[
+        "smiling, smile",  # Concepts to apply
+        "glasses, wearing glasses",
+        "curls, wavy hair, curly hair",
+        "beard, full beard, mustache",
+    ],
+    reverse_editing_direction=[False, False, False, False],  # Direction of guidance i.e. increase all concepts
+    edit_warmup_steps=[10, 10, 10, 10],  # Warmup period for each concept
+    edit_guidance_scale=[4, 5, 5, 5.4],  # Guidance scale for each concept
+    edit_threshold=[
+        0.99,
+        0.975,
+        0.925,
+        0.96,
+    ],  # Threshold for each concept. Threshold equals the percentile of the latent space that will be discarded. I.e. threshold=0.99 uses 1% of the latent dimensions
+    edit_momentum_scale=0.3,  # Momentum scale that will be added to the latent guidance
+    edit_mom_beta=0.6,  # Momentum beta
+    edit_weights=[1, 1, 1, 1, 1],  # Weights of the individual concepts against each other
+)
+```
+
+For more examples check the colab notebook.
+
+## StableDiffusionSafePipelineOutput
+[[autodoc]] pipelines.semantic_stable_diffusion.SemanticStableDiffusionPipelineOutput
+	- all
+
+## SemanticStableDiffusionPipeline
+[[autodoc]] SemanticStableDiffusionPipeline
+	- all
+	- __call__

docs/source/en/api/pipelines/stable_diffusion/attend_and_excite.mdx

@@ -0,0 +1,75 @@
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
+
+Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
+the License. You may obtain a copy of the License at
+
+http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
+an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
+specific language governing permissions and limitations under the License.
+-->
+
+# Attend and Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models
+
+## Overview
+
+Attend and Excite for Stable Diffusion was proposed in [Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models](https://attendandexcite.github.io/Attend-and-Excite/) and provides textual attention control over the image generation.
+
+The abstract of the paper is the following:
+
+*Text-to-image diffusion models have recently received a lot of interest for their astonishing ability to produce high-fidelity images from text only. However, achieving one-shot generation that aligns with the user's intent is nearly impossible, yet small changes to the input prompt often result in very different images. This leaves the user with little semantic control. To put the user in control, we show how to interact with the diffusion process to flexibly steer it along semantic directions. This semantic guidance (SEGA) allows for subtle and extensive edits, changes in composition and style, as well as optimizing the overall artistic conception. We demonstrate SEGA's effectiveness on a variety of tasks and provide evidence for its versatility and flexibility.*
+
+Resources
+
+* [Project Page](https://attendandexcite.github.io/Attend-and-Excite/)
+* [Paper](https://arxiv.org/abs/2301.13826)
+* [Original Code](https://github.com/AttendAndExcite/Attend-and-Excite)
+* [Demo](https://huggingface.co/spaces/AttendAndExcite/Attend-and-Excite)
+
+
+## Available Pipelines:
+
+| Pipeline | Tasks | Colab | Demo
+|---|---|:---:|:---:|
+| [pipeline_semantic_stable_diffusion_attend_and_excite.py](https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/stable_diffusion/pipeline_semantic_stable_diffusion_attend_and_excite) | *Text-to-Image Generation* | - | https://huggingface.co/spaces/AttendAndExcite/Attend-and-Excite
+
+
+### Usage example
+
+
+```python
+import torch
+from diffusers import StableDiffusionAttendAndExcitePipeline
+
+model_id = "CompVis/stable-diffusion-v1-4"
+pipe = StableDiffusionAttendAndExcitePipeline.from_pretrained(model_id, torch_dtype=torch.float16).to("cuda")
+pipe = pipe.to("cuda")
+
+prompt = "a cat and a frog"
+
+# use get_indices function to find out indices of the tokens you want to alter
+pipe.get_indices(prompt)
+
+token_indices = [2, 5]
+seed = 6141
+generator = torch.Generator("cuda").manual_seed(seed)
+
+images = pipe(
+    prompt=prompt,
+    token_indices=token_indices,
+    guidance_scale=7.5,
+    generator=generator,
+    num_inference_steps=50,
+    max_iter_to_alter=25,
+).images
+
+image = images[0]
+image.save(f"../images/{prompt}_{seed}.png")
+```
+
+
+## StableDiffusionAttendAndExcitePipeline
+[[autodoc]] StableDiffusionAttendAndExcitePipeline
+	- all
+	- __call__

docs/source/en/api/pipelines/stable_diffusion/controlnet.mdx

@@ -0,0 +1,167 @@
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
+
+Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
+the License. You may obtain a copy of the License at
+
+http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
+an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
+specific language governing permissions and limitations under the License.
+-->
+
+# Text-to-Image Generation with ControlNet Conditioning
+
+## Overview
+
+[Adding Conditional Control to Text-to-Image Diffusion Models](https://arxiv.org/abs/2302.05543) by Lvmin Zhang and Maneesh Agrawala.
+
+Using the pretrained models we can provide control images (for example, a depth map) to control Stable Diffusion text-to-image generation so that it follows the structure of the depth image and fills in the details.
+
+The abstract of the paper is the following:
+
+*We present a neural network structure, ControlNet, to control pretrained large diffusion models to support additional input conditions. The ControlNet learns task-specific conditions in an end-to-end way, and the learning is robust even when the training dataset is small (< 50k). Moreover, training a ControlNet is as fast as fine-tuning a diffusion model, and the model can be trained on a personal devices. Alternatively, if powerful computation clusters are available, the model can scale to large amounts (millions to billions) of data. We report that large diffusion models like Stable Diffusion can be augmented with ControlNets to enable conditional inputs like edge maps, segmentation maps, keypoints, etc. This may enrich the methods to control large diffusion models and further facilitate related applications.*
+
+This model was contributed by the amazing community contributor [takuma104](https://huggingface.co/takuma104) ❤️ .
+
+Resources:
+
+* [Paper](https://arxiv.org/abs/2302.05543)
+* [Original Code](https://github.com/lllyasviel/ControlNet)
+
+## Available Pipelines:
+
+| Pipeline | Tasks | Demo
+|---|---|:---:|
+| [StableDiffusionControlNetPipeline](https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_controlnet.py) | *Text-to-Image Generation with ControlNet Conditioning* | [Colab Example](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/controlnet.ipynb)
+
+## Usage example
+
+In the following we give a simple example of how to use a *ControlNet* checkpoint with Diffusers for inference.
+The inference pipeline is the same for all pipelines:
+
+* 1. Take an image and run it through a pre-conditioning processor.
+* 2. Run the pre-processed image through the [`StableDiffusionControlNetPipeline`].
+
+Let's have a look at a simple example using the [Canny Edge ControlNet](https://huggingface.co/lllyasviel/sd-controlnet-canny).
+
+```python
+from diffusers import StableDiffusionControlNetPipeline
+from diffusers.utils import load_image
+
+# Let's load the popular vermeer image
+image = load_image(
+    "https://hf.co/datasets/huggingface/documentation-images/resolve/main/diffusers/input_image_vermeer.png"
+)
+```
+
+![img](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/input_image_vermeer.png)
+
+Next, we process the image to get the canny image. This is step *1.* - running the pre-conditioning processor. The pre-conditioning processor is different for every ControlNet. Please see the model cards of the [official checkpoints](#controlnet-with-stable-diffusion-1.5) for more information about other models.
+
+First, we need to install opencv:
+
+```
+pip install opencv-contrib-python
+```
+
+Next, let's also install all required Hugging Face libraries:
+
+```
+pip install diffusers transformers git+https://github.com/huggingface/accelerate.git
+```
+
+Then we can retrieve the canny edges of the image.
+
+```python
+import cv2
+from PIL import Image
+import numpy as np
+
+image = np.array(image)
+
+low_threshold = 100
+high_threshold = 200
+
+image = cv2.Canny(image, low_threshold, high_threshold)
+image = image[:, :, None]
+image = np.concatenate([image, image, image], axis=2)
+canny_image = Image.fromarray(image)
+```
+
+Let's take a look at the processed image.
+
+![img](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/vermeer_canny_edged.png)
+
+Now, we load the official [Stable Diffusion 1.5 Model](runwayml/stable-diffusion-v1-5) as well as the ControlNet for canny edges.
+
+```py
+from diffusers import StableDiffusionControlNetPipeline, ControlNetModel
+import torch
+
+controlnet = ControlNetModel.from_pretrained("lllyasviel/sd-controlnet-canny", torch_dtype=torch.float16)
+pipe = StableDiffusionControlNetPipeline.from_pretrained(
+    "runwayml/stable-diffusion-v1-5", controlnet=controlnet, torch_dtype=torch.float16
+)
+```
+
+To speed-up things and reduce memory, let's enable model offloading and use the fast [`UniPCMultistepScheduler`].
+
+```py
+from diffusers import UniPCMultistepScheduler
+
+pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config)
+
+# this command loads the individual model components on GPU on-demand.
+pipe.enable_model_cpu_offload()
+```
+
+Finally, we can run the pipeline:
+
+```py
+generator = torch.manual_seed(0)
+
+out_image = pipe(
+    "disco dancer with colorful lights", num_inference_steps=20, generator=generator, image=canny_image
+).images[0]
+```
+
+This should take only around 3-4 seconds on GPU (depending on hardware). The output image then looks as follows:
+
+![img](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/vermeer_disco_dancing.png)
+
+
+**Note**: To see how to run all other ControlNet checkpoints, please have a look at [ControlNet with Stable Diffusion 1.5](#controlnet-with-stable-diffusion-1.5)
+
+<!-- TODO: add space -->
+
+## Available checkpoints
+
+ControlNet requires a *control image* in addition to the text-to-image *prompt*. 
+Each pretrained model is trained using a different conditioning method that requires different images for conditioning the generated outputs. For example, Canny edge conditioning requires the control image to be the output of a Canny filter, while depth conditioning requires the control image to be a depth map. See the overview and image examples below to know more.
+
+All checkpoints can be found under the authors' namespace [lllyasviel](https://huggingface.co/lllyasviel).
+
+### ControlNet with Stable Diffusion 1.5
+
+| Model Name | Control Image Overview| Control Image Example | Generated Image Example |
+|---|---|---|---|
+|[lllyasviel/sd-controlnet-canny](https://huggingface.co/lllyasviel/sd-controlnet-canny)<br/> *Trained with canny edge detection* | A monochrome image with white edges on a black background.|<a href="https://huggingface.co/takuma104/controlnet_dev/blob/main/gen_compare/control_images/converted/control_bird_canny.png"><img width="64" style="margin:0;padding:0;" src="https://huggingface.co/takuma104/controlnet_dev/resolve/main/gen_compare/control_images/converted/control_bird_canny.png"/></a>|<a href="https://huggingface.co/takuma104/controlnet_dev/resolve/main/gen_compare/output_images/diffusers/output_bird_canny_1.png"><img width="64" src="https://huggingface.co/takuma104/controlnet_dev/resolve/main/gen_compare/output_images/diffusers/output_bird_canny_1.png"/></a>|
+|[lllyasviel/sd-controlnet-depth](https://huggingface.co/lllyasviel/sd-controlnet-depth)<br/> *Trained with Midas depth estimation*  |A grayscale image with black representing deep areas and white representing shallow areas.|<a href="https://huggingface.co/takuma104/controlnet_dev/blob/main/gen_compare/control_images/converted/control_vermeer_depth.png"><img width="64" src="https://huggingface.co/takuma104/controlnet_dev/resolve/main/gen_compare/control_images/converted/control_vermeer_depth.png"/></a>|<a href="https://huggingface.co/takuma104/controlnet_dev/resolve/main/gen_compare/output_images/diffusers/output_vermeer_depth_2.png"><img width="64" src="https://huggingface.co/takuma104/controlnet_dev/resolve/main/gen_compare/output_images/diffusers/output_vermeer_depth_2.png"/></a>|
+|[lllyasviel/sd-controlnet-hed](https://huggingface.co/lllyasviel/sd-controlnet-hed)<br/> *Trained with HED edge detection (soft edge)*  |A monochrome image with white soft edges on a black background.|<a href="https://huggingface.co/takuma104/controlnet_dev/blob/main/gen_compare/control_images/converted/control_bird_hed.png"><img width="64" src="https://huggingface.co/takuma104/controlnet_dev/resolve/main/gen_compare/control_images/converted/control_bird_hed.png"/></a>|<a href="https://huggingface.co/takuma104/controlnet_dev/resolve/main/gen_compare/output_images/diffusers/output_bird_hed_1.png"><img width="64" src="https://huggingface.co/takuma104/controlnet_dev/resolve/main/gen_compare/output_images/diffusers/output_bird_hed_1.png"/></a> |
+|[lllyasviel/sd-controlnet-mlsd](https://huggingface.co/lllyasviel/sd-controlnet-mlsd)<br/> *Trained with M-LSD line detection*  |A monochrome image composed only of white straight lines on a black background.|<a href="https://huggingface.co/takuma104/controlnet_dev/blob/main/gen_compare/control_images/converted/control_room_mlsd.png"><img width="64" src="https://huggingface.co/takuma104/controlnet_dev/resolve/main/gen_compare/control_images/converted/control_room_mlsd.png"/></a>|<a href="https://huggingface.co/takuma104/controlnet_dev/resolve/main/gen_compare/output_images/diffusers/output_room_mlsd_0.png"><img width="64" src="https://huggingface.co/takuma104/controlnet_dev/resolve/main/gen_compare/output_images/diffusers/output_room_mlsd_0.png"/></a>|
+|[lllyasviel/sd-controlnet-normal](https://huggingface.co/lllyasviel/sd-controlnet-normal)<br/> *Trained with normal map*  |A [normal mapped](https://en.wikipedia.org/wiki/Normal_mapping) image.|<a href="https://huggingface.co/takuma104/controlnet_dev/blob/main/gen_compare/control_images/converted/control_human_normal.png"><img width="64" src="https://huggingface.co/takuma104/controlnet_dev/resolve/main/gen_compare/control_images/converted/control_human_normal.png"/></a>|<a href="https://huggingface.co/takuma104/controlnet_dev/resolve/main/gen_compare/output_images/diffusers/output_human_normal_1.png"><img width="64" src="https://huggingface.co/takuma104/controlnet_dev/resolve/main/gen_compare/output_images/diffusers/output_human_normal_1.png"/></a>|
+|[lllyasviel/sd-controlnet-openpose](https://huggingface.co/lllyasviel/sd-controlnet_openpose)<br/> *Trained with OpenPose bone image*  |A [OpenPose bone](https://github.com/CMU-Perceptual-Computing-Lab/openpose) image.|<a href="https://huggingface.co/takuma104/controlnet_dev/blob/main/gen_compare/control_images/converted/control_human_openpose.png"><img width="64" src="https://huggingface.co/takuma104/controlnet_dev/resolve/main/gen_compare/control_images/converted/control_human_openpose.png"/></a>|<a href="https://huggingface.co/takuma104/controlnet_dev/resolve/main/gen_compare/output_images/diffusers/output_human_openpose_0.png"><img width="64" src="https://huggingface.co/takuma104/controlnet_dev/resolve/main/gen_compare/output_images/diffusers/output_human_openpose_0.png"/></a>|
+|[lllyasviel/sd-controlnet-scribble](https://huggingface.co/lllyasviel/sd-controlnet_scribble)<br/> *Trained with human scribbles*  |A hand-drawn monochrome image with white outlines on a black background.|<a href="https://huggingface.co/takuma104/controlnet_dev/blob/main/gen_compare/control_images/converted/control_vermeer_scribble.png"><img width="64" src="https://huggingface.co/takuma104/controlnet_dev/resolve/main/gen_compare/control_images/converted/control_vermeer_scribble.png"/></a>|<a href="https://huggingface.co/takuma104/controlnet_dev/resolve/main/gen_compare/output_images/diffusers/output_vermeer_scribble_0.png"><img width="64" src="https://huggingface.co/takuma104/controlnet_dev/resolve/main/gen_compare/output_images/diffusers/output_vermeer_scribble_0.png"/></a> |
+|[lllyasviel/sd-controlnet-seg](https://huggingface.co/lllyasviel/sd-controlnet_seg)<br/>*Trained with semantic segmentation*  |An [ADE20K](https://groups.csail.mit.edu/vision/datasets/ADE20K/)'s segmentation protocol image.|<a href="https://huggingface.co/takuma104/controlnet_dev/blob/main/gen_compare/control_images/converted/control_room_seg.png"><img width="64" src="https://huggingface.co/takuma104/controlnet_dev/resolve/main/gen_compare/control_images/converted/control_room_seg.png"/></a>|<a href="https://huggingface.co/takuma104/controlnet_dev/resolve/main/gen_compare/output_images/diffusers/output_room_seg_1.png"><img width="64" src="https://huggingface.co/takuma104/controlnet_dev/resolve/main/gen_compare/output_images/diffusers/output_room_seg_1.png"/></a> |
+
+## StableDiffusionControlNetPipeline
+[[autodoc]] StableDiffusionControlNetPipeline
+	- all
+	- __call__
+	- enable_attention_slicing
+	- disable_attention_slicing
+	- enable_vae_slicing
+	- disable_vae_slicing
+	- enable_xformers_memory_efficient_attention
+	- disable_xformers_memory_efficient_attention

docs/source/en/api/pipelines/stable_diffusion/depth2img.mdx

@@ -1,4 +1,4 @@
-<!--Copyright 2022 The HuggingFace Team. All rights reserved.
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at

docs/source/en/api/pipelines/stable_diffusion/image_variation.mdx

@@ -1,4 +1,4 @@
-<!--Copyright 2022 The HuggingFace Team. All rights reserved.
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at

docs/source/en/api/pipelines/stable_diffusion/img2img.mdx

@@ -1,4 +1,4 @@
-<!--Copyright 2022 The HuggingFace Team. All rights reserved.
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at
@@ -20,6 +20,9 @@ The original codebase can be found here: [CampVis/stable-diffusion](https://gith
 
 [`StableDiffusionImg2ImgPipeline`] is compatible with all Stable Diffusion checkpoints for [Text-to-Image](./text2img) 
 
+The pipeline uses the diffusion-denoising mechanism proposed by SDEdit ([SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations](https://arxiv.org/abs/2108.01073)
+proposed by Chenlin Meng, Yutong He, Yang Song, Jiaming Song, Jiajun Wu, Jun-Yan Zhu, Stefano Ermon).
+
 [[autodoc]] StableDiffusionImg2ImgPipeline
 	- all
 	- __call__

docs/source/en/api/pipelines/stable_diffusion/inpaint.mdx

@@ -1,4 +1,4 @@
-<!--Copyright 2022 The HuggingFace Team. All rights reserved.
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at

docs/source/en/api/pipelines/stable_diffusion/overview.mdx

@@ -1,4 +1,4 @@
-<!--Copyright 2022 The HuggingFace Team. All rights reserved.
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at
@@ -33,6 +33,8 @@ For more details about how Stable Diffusion works and how it differs from the ba
 | [StableDiffusionUpscalePipeline](./upscale) | **Experimental** – *Text-Guided Image Super-Resolution * | | Coming soon
 | [StableDiffusionLatentUpscalePipeline](./latent_upscale) | **Experimental** – *Text-Guided Image Super-Resolution * | | Coming soon
 | [StableDiffusionInstructPix2PixPipeline](./pix2pix) | **Experimental** – *Text-Based Image Editing * | | [InstructPix2Pix: Learning to Follow Image Editing Instructions](https://huggingface.co/spaces/timbrooks/instruct-pix2pix)
+| [StableDiffusionAttendAndExcitePipeline](./attend_and_excite) | **Experimental** – *Text-to-Image Generation * | | [Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models](https://huggingface.co/spaces/AttendAndExcite/Attend-and-Excite)
+| [StableDiffusionPix2PixZeroPipeline](./pix2pix_zero) | **Experimental** – *Text-Based Image Editing * | | [Zero-shot Image-to-Image Translation](https://arxiv.org/abs/2302.03027)
 
 
 

docs/source/en/api/pipelines/stable_diffusion/panorama.mdx

@@ -0,0 +1,58 @@
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
+
+Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
+the License. You may obtain a copy of the License at
+
+http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
+an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
+specific language governing permissions and limitations under the License.
+-->
+
+# MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation
+
+## Overview
+
+[MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation](https://arxiv.org/abs/2302.08113) by Omer Bar-Tal, Lior Yariv, Yaron Lipman, and Tali Dekel.
+
+The abstract of the paper is the following:
+
+*Recent advances in text-to-image generation with diffusion models present transformative capabilities in image quality. However, user controllability of the generated image, and fast adaptation to new tasks still remains an open challenge, currently mostly addressed by costly and long re-training and fine-tuning or ad-hoc adaptations to specific image generation tasks. In this work, we present MultiDiffusion, a unified framework that enables versatile and controllable image generation, using a pre-trained text-to-image diffusion model, without any further training or finetuning. At the center of our approach is a new generation process, based on an optimization task that binds together multiple diffusion generation processes with a shared set of parameters or constraints. We show that MultiDiffusion can be readily applied to generate high quality and diverse images that adhere to user-provided controls, such as desired aspect ratio (e.g., panorama), and spatial guiding signals, ranging from tight segmentation masks to bounding boxes.
+
+Resources:
+
+* [Project Page](https://multidiffusion.github.io/).
+* [Paper](https://arxiv.org/abs/2302.08113).
+* [Original Code](https://github.com/omerbt/MultiDiffusion).
+* [Demo](https://huggingface.co/spaces/weizmannscience/MultiDiffusion).
+
+## Available Pipelines:
+
+| Pipeline | Tasks | Demo
+|---|---|:---:|
+| [StableDiffusionPanoramaPipeline](https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_panorama.py) | *Text-Guided Panorama View Generation* | [🤗 Space](https://huggingface.co/spaces/weizmannscience/MultiDiffusion)) |
+
+<!-- TODO: add Colab -->
+
+## Usage example
+
+```python
+import torch
+from diffusers import StableDiffusionPanoramaPipeline, DDIMScheduler
+
+model_ckpt = "stabilityai/stable-diffusion-2-base"
+scheduler = DDIMScheduler.from_pretrained(model_ckpt, subfolder="scheduler")
+pipe = StableDiffusionPanoramaPipeline.from_pretrained(model_ckpt, scheduler=scheduler, torch_dtype=torch.float16)
+
+pipe = pipe.to("cuda")
+
+prompt = "a photo of the dolomites"
+image = pipe(prompt).images[0]
+image.save("dolomites.png")
+```
+
+## StableDiffusionPanoramaPipeline
+[[autodoc]] StableDiffusionPanoramaPipeline
+	- __call__
+	- all

docs/source/en/api/pipelines/stable_diffusion/pix2pix.mdx

@@ -60,7 +60,7 @@ def download_image(url):
 image = download_image(url)
 
 prompt = "make the mountains snowy"
-edit = pipe(prompt, image=image, num_inference_steps=20, image_guidance_scale=1.5, guidance_scale=7).images[0]
+images = pipe(prompt, image=image, num_inference_steps=20, image_guidance_scale=1.5, guidance_scale=7).images
 images[0].save("snowy_mountains.png")
 ```
 

docs/source/en/api/pipelines/stable_diffusion/pix2pix_zero.mdx

@@ -0,0 +1,291 @@
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
+
+Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
+the License. You may obtain a copy of the License at
+
+http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
+an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
+specific language governing permissions and limitations under the License.
+-->
+
+# Zero-shot Image-to-Image Translation
+
+## Overview
+
+[Zero-shot Image-to-Image Translation](https://arxiv.org/abs/2302.03027).
+
+The abstract of the paper is the following:
+
+*Large-scale text-to-image generative models have shown their remarkable ability to synthesize diverse and high-quality images. However, it is still challenging to directly apply these models for editing real images for two reasons. First, it is hard for users to come up with a perfect text prompt that accurately describes every visual detail in the input image. Second, while existing models can introduce desirable changes in certain regions, they often dramatically alter the input content and introduce unexpected changes in unwanted regions. In this work, we propose pix2pix-zero, an image-to-image translation method that can preserve the content of the original image without manual prompting. We first automatically discover editing directions that reflect desired edits in the text embedding space. To preserve the general content structure after editing, we further propose cross-attention guidance, which aims to retain the cross-attention maps of the input image throughout the diffusion process. In addition, our method does not need additional training for these edits and can directly use the existing pre-trained text-to-image diffusion model. We conduct extensive experiments and show that our method outperforms existing and concurrent works for both real and synthetic image editing.*
+
+Resources:
+
+* [Project Page](https://pix2pixzero.github.io/).
+* [Paper](https://arxiv.org/abs/2302.03027).
+* [Original Code](https://github.com/pix2pixzero/pix2pix-zero).
+* [Demo](https://huggingface.co/spaces/pix2pix-zero-library/pix2pix-zero-demo).
+
+## Tips 
+
+* The pipeline can be conditioned on real input images. Check out the code examples below to know more.
+* The pipeline exposes two arguments namely `source_embeds` and `target_embeds`
+that let you control the direction of the semantic edits in the final image to be generated. Let's say,
+you wanted to translate from "cat" to "dog". In this case, the edit direction will be "cat -> dog". To reflect
+this in the pipeline, you simply have to set the embeddings related to the phrases including "cat" to
+`source_embeds` and "dog" to `target_embeds`. Refer to the code example below for more details.
+* When you're using this pipeline from a prompt, specify the _source_ concept in the prompt. Taking
+the above example, a valid input prompt would be: "a high resolution painting of a **cat** in the style of van gough".
+* If you wanted to reverse the direction in the example above, i.e., "dog -> cat", then it's recommended to:
+    * Swap the `source_embeds` and `target_embeds`.
+    * Change the input prompt to include "dog".  
+* To learn more about how the source and target embeddings are generated, refer to the [original 
+paper](https://arxiv.org/abs/2302.03027). Below, we also provide some directions on how to generate the embeddings.
+* Note that the quality of the outputs generated with this pipeline is dependent on how good the `source_embeds` and `target_embeds` are. Please, refer to [this discussion](#generating-source-and-target-embeddings) for some suggestions on the topic.
+
+## Available Pipelines:
+
+| Pipeline | Tasks | Demo
+|---|---|:---:|
+| [StableDiffusionPix2PixZeroPipeline](https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_pix2pix_zero.py) | *Text-Based Image Editing* | [🤗 Space](https://huggingface.co/spaces/pix2pix-zero-library/pix2pix-zero-demo) |
+
+<!-- TODO: add Colab -->
+
+## Usage example
+
+### Based on an image generated with the input prompt
+
+```python
+import requests
+import torch
+
+from diffusers import DDIMScheduler, StableDiffusionPix2PixZeroPipeline
+
+
+def download(embedding_url, local_filepath):
+    r = requests.get(embedding_url)
+    with open(local_filepath, "wb") as f:
+        f.write(r.content)
+
+
+model_ckpt = "CompVis/stable-diffusion-v1-4"
+pipeline = StableDiffusionPix2PixZeroPipeline.from_pretrained(
+    model_ckpt, conditions_input_image=False, torch_dtype=torch.float16
+)
+pipeline.scheduler = DDIMScheduler.from_config(pipeline.scheduler.config)
+pipeline.to("cuda")
+
+prompt = "a high resolution painting of a cat in the style of van gogh"
+src_embs_url = "https://github.com/pix2pixzero/pix2pix-zero/raw/main/assets/embeddings_sd_1.4/cat.pt"
+target_embs_url = "https://github.com/pix2pixzero/pix2pix-zero/raw/main/assets/embeddings_sd_1.4/dog.pt"
+
+for url in [src_embs_url, target_embs_url]:
+    download(url, url.split("/")[-1])
+
+src_embeds = torch.load(src_embs_url.split("/")[-1])
+target_embeds = torch.load(target_embs_url.split("/")[-1])
+
+images = pipeline(
+    prompt,
+    source_embeds=src_embeds,
+    target_embeds=target_embeds,
+    num_inference_steps=50,
+    cross_attention_guidance_amount=0.15,
+).images
+images[0].save("edited_image_dog.png")
+```
+
+### Based on an input image
+
+When the pipeline is conditioned on an input image, we first obtain an inverted
+noise from it using a `DDIMInverseScheduler` with the help of a generated caption. Then 
+the inverted noise is used to start the generation process. 
+
+First, let's load our pipeline: 
+
+```py
+import torch
+from transformers import BlipForConditionalGeneration, BlipProcessor
+from diffusers import DDIMScheduler, DDIMInverseScheduler, StableDiffusionPix2PixZeroPipeline
+
+captioner_id = "Salesforce/blip-image-captioning-base"
+processor = BlipProcessor.from_pretrained(captioner_id)
+model = BlipForConditionalGeneration.from_pretrained(captioner_id, torch_dtype=torch.float16, low_cpu_mem_usage=True)
+
+sd_model_ckpt = "CompVis/stable-diffusion-v1-4"
+pipeline = StableDiffusionPix2PixZeroPipeline.from_pretrained(
+    sd_model_ckpt,
+    caption_generator=model,
+    caption_processor=processor,
+    torch_dtype=torch.float16,
+    safety_checker=None,
+)
+pipeline.scheduler = DDIMScheduler.from_config(pipeline.scheduler.config)
+pipeline.inverse_scheduler = DDIMInverseScheduler.from_config(pipeline.scheduler.config)
+pipeline.enable_model_cpu_offload()
+```
+
+Then, we load an input image for conditioning and obtain a suitable caption for it: 
+
+```py
+import requests
+from PIL import Image
+
+img_url = "https://github.com/pix2pixzero/pix2pix-zero/raw/main/assets/test_images/cats/cat_6.png"
+raw_image = Image.open(requests.get(img_url, stream=True).raw).convert("RGB").resize((512, 512))
+caption = pipeline.generate_caption(raw_image)
+```
+
+Then we employ the generated caption and the input image to get the inverted noise: 
+
+```py 
+generator = torch.manual_seed(0)
+inv_latents = pipeline.invert(caption, image=raw_image, generator=generator).latents
+```
+
+Now, generate the image with edit directions: 
+
+```py
+# See the "Generating source and target embeddings" section below to
+# automate the generation of these captions with a pre-trained model like Flan-T5 as explained below.
+source_prompts = ["a cat sitting on the street", "a cat playing in the field", "a face of a cat"]
+target_prompts = ["a dog sitting on the street", "a dog playing in the field", "a face of a dog"]
+
+source_embeds = pipeline.get_embeds(source_prompts, batch_size=2)
+target_embeds = pipeline.get_embeds(target_prompts, batch_size=2)
+
+
+image = pipeline(
+    caption,
+    source_embeds=source_embeds,
+    target_embeds=target_embeds,
+    num_inference_steps=50,
+    cross_attention_guidance_amount=0.15,
+    generator=generator,
+    latents=inv_latents,
+    negative_prompt=caption,
+).images[0]
+image.save("edited_image.png")
+```
+
+## Generating source and target embeddings 
+
+The authors originally used the [GPT-3 API](https://openai.com/api/) to generate the source and target captions for discovering
+edit directions. However, we can also leverage open source and public models for the same purpose.
+Below, we provide an end-to-end example with the [Flan-T5](https://huggingface.co/docs/transformers/model_doc/flan-t5) model
+for generating captions and [CLIP](https://huggingface.co/docs/transformers/model_doc/clip) for
+computing embeddings on the generated captions.  
+
+**1. Load the generation model**:
+
+```py
+import torch
+from transformers import AutoTokenizer, T5ForConditionalGeneration
+
+tokenizer = AutoTokenizer.from_pretrained("google/flan-t5-xl")
+model = T5ForConditionalGeneration.from_pretrained("google/flan-t5-xl", device_map="auto", torch_dtype=torch.float16)
+```
+
+**2. Construct a starting prompt**: 
+
+```py
+source_concept = "cat"
+target_concept = "dog"
+
+source_text = f"Provide a caption for images containing a {source_concept}. "
+"The captions should be in English and should be no longer than 150 characters."
+
+target_text = f"Provide a caption for images containing a {target_concept}. "
+"The captions should be in English and should be no longer than 150 characters."
+```
+
+Here, we're interested in the "cat -> dog" direction. 
+
+**3. Generate captions**:
+
+We can use a utility like so for this purpose. 
+
+```py
+def generate_captions(input_prompt):
+    input_ids = tokenizer(input_prompt, return_tensors="pt").input_ids.to("cuda")
+
+    outputs = model.generate(
+        input_ids, temperature=0.8, num_return_sequences=16, do_sample=True, max_new_tokens=128, top_k=10
+    )
+    return tokenizer.batch_decode(outputs, skip_special_tokens=True)
+```
+
+And then we just call it to generate our captions:
+
+```py
+source_captions = generate_captions(source_text)
+target_captions = generate_captions(target_concept)
+```
+
+We encourage you to play around with the different parameters supported by the
+`generate()` method ([documentation](https://huggingface.co/docs/transformers/main/en/main_classes/text_generation#transformers.generation_tf_utils.TFGenerationMixin.generate)) for the generation quality you are looking for.
+
+**4. Load the embedding model**: 
+
+Here, we need to use the same text encoder model used by the subsequent Stable Diffusion model.
+
+```py 
+from diffusers import StableDiffusionPix2PixZeroPipeline 
+
+pipeline = StableDiffusionPix2PixZeroPipeline.from_pretrained(
+    "CompVis/stable-diffusion-v1-4", torch_dtype=torch.float16
+)
+pipeline = pipeline.to("cuda")
+tokenizer = pipeline.tokenizer
+text_encoder = pipeline.text_encoder
+```
+
+**5. Compute embeddings**:
+
+```py 
+import torch 
+
+def embed_captions(sentences, tokenizer, text_encoder, device="cuda"):
+    with torch.no_grad():
+        embeddings = []
+        for sent in sentences:
+            text_inputs = tokenizer(
+                sent,
+                padding="max_length",
+                max_length=tokenizer.model_max_length,
+                truncation=True,
+                return_tensors="pt",
+            )
+            text_input_ids = text_inputs.input_ids
+            prompt_embeds = text_encoder(text_input_ids.to(device), attention_mask=None)[0]
+            embeddings.append(prompt_embeds)
+    return torch.concatenate(embeddings, dim=0).mean(dim=0).unsqueeze(0)
+
+source_embeddings = embed_captions(source_captions, tokenizer, text_encoder)
+target_embeddings = embed_captions(target_captions, tokenizer, text_encoder)
+```
+
+And you're done! [Here](https://colab.research.google.com/drive/1tz2C1EdfZYAPlzXXbTnf-5PRBiR8_R1F?usp=sharing) is a Colab Notebook that you can use to interact with the entire process.
+
+Now, you can use these embeddings directly while calling the pipeline: 
+
+```py
+from diffusers import DDIMScheduler
+
+pipeline.scheduler = DDIMScheduler.from_config(pipeline.scheduler.config)
+
+images = pipeline(
+    prompt,
+    source_embeds=source_embeddings,
+    target_embeds=target_embeddings,
+    num_inference_steps=50,
+    cross_attention_guidance_amount=0.15,
+).images
+images[0].save("edited_image_dog.png")
+```
+
+## StableDiffusionPix2PixZeroPipeline
+[[autodoc]] StableDiffusionPix2PixZeroPipeline
+	- __call__
+	- all

docs/source/en/api/pipelines/stable_diffusion/self_attention_guidance.mdx

@@ -0,0 +1,64 @@
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
+
+Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
+the License. You may obtain a copy of the License at
+
+http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
+an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
+specific language governing permissions and limitations under the License.
+-->
+
+# Self-Attention Guidance (SAG)
+
+## Overview
+
+[Self-Attention Guidance](https://arxiv.org/abs/2210.00939) by Susung Hong et al.
+
+The abstract of the paper is the following:
+
+*Denoising diffusion models (DDMs) have been drawing much attention for their appreciable sample quality and diversity. Despite their remarkable performance, DDMs remain black boxes on which further study is necessary to take a profound step. Motivated by this, we delve into the design of conventional U-shaped diffusion models. More specifically, we investigate the self-attention modules within these models through carefully designed experiments and explore their characteristics. In addition, inspired by the studies that substantiate the effectiveness of the guidance schemes, we present plug-and-play diffusion guidance, namely Self-Attention Guidance (SAG), that can drastically boost the performance of existing diffusion models. Our method, SAG, extracts the intermediate attention map from a diffusion model at every iteration and selects tokens above a certain attention score for masking and blurring to obtain a partially blurred input. Subsequently, we measure the dissimilarity between the predicted noises obtained from feeding the blurred and original input to the diffusion model and leverage it as guidance. With this guidance, we observe apparent improvements in a wide range of diffusion models, e.g., ADM, IDDPM, and Stable Diffusion, and show that the results further improve by combining our method with the conventional guidance scheme. We provide extensive ablation studies to verify our choices.*
+
+Resources:
+
+* [Project Page](https://ku-cvlab.github.io/Self-Attention-Guidance).
+* [Paper](https://arxiv.org/abs/2210.00939).
+* [Original Code](https://github.com/KU-CVLAB/Self-Attention-Guidance).
+* [Demo](https://colab.research.google.com/github/SusungHong/Self-Attention-Guidance/blob/main/SAG_Stable.ipynb).
+
+
+## Available Pipelines:
+
+| Pipeline | Tasks | Demo
+|---|---|:---:|
+| [StableDiffusionSAGPipeline](https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_sag.py) | *Text-to-Image Generation* | [Colab](https://colab.research.google.com/github/SusungHong/Self-Attention-Guidance/blob/main/SAG_Stable.ipynb) |
+
+## Usage example
+
+```python
+import torch
+from diffusers import StableDiffusionSAGPipeline
+from accelerate.utils import set_seed
+
+pipe = StableDiffusionSAGPipeline.from_pretrained("CompVis/stable-diffusion-v1-4", torch_dtype=torch.float16)
+pipe = pipe.to("cuda")
+
+seed = 8978
+prompt = "."
+guidance_scale = 7.5
+num_images_per_prompt = 1
+
+sag_scale = 1.0
+
+set_seed(seed)
+images = pipe(
+    prompt, num_images_per_prompt=num_images_per_prompt, guidance_scale=guidance_scale, sag_scale=sag_scale
+).images
+images[0].save("example.png")
+```
+
+## StableDiffusionSAGPipeline
+[[autodoc]] StableDiffusionSAGPipeline
+	- __call__
+	- all

docs/source/en/api/pipelines/stable_diffusion/text2img.mdx

@@ -1,4 +1,4 @@
-<!--Copyright 2022 The HuggingFace Team. All rights reserved.
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at
@@ -17,7 +17,7 @@ specific language governing permissions and limitations under the License.
 The Stable Diffusion model was created by the researchers and engineers from [CompVis](https://github.com/CompVis), [Stability AI](https://stability.ai/), [runway](https://github.com/runwayml), and [LAION](https://laion.ai/). The [`StableDiffusionPipeline`] is capable of generating photo-realistic images given any text input using Stable Diffusion.
 
 The original codebase can be found here: 
-- *Stable Diffusion V1*: [CampVis/stable-diffusion](https://github.com/CompVis/stable-diffusion)
+- *Stable Diffusion V1*: [CompVis/stable-diffusion](https://github.com/CompVis/stable-diffusion)
 - *Stable Diffusion v2*: [Stability-AI/stablediffusion](https://github.com/Stability-AI/stablediffusion)
 
 Available Checkpoints are:
@@ -36,4 +36,6 @@ Available Checkpoints are:
 	- enable_vae_slicing
 	- disable_vae_slicing
 	- enable_xformers_memory_efficient_attention
-	- disable_xformers_memory_efficient_attention
+	- disable_xformers_memory_efficient_attention
+	- enable_vae_tiling
+	- disable_vae_tiling

docs/source/en/api/pipelines/stable_diffusion/upscale.mdx

@@ -1,4 +1,4 @@
-<!--Copyright 2022 The HuggingFace Team. All rights reserved.
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at

docs/source/en/api/pipelines/stable_diffusion_2.mdx

@@ -1,4 +1,4 @@
-<!--Copyright 2022 The HuggingFace Team. All rights reserved.
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at

docs/source/en/api/pipelines/stable_diffusion_safe.mdx

@@ -1,4 +1,4 @@
-<!--Copyright 2022 The HuggingFace Team. All rights reserved.
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at
@@ -24,7 +24,7 @@ The abstract of the paper is the following:
 
 | Pipeline | Tasks | Colab | Demo
 |---|---|:---:|:---:|
-| [pipeline_stable_diffusion_safe.py](https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/stable_diffusion_safe/pipeline_stable_diffusion_safe.py) | *Text-to-Image Generation* |  [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/ml-research/safe-latent-diffusion/blob/main/examples/Safe%20Latent%20Diffusion.ipynb) | -
+| [pipeline_stable_diffusion_safe.py](https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/stable_diffusion_safe/pipeline_stable_diffusion_safe.py) | *Text-to-Image Generation* |  [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/ml-research/safe-latent-diffusion/blob/main/examples/Safe%20Latent%20Diffusion.ipynb) | [![Huggingface Spaces](https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Spaces-blue)](https://huggingface.co/spaces/AIML-TUDA/unsafe-vs-safe-stable-diffusion)
 
 ## Tips
 
@@ -58,7 +58,7 @@ You may use the 4 configurations defined in the [Safe Latent Diffusion paper](ht
 >>> out = pipeline(prompt=prompt, **SafetyConfig.MAX)
 ```
 
-The following configurations are available: `SafetyConfig.WEAK`, `SafetyConfig.MEDIUM`, `SafetyConfig.STRONg`, and `SafetyConfig.MAX`.
+The following configurations are available: `SafetyConfig.WEAK`, `SafetyConfig.MEDIUM`, `SafetyConfig.STRONG`, and `SafetyConfig.MAX`.
 
 ### How to load and use different schedulers.
 

docs/source/en/api/pipelines/stable_unclip.mdx

@@ -0,0 +1,97 @@
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
+
+Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
+the License. You may obtain a copy of the License at
+
+http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
+an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
+specific language governing permissions and limitations under the License.
+-->
+
+# Stable unCLIP
+
+Stable unCLIP checkpoints are finetuned from [stable diffusion 2.1](./stable_diffusion_2) checkpoints to condition on CLIP image embeddings.
+Stable unCLIP also still conditions on text embeddings. Given the two separate conditionings, stable unCLIP can be used
+for text guided image variation. When combined with an unCLIP prior, it can also be used for full text to image generation.
+
+## Tips
+
+Stable unCLIP takes a `noise_level` as input during inference. `noise_level` determines how much noise is added 
+to the image embeddings. A higher `noise_level` increases variation in the final un-noised images. By default, 
+we do not add any additional noise to the image embeddings i.e. `noise_level = 0`.
+
+### Available checkpoints:
+
+TODO
+
+### Text-to-Image Generation
+
+```python
+import torch
+from diffusers import StableUnCLIPPipeline
+
+pipe = StableUnCLIPPipeline.from_pretrained(
+    "fusing/stable-unclip-2-1-l", torch_dtype=torch.float16
+)  # TODO update model path
+pipe = pipe.to("cuda")
+
+prompt = "a photo of an astronaut riding a horse on mars"
+images = pipe(prompt).images
+images[0].save("astronaut_horse.png")
+```
+
+
+### Text guided Image-to-Image Variation
+
+```python
+import requests
+import torch
+from PIL import Image
+from io import BytesIO
+
+from diffusers import StableUnCLIPImg2ImgPipeline
+
+pipe = StableUnCLIPImg2ImgPipeline.from_pretrained(
+    "fusing/stable-unclip-2-1-l-img2img", torch_dtype=torch.float16
+)  # TODO update model path
+pipe = pipe.to("cuda")
+
+url = "https://raw.githubusercontent.com/CompVis/stable-diffusion/main/assets/stable-samples/img2img/sketch-mountains-input.jpg"
+
+response = requests.get(url)
+init_image = Image.open(BytesIO(response.content)).convert("RGB")
+init_image = init_image.resize((768, 512))
+
+prompt = "A fantasy landscape, trending on artstation"
+
+images = pipe(prompt, init_image).images
+images[0].save("fantasy_landscape.png")
+```
+
+### StableUnCLIPPipeline
+
+[[autodoc]] StableUnCLIPPipeline
+	- all
+	- __call__
+	- enable_attention_slicing
+	- disable_attention_slicing
+	- enable_vae_slicing
+	- disable_vae_slicing
+	- enable_xformers_memory_efficient_attention
+	- disable_xformers_memory_efficient_attention
+
+
+### StableUnCLIPImg2ImgPipeline
+
+[[autodoc]] StableUnCLIPImg2ImgPipeline
+	- all
+	- __call__
+	- enable_attention_slicing
+	- disable_attention_slicing
+	- enable_vae_slicing
+	- disable_vae_slicing
+	- enable_xformers_memory_efficient_attention
+	- disable_xformers_memory_efficient_attention
+    

docs/source/en/api/pipelines/stochastic_karras_ve.mdx

@@ -1,4 +1,4 @@
-<!--Copyright 2022 The HuggingFace Team. All rights reserved.
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at

docs/source/en/api/pipelines/unclip.mdx

@@ -1,4 +1,4 @@
-<!--Copyright 2022 The HuggingFace Team. All rights reserved.
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at
 http://www.apache.org/licenses/LICENSE-2.0

docs/source/en/api/pipelines/versatile_diffusion.mdx

@@ -1,4 +1,4 @@
-<!--Copyright 2022 The HuggingFace Team. All rights reserved.
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at

docs/source/en/api/pipelines/vq_diffusion.mdx

@@ -1,4 +1,4 @@
-<!--Copyright 2022 The HuggingFace Team. All rights reserved.
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at

docs/source/en/api/schedulers/ddim.mdx

@@ -1,4 +1,4 @@
-<!--Copyright 2022 The HuggingFace Team. All rights reserved.
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at

docs/source/en/api/schedulers/ddim_inverse.mdx

@@ -0,0 +1,21 @@
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
+
+Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
+the License. You may obtain a copy of the License at
+
+http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
+an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
+specific language governing permissions and limitations under the License.
+-->
+
+# Inverse Denoising Diffusion Implicit Models (DDIMInverse)
+
+## Overview
+
+This scheduler is the inverted scheduler of [Denoising Diffusion Implicit Models](https://arxiv.org/abs/2010.02502) (DDIM) by Jiaming Song, Chenlin Meng and Stefano Ermon.
+The implementation is mostly based on the DDIM inversion definition of [Null-text Inversion for Editing Real Images using Guided Diffusion Models](https://arxiv.org/pdf/2211.09794.pdf)
+
+## DDIMInverseScheduler
+[[autodoc]] DDIMInverseScheduler

docs/source/en/api/schedulers/ddpm.mdx

@@ -1,4 +1,4 @@
-<!--Copyright 2022 The HuggingFace Team. All rights reserved.
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at

docs/source/en/api/schedulers/deis.mdx

@@ -1,4 +1,4 @@
-<!--Copyright 2022 The HuggingFace Team. All rights reserved.
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at

docs/source/en/api/schedulers/dpm_discrete.mdx

@@ -1,4 +1,4 @@
-<!--Copyright 2022 The HuggingFace Team. All rights reserved.
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at

docs/source/en/api/schedulers/dpm_discrete_ancestral.mdx

@@ -1,4 +1,4 @@
-<!--Copyright 2022 The HuggingFace Team. All rights reserved.
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at

docs/source/en/api/schedulers/euler.mdx

@@ -1,4 +1,4 @@
-<!--Copyright 2022 The HuggingFace Team. All rights reserved.
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at

docs/source/en/api/schedulers/euler_ancestral.mdx

@@ -1,4 +1,4 @@
-<!--Copyright 2022 The HuggingFace Team. All rights reserved.
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at

docs/source/en/api/schedulers/heun.mdx

@@ -1,4 +1,4 @@
-<!--Copyright 2022 The HuggingFace Team. All rights reserved.
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at

docs/source/en/api/schedulers/ipndm.mdx

@@ -1,4 +1,4 @@
-<!--Copyright 2022 The HuggingFace Team. All rights reserved.
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at

docs/source/en/api/schedulers/lms_discrete.mdx

@@ -1,4 +1,4 @@
-<!--Copyright 2022 The HuggingFace Team. All rights reserved.
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at

docs/source/en/api/schedulers/multistep_dpm_solver.mdx

@@ -1,4 +1,4 @@
-<!--Copyright 2022 The HuggingFace Team. All rights reserved.
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at

docs/source/en/api/schedulers/overview.mdx

@@ -1,4 +1,4 @@
-<!--Copyright 2022 The HuggingFace Team. All rights reserved.
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at
@@ -43,11 +43,12 @@ To this end, the design of schedulers is such that:
 
 The following table summarizes all officially supported schedulers, their corresponding paper
 
-
 | Scheduler | Paper |
 |---|---|
 | [ddim](./ddim) | [**Denoising Diffusion Implicit Models**](https://arxiv.org/abs/2010.02502) |
+| [ddim_inverse](./ddim_inverse) | [**Denoising Diffusion Implicit Models**](https://arxiv.org/abs/2010.02502) |
 | [ddpm](./ddpm) | [**Denoising Diffusion Probabilistic Models**](https://arxiv.org/abs/2006.11239) |
+| [deis](./deis) | [**DEISMultistepScheduler**](https://arxiv.org/abs/2204.13902) |
 | [singlestep_dpm_solver](./singlestep_dpm_solver) | [**Singlestep DPM-Solver**](https://arxiv.org/abs/2206.00927) |
 | [multistep_dpm_solver](./multistep_dpm_solver) | [**Multistep DPM-Solver**](https://arxiv.org/abs/2206.00927) |
 | [heun](./heun) | [**Heun scheduler inspired by Karras et. al paper**](https://arxiv.org/abs/2206.00364) |
@@ -62,6 +63,7 @@ The following table summarizes all officially supported schedulers, their corres
 | [euler](./euler) | [**Euler scheduler**](https://arxiv.org/abs/2206.00364) |
 | [euler_ancestral](./euler_ancestral) | [**Euler Ancestral scheduler**](https://github.com/crowsonkb/k-diffusion/blob/481677d114f6ea445aa009cf5bd7a9cdee909e47/k_diffusion/sampling.py#L72) |
 | [vq_diffusion](./vq_diffusion) | [**VQDiffusionScheduler**](https://arxiv.org/abs/2111.14822) |
+| [unipc](./unipc) | [**UniPCMultistepScheduler**](https://arxiv.org/abs/2302.04867) |
 | [repaint](./repaint) | [**RePaint scheduler**](https://arxiv.org/abs/2201.09865) |
 
 ## API
@@ -83,4 +85,8 @@ The class [`SchedulerOutput`] contains the outputs from any schedulers `step(...
 
 ### KarrasDiffusionSchedulers
 
+`KarrasDiffusionSchedulers` encompasses the main generalization of schedulers in Diffusers. The schedulers in this class are distinguished, at a high level, by their noise sampling strategy; the type of network and scaling; and finally the training strategy or how the loss is weighed.
+
+The different schedulers, depending on the type of ODE solver, fall into the above taxonomy and provide a good abstraction for the design of the main schedulers implemented in Diffusers. The schedulers in this class are given below:
+
 [[autodoc]] schedulers.scheduling_utils.KarrasDiffusionSchedulers

docs/source/en/api/schedulers/pndm.mdx

@@ -1,4 +1,4 @@
-<!--Copyright 2022 The HuggingFace Team. All rights reserved.
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at

docs/source/en/api/schedulers/repaint.mdx

@@ -1,4 +1,4 @@
-<!--Copyright 2022 The HuggingFace Team. All rights reserved.
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at

docs/source/en/api/schedulers/score_sde_ve.mdx

@@ -1,4 +1,4 @@
-<!--Copyright 2022 The HuggingFace Team. All rights reserved.
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at

docs/source/en/api/schedulers/score_sde_vp.mdx

@@ -1,4 +1,4 @@
-<!--Copyright 2022 The HuggingFace Team. All rights reserved.
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at

docs/source/en/api/schedulers/singlestep_dpm_solver.mdx

@@ -1,4 +1,4 @@
-<!--Copyright 2022 The HuggingFace Team. All rights reserved.
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at

docs/source/en/api/schedulers/stochastic_karras_ve.mdx

@@ -1,4 +1,4 @@
-<!--Copyright 2022 The HuggingFace Team. All rights reserved.
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at

docs/source/en/api/schedulers/unipc.mdx

@@ -0,0 +1,24 @@
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
+
+Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
+the License. You may obtain a copy of the License at
+
+http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
+an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
+specific language governing permissions and limitations under the License.
+-->
+
+# UniPC
+
+## Overview
+
+UniPC is a training-free framework designed for the fast sampling of diffusion models, which consists of a corrector (UniC) and a predictor (UniP) that share a unified analytical form and support arbitrary orders.
+
+For more details about the method, please refer to the [[paper]](https://arxiv.org/abs/2302.04867) and the [[code]](https://github.com/wl-zhao/UniPC).
+
+Fast Sampling of Diffusion Models with Exponential Integrator.
+
+## UniPCMultistepScheduler
+[[autodoc]] UniPCMultistepScheduler

docs/source/en/api/schedulers/vq_diffusion.mdx

@@ -1,4 +1,4 @@
-<!--Copyright 2022 The HuggingFace Team. All rights reserved.
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at

docs/source/en/conceptual/contribution.mdx

@@ -1,4 +1,4 @@
-<!--Copyright 2022 The HuggingFace Team. All rights reserved.
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at
@@ -177,7 +177,7 @@ Follow these steps to start contributing ([supported Python versions](https://gi
    $ make style
    ```
 
-   🧨 Diffusers also uses `flake8` and a few custom scripts to check for coding mistakes. Quality
+   🧨 Diffusers also uses `ruff` and a few custom scripts to check for coding mistakes. Quality
    control runs in CI, however you can also run the same checks with:
 
    ```bash

docs/source/en/conceptual/ethical_guidelines.mdx

@@ -0,0 +1,49 @@
+# 🧨 Diffusers’ Ethical Guidelines
+
+## Preamble
+
+[Diffusers](https://huggingface.co/docs/diffusers/index) provides pre-trained diffusion models and serves as a modular toolbox for inference and training. 
+
+Given its real case applications in the world and potential negative impacts on society, we think it is important to provide the project with ethical guidelines to guide the development, users’ contributions, and usage of the Diffusers library.
+
+The risks associated with using this technology are still being examined, but to name a few: copyrights issues for artists; deep-fake exploitation; sexual content generation in inappropriate contexts; non-consensual impersonation; harmful social biases perpetuating the oppression of marginalized groups.
+We will keep tracking risks and adapt the following guidelines based on the community's responsiveness and valuable feedback.
+
+
+## Scope
+
+The Diffusers community will apply the following ethical guidelines to the project’s development and help coordinate how the community will integrate the contributions, especially concerning sensitive topics related to ethical concerns.
+
+
+## Ethical guidelines
+
+The following ethical guidelines apply generally, but we will primarily implement them when dealing with ethically sensitive issues while making a technical choice. Furthermore, we commit to adapting those ethical principles over time following emerging harms related to the state of the art of the technology in question.
+
+- **Transparency**: we are committed to being transparent in managing PRs, explaining our choices to users, and making technical decisions.
+
+- **Consistency**: we are committed to guaranteeing our users the same level of attention in project management, keeping it technically stable and consistent.
+
+- **Simplicity**: with a desire to make it easy to use and exploit the Diffusers library, we are committed to keeping the project’s goals lean and coherent.
+
+- **Accessibility**: the Diffusers project helps lower the entry bar for contributors who can help run it even without technical expertise. Doing so makes research artifacts more accessible to the community.
+
+- **Reproducibility**: we aim to be transparent about the reproducibility of upstream code, models, and datasets when made available through the Diffusers library.
+
+- **Responsibility**: as a community and through teamwork, we hold a collective responsibility to our users by anticipating and mitigating this technology's potential risks and dangers.
+
+
+## Examples of implementations: Safety features and Mechanisms
+
+The team works daily to make the technical and non-technical tools available to deal with the potential ethical and social risks associated with diffusion technology. Moreover, the community's input is invaluable in ensuring these features' implementation and raising awareness with us. 
+
+- [**Community tab**](https://huggingface.co/docs/hub/repositories-pull-requests-discussions): it enables the community to discuss and better collaborate on a project.
+
+- **Bias exploration and evaluation**: the Hugging Face team provides a [space](https://huggingface.co/spaces/society-ethics/DiffusionBiasExplorer) to demonstrate the biases in Stable Diffusion interactively. In this sense, we support and encourage bias explorers and evaluations.
+
+- **Encouraging safety in deployment**
+
+  - [**Safe Stable Diffusion**](https://huggingface.co/docs/diffusers/main/en/api/pipelines/stable_diffusion_safe): It mitigates the well-known issue that models, like Stable Diffusion, that are trained on unfiltered, web-crawled datasets tend to suffer from inappropriate degeneration. Related paper: [Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Models](https://arxiv.org/abs/2211.05105).
+
+- **Staged released on the Hub**: in particularly sensitive situations, access to some repositories should be restricted. This staged release is an intermediary step that allows the repository’s authors to have more control over its use.
+
+- **Licensing**: [OpenRAILs](https://huggingface.co/blog/open_rail), a new type of licensing, allow us to ensure free access while having a set of restrictions that ensure more responsible use. 

docs/source/en/conceptual/philosophy.mdx

@@ -1,4 +1,4 @@
-<!--Copyright 2022 The HuggingFace Team. All rights reserved.
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at

docs/source/en/index.mdx

@@ -1,4 +1,4 @@
-<!--Copyright 2022 The HuggingFace Team. All rights reserved.
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at
@@ -36,6 +36,7 @@ available a colab notebook to directly try them out.
 |---|---|:---:|:---:|
 | [alt_diffusion](./api/pipelines/alt_diffusion) | [**AltDiffusion**](https://arxiv.org/abs/2211.06679) | Image-to-Image Text-Guided Generation |
 | [audio_diffusion](./api/pipelines/audio_diffusion) | [**Audio Diffusion**](https://github.com/teticio/audio-diffusion.git) | Unconditional Audio Generation | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/teticio/audio-diffusion/blob/master/notebooks/audio_diffusion_pipeline.ipynb)
+| [controlnet](./api/pipelines/stable_diffusion/controlnet) | [**ControlNet with Stable Diffusion**](https://arxiv.org/abs/2302.05543) | Image-to-Image Text-Guided Generation | [![Open In Colab](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/controlnet.ipynb)
 | [cycle_diffusion](./api/pipelines/cycle_diffusion) | [**Cycle Diffusion**](https://arxiv.org/abs/2210.05559) | Image-to-Image Text-Guided Generation |
 | [dance_diffusion](./api/pipelines/dance_diffusion) | [**Dance Diffusion**](https://github.com/williamberman/diffusers.git) | Unconditional Audio Generation |
 | [ddpm](./api/pipelines/ddpm) | [**Denoising Diffusion Probabilistic Models**](https://arxiv.org/abs/2006.11239) | Unconditional Image Generation |
@@ -47,13 +48,24 @@ available a colab notebook to directly try them out.
 | [pndm](./api/pipelines/pndm) | [**Pseudo Numerical Methods for Diffusion Models on Manifolds**](https://arxiv.org/abs/2202.09778) | Unconditional Image Generation | 
 | [score_sde_ve](./api/pipelines/score_sde_ve) | [**Score-Based Generative Modeling through Stochastic Differential Equations**](https://openreview.net/forum?id=PxTIG12RRHS) | Unconditional Image Generation | 
 | [score_sde_vp](./api/pipelines/score_sde_vp) | [**Score-Based Generative Modeling through Stochastic Differential Equations**](https://openreview.net/forum?id=PxTIG12RRHS) | Unconditional Image Generation | 
-| [stable_diffusion](./api/pipelines/stable_diffusion/text2img) | [**Stable Diffusion**](https://stability.ai/blog/stable-diffusion-public-release) | Text-to-Image Generation | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/training_example.ipynb)
-| [stable_diffusion](./api/pipelines/stable_diffusion/img2img) | [**Stable Diffusion**](https://stability.ai/blog/stable-diffusion-public-release) | Image-to-Image Text-Guided Generation | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/image_2_image_using_diffusers.ipynb)
-| [stable_diffusion](./api/pipelines/stable_diffusion/inpaint) | [**Stable Diffusion**](https://stability.ai/blog/stable-diffusion-public-release) | Text-Guided Image Inpainting | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/in_painting_with_stable_diffusion_using_diffusers.ipynb)
-| [stable_diffusion_2](./api/pipelines/stable_diffusion_2) | [**Stable Diffusion 2**](https://stability.ai/blog/stable-diffusion-v2-release) | Text-to-Image Generation | 
+| [semantic_stable_diffusion](./api/pipelines/semantic_stable_diffusion) | [**Semantic Guidance**](https://arxiv.org/abs/2301.12247) | Text-Guided Generation | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/ml-research/semantic-image-editing/blob/main/examples/SemanticGuidance.ipynb)
+| [stable_diffusion_text2img](./api/pipelines/stable_diffusion/text2img) | [**Stable Diffusion**](https://stability.ai/blog/stable-diffusion-public-release) | Text-to-Image Generation | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/training_example.ipynb)
+| [stable_diffusion_img2img](./api/pipelines/stable_diffusion/img2img) | [**Stable Diffusion**](https://stability.ai/blog/stable-diffusion-public-release) | Image-to-Image Text-Guided Generation | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/image_2_image_using_diffusers.ipynb)
+| [stable_diffusion_inpaint](./api/pipelines/stable_diffusion/inpaint) | [**Stable Diffusion**](https://stability.ai/blog/stable-diffusion-public-release) | Text-Guided Image Inpainting | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/in_painting_with_stable_diffusion_using_diffusers.ipynb)
+| [stable_diffusion_panorama](./api/pipelines/stable_diffusion/panorama) | [**MultiDiffusion**](https://multidiffusion.github.io/) | Text-to-Panorama Generation |
+| [stable_diffusion_pix2pix](./api/pipelines/stable_diffusion/pix2pix) | [**InstructPix2Pix**](https://github.com/timothybrooks/instruct-pix2pix) | Text-Guided Image Editing| 
+| [stable_diffusion_pix2pix_zero](./api/pipelines/stable_diffusion/pix2pix_zero) | [**Zero-shot Image-to-Image Translation**](https://pix2pixzero.github.io/) | Text-Guided Image Editing | 
+| [stable_diffusion_attend_and_excite](./api/pipelines/stable_diffusion/attend_and_excite) | [**Attend and Excite for Stable Diffusion**](https://attendandexcite.github.io/Attend-and-Excite/) | Text-to-Image Generation | 
+| [stable_diffusion_self_attention_guidance](./api/pipelines/stable_diffusion/self_attention_guidance) | [**Self-Attention Guidance**](https://ku-cvlab.github.io/Self-Attention-Guidance) | Text-to-Image Generation | 
+| [stable_diffusion_image_variation](./stable_diffusion/image_variation) | [**Stable Diffusion Image Variations**](https://github.com/LambdaLabsML/lambda-diffusers#stable-diffusion-image-variations) | Image-to-Image Generation |
+| [stable_diffusion_latent_upscale](./stable_diffusion/latent_upscale) | [**Stable Diffusion Latent Upscaler**](https://twitter.com/StabilityAI/status/1590531958815064065) | Text-Guided Super Resolution Image-to-Image |
+| [stable_diffusion_2](./api/pipelines/stable_diffusion_2) | [**Stable Diffusion 2**](https://stability.ai/blog/stable-diffusion-v2-release) | Text-to-Image Generation |
 | [stable_diffusion_2](./api/pipelines/stable_diffusion_2) | [**Stable Diffusion 2**](https://stability.ai/blog/stable-diffusion-v2-release) | Text-Guided Image Inpainting | 
+| [stable_diffusion_2](./api/pipelines/stable_diffusion_2) | [**Depth-Conditional Stable Diffusion**](https://github.com/Stability-AI/stablediffusion#depth-conditional-stable-diffusion) | Depth-to-Image Generation | 
 | [stable_diffusion_2](./api/pipelines/stable_diffusion_2) | [**Stable Diffusion 2**](https://stability.ai/blog/stable-diffusion-v2-release) | Text-Guided Super Resolution Image-to-Image |
 | [stable_diffusion_safe](./api/pipelines/stable_diffusion_safe) | [**Safe Stable Diffusion**](https://arxiv.org/abs/2211.05105) | Text-Guided Generation | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/ml-research/safe-latent-diffusion/blob/main/examples/Safe%20Latent%20Diffusion.ipynb)
+| [stable_unclip](./stable_unclip) | **Stable unCLIP** | Text-to-Image Generation |
+| [stable_unclip](./stable_unclip) | **Stable unCLIP** | Image-to-Image Text-Guided Generation |
 | [stochastic_karras_ve](./api/pipelines/stochastic_karras_ve) | [**Elucidating the Design Space of Diffusion-Based Generative Models**](https://arxiv.org/abs/2206.00364) | Unconditional Image Generation | 
 | [unclip](./api/pipelines/unclip) | [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://arxiv.org/abs/2204.06125) | Text-to-Image Generation |
 | [versatile_diffusion](./api/pipelines/versatile_diffusion) | [Versatile Diffusion: Text, Images and Variations All in One Diffusion Model](https://arxiv.org/abs/2211.08332) | Text-to-Image Generation | 

docs/source/en/installation.mdx

@@ -1,4 +1,4 @@
-<!--Copyright 2022 The HuggingFace Team. All rights reserved.
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at

docs/source/en/optimization/fp16.mdx

@@ -1,4 +1,4 @@
-<!--Copyright 2022 The HuggingFace Team. All rights reserved.
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at
@@ -133,6 +133,35 @@ images = pipe([prompt] * 32).images
 You may see a small performance boost in VAE decode on multi-image batches. There should be no performance impact on single-image batches.
 
 
+## Tiled VAE decode and encode for large images
+
+Tiled VAE processing makes it possible to work with large images on limited VRAM. For example, generating 4k images in 8GB of VRAM. Tiled VAE decoder splits the image into overlapping tiles, decodes the tiles, and blends the outputs to make the final image.
+
+You want to couple this with [`~StableDiffusionPipeline.enable_attention_slicing`] or [`~StableDiffusionPipeline.enable_xformers_memory_efficient_attention`] to further minimize memory use.
+
+To use tiled VAE processing, invoke [`~StableDiffusionPipeline.enable_vae_tiling`] in your pipeline before inference. For example:
+
+```python
+import torch
+from diffusers import StableDiffusionPipeline, UniPCMultistepScheduler
+
+pipe = StableDiffusionPipeline.from_pretrained(
+    "runwayml/stable-diffusion-v1-5",
+    torch_dtype=torch.float16,
+)
+pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config)
+pipe = pipe.to("cuda")
+prompt = "a beautiful landscape photograph"
+pipe.enable_vae_tiling()
+pipe.enable_xformers_memory_efficient_attention()
+
+image = pipe([prompt], width=3840, height=2224, num_inference_steps=20).images[0]
+```
+
+The output image will have some tile-to-tile tone variation from the tiles having separate decoders, but you shouldn't see sharp seams between the tiles. The tiling is turned off for images that are 512x512 or smaller.
+
+
+<a name="sequential_offloading"></a>
 ## Offloading to CPU with accelerate for memory savings
 
 For additional memory savings, you can offload the weights to CPU and only load them to GPU when performing the forward pass.
@@ -156,7 +185,13 @@ image = pipe(prompt).images[0]
 
 And you can get the memory consumption to < 3GB.
 
-If is also possible to chain it with attention slicing for minimal memory consumption (< 2GB).
+Note that this method works at the submodule level, not on whole models. This is the best way to minimize memory consumption, but inference is much slower due to the iterative nature of the process. The UNet component of the pipeline runs several times (as many as `num_inference_steps`); each time, the different submodules of the UNet are sequentially onloaded and then offloaded as they are needed, so the number of memory transfers is large.
+
+<Tip>
+Consider using <a href="#model_offloading">model offloading</a> as another point in the optimization space: it will be much faster, but memory savings won't be as large.
+</Tip>
+
+It is also possible to chain offloading with attention slicing for minimal memory consumption (< 2GB).
 
 ```Python
 import torch
@@ -177,6 +212,55 @@ image = pipe(prompt).images[0]
 
 **Note**: When using `enable_sequential_cpu_offload()`, it is important to **not** move the pipeline to CUDA beforehand or else the gain in memory consumption will only be minimal. See [this issue](https://github.com/huggingface/diffusers/issues/1934) for more information.
 
+
+<a name="model_offloading"></a>
+## Model offloading for fast inference and memory savings
+
+[Sequential CPU offloading](#sequential_offloading), as discussed in the previous section, preserves a lot of memory but makes inference slower, because submodules are moved to GPU as needed, and immediately returned to CPU when a new module runs.
+
+Full-model offloading is an alternative that moves whole models to the GPU, instead of handling each model's constituent _modules_. This results in a negligible impact on inference time (compared with moving the pipeline to `cuda`), while still providing some memory savings.
+
+In this scenario, only one of the main components of the pipeline (typically: text encoder, unet and vae)
+will be in the GPU while the others wait in the CPU. Compoments like the UNet that run for multiple iterations will stay on GPU until they are no longer needed.
+
+This feature can be enabled by invoking `enable_model_cpu_offload()` on the pipeline, as shown below.
+
+```Python
+import torch
+from diffusers import StableDiffusionPipeline
+
+pipe = StableDiffusionPipeline.from_pretrained(
+    "runwayml/stable-diffusion-v1-5",  
+    torch_dtype=torch.float16,
+)
+
+prompt = "a photo of an astronaut riding a horse on mars"
+pipe.enable_model_cpu_offload()
+image = pipe(prompt).images[0]
+```
+
+This is also compatible with attention slicing for additional memory savings.
+
+```Python
+import torch
+from diffusers import StableDiffusionPipeline
+
+pipe = StableDiffusionPipeline.from_pretrained(
+    "runwayml/stable-diffusion-v1-5",
+    torch_dtype=torch.float16,
+)
+
+prompt = "a photo of an astronaut riding a horse on mars"
+pipe.enable_model_cpu_offload()
+pipe.enable_attention_slicing(1)
+
+image = pipe(prompt).images[0]
+```
+
+<Tip>
+This feature requires `accelerate` version 0.17.0 or larger.
+</Tip>
+
 ## Using Channels Last memory format
 
 Channels last memory format is an alternative way of ordering NCHW tensors in memory preserving dimensions ordering. Channels last tensors ordered in such a way that channels become the densest dimension (aka storing images pixel-per-pixel). Since not all operators currently support channels last format it may result in a worst performance, so it's better to try it and see if it works for your model.
@@ -210,6 +294,7 @@ torch.set_grad_enabled(False)
 n_experiments = 2
 unet_runs_per_experiment = 50
 
+
 # load inputs
 def generate_inputs():
     sample = torch.randn(2, 4, 64, 64).half().cuda()
@@ -288,6 +373,8 @@ pipe = StableDiffusionPipeline.from_pretrained(
 
 # use jitted unet
 unet_traced = torch.jit.load("unet_traced.pt")
+
+
 # del pipe.unet
 class TracedUNet(torch.nn.Module):
     def __init__(self):

docs/source/en/optimization/habana.mdx

@@ -1,4 +1,4 @@
-<!--Copyright 2022 The HuggingFace Team. All rights reserved.
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at

docs/source/en/optimization/mps.mdx

@@ -1,4 +1,4 @@
-<!--Copyright 2022 The HuggingFace Team. All rights reserved.
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at

docs/source/en/optimization/onnx.mdx

@@ -1,4 +1,4 @@
-<!--Copyright 2022 The HuggingFace Team. All rights reserved.
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at
@@ -21,13 +21,13 @@ specific language governing permissions and limitations under the License.
 
 ## Stable Diffusion Inference
 
-The snippet below demonstrates how to use the ONNX runtime. You need to use `StableDiffusionOnnxPipeline` instead of `StableDiffusionPipeline`. You also need to download the weights from the `onnx` branch of the repository, and indicate the runtime provider you want to use.
+The snippet below demonstrates how to use the ONNX runtime. You need to use `OnnxStableDiffusionPipeline` instead of `StableDiffusionPipeline`. You also need to download the weights from the `onnx` branch of the repository, and indicate the runtime provider you want to use.
 
 ```python
 # make sure you're logged in with `huggingface-cli login`
-from diffusers import StableDiffusionOnnxPipeline
+from diffusers import OnnxStableDiffusionPipeline
 
-pipe = StableDiffusionOnnxPipeline.from_pretrained(
+pipe = OnnxStableDiffusionPipeline.from_pretrained(
     "runwayml/stable-diffusion-v1-5",
     revision="onnx",
     provider="CUDAExecutionProvider",
@@ -37,6 +37,37 @@ prompt = "a photo of an astronaut riding a horse on mars"
 image = pipe(prompt).images[0]
 ```
 
+The snippet below demonstrates how to use the ONNX runtime with the Stable Diffusion upscaling pipeline.
+
+```python
+from diffusers import OnnxStableDiffusionPipeline, OnnxStableDiffusionUpscalePipeline
+
+prompt = "a photo of an astronaut riding a horse on mars"
+steps = 50
+
+txt2img = OnnxStableDiffusionPipeline.from_pretrained(
+    "runwayml/stable-diffusion-v1-5",
+    revision="onnx",
+    provider="CUDAExecutionProvider",
+)
+small_image = txt2img(
+    prompt,
+    num_inference_steps=steps,
+).images[0]
+
+generator = torch.manual_seed(0)
+upscale = OnnxStableDiffusionUpscalePipeline.from_pretrained(
+    "ssube/stable-diffusion-x4-upscaler-onnx",
+    provider="CUDAExecutionProvider",
+)
+large_image = upscale(
+    prompt,
+    small_image,
+    generator=generator,
+    num_inference_steps=steps,
+).images[0]
+```
+
 ## Known Issues
 
 - Generating multiple prompts in a batch seems to take too much memory. While we look into it, you may need to iterate instead of batching.

docs/source/en/optimization/open_vino.mdx

@@ -1,4 +1,4 @@
-<!--Copyright 2022 The HuggingFace Team. All rights reserved.
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at

docs/source/en/optimization/torch2.0.mdx

@@ -0,0 +1,208 @@
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
+
+Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
+the License. You may obtain a copy of the License at
+
+http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
+an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
+specific language governing permissions and limitations under the License.
+-->
+
+# Accelerated PyTorch 2.0 support in Diffusers
+
+Starting from version `0.13.0`, Diffusers supports the latest optimization from the upcoming [PyTorch 2.0](https://pytorch.org/get-started/pytorch-2.0/) release. These include:
+1. Support for accelerated transformers implementation with memory-efficient attention – no extra dependencies required.
+2. [torch.compile](https://pytorch.org/tutorials/intermediate/torch_compile_tutorial.html) support for extra performance boost when individual models are compiled.
+
+
+## Installation
+To benefit from the accelerated transformers implementation and `torch.compile`, we will need to install the nightly version of PyTorch, as the stable version is yet to be released. The first step is to install CUDA 11.7 or CUDA 11.8, 
+as PyTorch 2.0 does not support the previous versions. Once CUDA is installed, torch nightly can be installed using:
+
+```bash
+pip install --pre torch torchvision --index-url https://download.pytorch.org/whl/nightly/cu117
+```
+
+## Using accelerated transformers and torch.compile.
+
+
+1. **Accelerated Transformers implementation**
+
+   PyTorch 2.0 includes an optimized and memory-efficient attention implementation through the [`torch.nn.functional.scaled_dot_product_attention`](https://pytorch.org/docs/master/generated/torch.nn.functional.scaled_dot_product_attention) function, which automatically enables several optimizations depending on the inputs and the GPU type. This is similar to the `memory_efficient_attention` from [xFormers](https://github.com/facebookresearch/xformers), but built natively into PyTorch. 
+
+   These optimizations will be enabled by default in Diffusers if PyTorch 2.0 is installed and if `torch.nn.functional.scaled_dot_product_attention` is available. To use it, just install `torch 2.0` as suggested above and simply use the pipeline. For example:
+
+    ```Python
+    import torch
+    from diffusers import StableDiffusionPipeline
+
+    pipe = StableDiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16)
+    pipe = pipe.to("cuda")
+
+    prompt = "a photo of an astronaut riding a horse on mars"
+    image = pipe(prompt).images[0]
+    ```
+
+    If you want to enable it explicitly (which is not required), you can do so as shown below.
+
+    ```Python
+    import torch
+    from diffusers import StableDiffusionPipeline
+    from diffusers.models.cross_attention import AttnProcessor2_0
+
+    pipe = StableDiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16).to("cuda")
+    pipe.unet.set_attn_processor(AttnProcessor2_0())
+
+    prompt = "a photo of an astronaut riding a horse on mars"
+    image = pipe(prompt).images[0]
+    ```
+
+    This should be as fast and memory efficient as `xFormers`. More details [in our benchmark](#benchmark).
+
+
+2. **torch.compile**
+
+    To get an additional speedup, we can use the new `torch.compile` feature. To do so, we simply wrap our `unet` with `torch.compile`. For more information and different options, refer to the 
+    [torch compile docs](https://pytorch.org/tutorials/intermediate/torch_compile_tutorial.html).
+
+    ```python
+    import torch
+    from diffusers import StableDiffusionPipeline
+
+    pipe = StableDiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16).to(
+        "cuda"
+    )
+    pipe.unet = torch.compile(pipe.unet)
+
+    batch_size = 10
+    prompt = "A photo of an astronaut riding a horse on marse."
+    images = pipe(prompt, num_inference_steps=steps, num_images_per_prompt=batch_size).images
+    ```
+
+    Depending on the type of GPU, `compile()` can yield between 2-9% of _additional speed-up_ over the accelerated transformer optimizations. Note, however, that compilation is able to squeeze more performance improvements in more recent GPU architectures such as Ampere (A100, 3090), Ada (4090) and Hopper (H100).
+    
+    Compilation takes some time to complete, so it is best suited for situations where you need to prepare your pipeline once and then perform the same type of inference operations multiple times.
+
+
+## Benchmark
+
+We conducted a simple benchmark on different GPUs to compare vanilla attention, xFormers, `torch.nn.functional.scaled_dot_product_attention` and `torch.compile+torch.nn.functional.scaled_dot_product_attention`.
+For the benchmark we used the the [stable-diffusion-v1-4](https://huggingface.co/CompVis/stable-diffusion-v1-4) model with 50 steps. The `xFormers` benchmark is done using the `torch==1.13.1` version, while the accelerated transformers optimizations are tested using nightly versions of PyTorch 2.0. The tables below summarize the results we got.
+
+The `Speed over xformers` columns denote the speed-up gained over `xFormers` using the `torch.compile+torch.nn.functional.scaled_dot_product_attention`.
+
+
+### FP16 benchmark
+
+The table below shows the benchmark results for inference using `fp16`. As we can see, `torch.nn.functional.scaled_dot_product_attention` is as fast as `xFormers` (sometimes slightly faster/slower) on all the GPUs we tested.
+And using `torch.compile` gives further speed-up of up of 10% over `xFormers`, but it's mostly noticeable on the A100 GPU.
+
+___The time reported is in seconds.___
+
+| GPU | Batch Size | Vanilla Attention | xFormers | PyTorch2.0 SDPA | SDPA + torch.compile | Speed over xformers (%) |
+| --- | --- | --- | --- | --- | --- | --- |
+| A100 | 10 | 12.02 | 8.7 | 8.79 | 7.89 | 9.31 |
+| A100 | 16 | 18.95 | 13.57 | 13.67 | 12.25 | 9.73 |
+| A100 | 32 (1) | OOM | 26.56 | 26.68 | 24.08 | 9.34 |
+| A100 | 64 | | 52.51 | 53.03 | 47.81 | 8.95 |
+| | | | | | | |
+| A10 | 4 | 13.94 | 9.81 | 10.01 | 9.35 | 4.69 |
+| A10 | 8 | 27.09 | 19 | 19.53 | 18.33 | 3.53 |
+| A10 | 10 | 33.69 | 23.53 | 24.19 | 22.52 | 4.29 |
+| A10 | 16 | OOM | 37.55 | 38.31 | 36.81 | 1.97 |
+| A10 | 32 (1) | | 77.19 | 78.43 | 76.64 | 0.71 |
+| A10 | 64 (1) | | 173.59 | 158.99 | 155.14 | 10.63 |
+| | | | | | | |
+| T4 | 4 | 38.81 | 30.09 | 29.74 | 27.55 | 8.44 |
+| T4 | 8 | OOM | 55.71 | 55.99 | 53.85 | 3.34 |
+| T4 | 10 | OOM | 68.96 | 69.86 | 65.35 | 5.23 |
+| T4 | 16 | OOM | 111.47 | 113.26  | 106.93  | 4.07 |
+| | | | | | | |
+| V100 | 4 | 9.84 | 8.16 | 8.09 | 7.65 | 6.25 |
+| V100 | 8 | OOM | 15.62 | 15.44 | 14.59 | 6.59 |
+| V100 | 10 | OOM | 19.52 | 19.28 | 18.18 | 6.86 |
+| V100 | 16 | OOM | 30.29 | 29.84 | 28.22 | 6.83 |
+| | | | | | | |
+| 3090 | 4 | 10.04 | 7.82 | 7.89 | 7.47 | 4.48 |
+| 3090 | 8 | 19.27 | 14.97 | 15.04 | 14.22 | 5.01 |
+| 3090 | 10| 24.08 | 18.7 | 18.7 | 17.69 | 5.40 |
+| 3090 | 16 | OOM | 29.06 | 29.06 | 28.2 | 2.96 |
+| 3090 | 32 (1) | | 58.05 | 58 | 54.88 | 5.46 |
+| 3090 | 64 (1) | | 126.54 | 126.03 | 117.33 | 7.28 |
+| | | | | | | |
+| 3090 Ti | 4 | 9.07 | 7.14 | 7.15 | 6.81 | 4.62 |
+| 3090 Ti | 8 | 17.51 | 13.65 | 13.72 | 12.99 | 4.84 |
+| 3090 Ti | 10 (2) | 21.79 | 16.85 | 16.93 | 16.02 | 4.93 |
+| 3090 Ti | 16 | OOM | 26.1 | 26.28 | 25.46 | 2.45 |
+| 3090 Ti | 32 (1) | | 51.78 | 52.04 | 49.15 | 5.08 |
+| 3090 Ti | 64 (1) | | 112.02 | 112.33 | 103.91 | 7.24 |
+| | | | | | | |
+| 4090 | 4 | 10.48 | 8.37 | 8.32 | 8.01 | 4.30 |
+| 4090 | 8 | 14.33 | 10.22 | 10.42 | 9.78 | 4.31 |
+| 4090 | 16 | | 17.07 | 17.46 | 17.15 | -0.47 |
+| 4090 | 32 (1) | | 39.03 | 39.86 | 37.97 | 2.72 |
+| 4090 | 64 (1) | | 77.29 | 79.44 | 77.67 | -0.49 |
+
+
+				
+### FP32 benchmark
+
+The table below shows the benchmark results for inference using `fp32`. In this case, `torch.nn.functional.scaled_dot_product_attention` is faster than `xFormers` on all the GPUs we tested.
+
+Using `torch.compile` in addition to the accelerated transformers implementation can yield up to 19% performance improvement over `xFormers` in Ampere and Ada cards, and up to 20% (Ampere) or 28% (Ada) over vanilla attention.
+
+| GPU | Batch Size | Vanilla Attention | xFormers | PyTorch2.0 SDPA | SDPA + torch.compile | Speed over xformers (%) | Speed over vanilla (%) |
+| --- | --- | --- | --- | --- | --- | --- | --- |
+| A100 | 4 | 16.56 | 12.42 | 12.2 | 11.84 | 4.67 | 28.50 |
+| A100 | 10 | OOM | 29.93 | 29.44 | 28.5 | 4.78 | |
+| A100 | 16 | | 47.08 | 46.27 | 44.8 | 4.84 | |
+| A100 | 32 | | 92.89 | 91.34 | 88.35 | 4.89 | |
+| A100 | 64 | | 185.3 | 182.71 | 176.48 | 4.76 | |
+| | | | | | | |
+| A10 | 1 | 10.59 | 8.81 | 7.51 | 7.35 | 16.57 | 30.59 |
+| A10 | 4 | 34.77 | 27.63 | 22.77 | 22.07 | 20.12 | 36.53 |
+| A10 | 8 | | 56.19 | 43.53 | 43.86 | 21.94 | |
+| A10 | 16 | | 116.49 | 88.56 | 86.64 | 25.62 | |
+| A10 | 32 | | 221.95 | 175.74 | 168.18 | 24.23 | |
+| A10 | 48 | | 333.23 | 264.84 | | 20.52 | |
+| | | | | | | |
+| T4 | 1 | 28.2 | 24.49 | 23.93 | 23.56 | 3.80 | 16.45 |
+| T4 | 2 | 52.77 | 45.7 | 45.88 | 45.06 | 1.40 | 14.61 |
+| T4 | 4 | OOM | 85.72 | 85.78 | 84.48 | 1.45 | |
+| T4 | 8 | | 149.64 | 150.75 | 148.4 | 0.83 | |
+| | | | | | | |
+| V100 | 1 | 7.4 | 6.84 | 6.8 | 6.66 | 2.63 | 10.00 |
+| V100 | 2 | 13.85 | 12.81 | 12.66 | 12.35 | 3.59 | 10.83 |
+| V100 | 4 | OOM | 25.73 | 25.31 | 24.78 | 3.69 | |
+| V100 | 8 | | 43.95 | 43.37 | 42.25 | 3.87 | |
+| V100 | 16 | | 84.99 | 84.73 | 82.55 | 2.87 | |
+| | | | | | | |
+| 3090 | 1 | 7.09 | 6.78 | 6.11 | 6.03 | 11.06 | 14.95 |
+| 3090 | 4 | 22.69 | 21.45 | 18.67 | 18.09 | 15.66 | 20.27 |
+| 3090 | 8 | | 42.59 | 36.75 | 35.59 | 16.44 | |
+| 3090 | 16 | | 85.35 | 72.37 | 70.25 | 17.69 | |
+| 3090 | 32 (1) | | 162.05 | 138.99 | 134.53 | 16.98 | |
+| 3090 | 48 | | 241.91 | 207.75 | | 14.12 | |
+| | | | | | | |
+| 3090 Ti | 1 | 6.45 | 6.19 | 5.64 | 5.49 | 11.31 | 14.88 |
+| 3090 Ti | 4 | 20.32 | 19.31 | 16.9 | 16.37 | 15.23 | 19.44 |
+| 3090 Ti | 8 (2) | | 37.93 | 33.05 | 31.99 | 15.66 | |
+| 3090 Ti | 16 | | 75.37 | 65.25 | 64.32 | 14.66 | |
+| 3090 Ti | 32 (1) | | 142.55 | 124.44 | 120.74 | 15.30 | |
+| 3090 Ti | 48 | | 213.19 | 186.55 | | 12.50 | |
+| | | | | | | |
+| 4090 | 1 | 5.54 | 4.99 | 4.51 | 4.44 | 11.02 | 19.86 |
+| 4090 | 4 | 13.67 | 11.4 | 10.3 | 9.84 | 13.68 | 28.02 |
+| 4090 | 8 | | 19.79 | 17.13 | 16.19 | 18.19 | |
+| 4090 | 16 | | 38.62 | 33.14 | 32.31 | 16.34 | |
+| 4090 | 32 (1) | | 76.57 | 65.96 | 62.05 | 18.96 | |
+| 4090 | 48 | | 114.44 | 98.78 | | 13.68 | |
+
+
+
+(1) Batch Size >= 32 requires enable_vae_slicing() because of https://github.com/pytorch/pytorch/issues/81665																										
+This is required for PyTorch 1.13.1, and also for PyTorch 2.0 and batch size of 64
+
+For more details about how this benchmark was run, please refer to [this PR](https://github.com/huggingface/diffusers/pull/2303).	

docs/source/en/optimization/xformers.mdx

@@ -1,4 +1,4 @@
-<!--Copyright 2022 The HuggingFace Team. All rights reserved.
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at

docs/source/en/quicktour.mdx

@@ -1,4 +1,4 @@
-<!--Copyright 2022 The HuggingFace Team. All rights reserved.
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at
@@ -10,10 +10,25 @@ an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express o
 specific language governing permissions and limitations under the License.
 -->
 
+[[open-in-colab]]
+
 # Quicktour
 
-Get up and running with 🧨 Diffusers quickly!
-Whether you're a developer or an everyday user, this quick tour will help you get started and show you how to use [`DiffusionPipeline`] for inference.
+Diffusion models are trained to denoise random Gaussian noise step-by-step to generate a sample of interest, such as an image or audio. This has sparked a tremendous amount of interest in generative AI, and you have probably seen examples of diffusion generated images on the internet. 🧨 Diffusers is a library aimed at making diffusion models widely accessible to everyone.
+
+Whether you're a developer or an everyday user, this quicktour will introduce you to 🧨 Diffusers and help you get up and generating quickly! There are three main components of the library to know about:
+
+* The [`DiffusionPipeline`] is a high-level end-to-end class designed to rapidly generate samples from pretrained diffusion models for inference.
+* Popular pretrained [model](./api/models) architectures and modules that can be used as building blocks for creating diffusion systems.
+* Many different [schedulers](./api/schedulers/overview) - algorithms that control how noise is added for training, and how to generate denoised images during inference.
+
+The quicktour will show you how to use the [`DiffusionPipeline`] for inference, and then walk you through how to combine a model and scheduler to replicate what's happening inside the [`DiffusionPipeline`].
+
+<Tip>
+
+The quicktour is a simplified version of the introductory 🧨 Diffusers [notebook](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/diffusers_intro.ipynb) to help you get started quickly. If you want to learn more about 🧨 Diffusers goal, design philosophy, and additional details about it's core API, check out the notebook!
+
+</Tip>
 
 Before you begin, make sure you have all the necessary libraries installed:
 
@@ -21,32 +36,32 @@ Before you begin, make sure you have all the necessary libraries installed:
 pip install --upgrade diffusers accelerate transformers
 ```
 
-- [`accelerate`](https://huggingface.co/docs/accelerate/index) speeds up model loading for inference and training
-- [`transformers`](https://huggingface.co/docs/transformers/index) is required to run the most popular diffusion models, such as [Stable Diffusion](https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion/overview)
+- [🤗 Accelerate](https://huggingface.co/docs/accelerate/index) speeds up model loading for inference and training.
+- [🤗 Transformers](https://huggingface.co/docs/transformers/index) is required to run the most popular diffusion models, such as [Stable Diffusion](https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion/overview).
 
 ## DiffusionPipeline
 
-The [`DiffusionPipeline`] is the easiest way to use a pre-trained diffusion system for inference. You can use the [`DiffusionPipeline`] out-of-the-box for many tasks across different modalities. Take a look at the table below for some supported tasks:
+The [`DiffusionPipeline`] is the easiest way to use a pretrained diffusion system for inference. It is an end-to-end system containing the model and the scheduler. You can use the [`DiffusionPipeline`] out-of-the-box for many tasks. Take a look at the table below for some supported tasks, and for a complete list of supported tasks, check out the [🧨 Diffusers Summary](./api/pipelines/overview#diffusers-summary) table.
 
 | **Task**                     | **Description**                                                                                              | **Pipeline**
 |------------------------------|--------------------------------------------------------------------------------------------------------------|-----------------|
-| Unconditional Image Generation          | generate an image from gaussian noise | [unconditional_image_generation](./using-diffusers/unconditional_image_generation`) |
+| Unconditional Image Generation          | generate an image from Gaussian noise | [unconditional_image_generation](./using-diffusers/unconditional_image_generation) |
 | Text-Guided Image Generation | generate an image given a text prompt | [conditional_image_generation](./using-diffusers/conditional_image_generation) |
 | Text-Guided Image-to-Image Translation     | adapt an image guided by a text prompt | [img2img](./using-diffusers/img2img) |
 | Text-Guided Image-Inpainting          | fill the masked part of an image given the image, the mask and a text prompt | [inpaint](./using-diffusers/inpaint) |
-| Text-Guided Depth-to-Image Translation | adapt parts of an image guided by a text prompt while preserving structure via depth estimation | [depth2image](./using-diffusers/depth2image) |
+| Text-Guided Depth-to-Image Translation | adapt parts of an image guided by a text prompt while preserving structure via depth estimation | [depth2img](./using-diffusers/depth2img) |
 
-For more in-detail information on how diffusion pipelines function for the different tasks, please have a look at the [**Using Diffusers**](./using-diffusers/overview) section.
+Start by creating an instance of a [`DiffusionPipeline`] and specify which pipeline checkpoint you would like to download.
+You can use the [`DiffusionPipeline`] for any [checkpoint](https://huggingface.co/models?library=diffusers&sort=downloads) stored on the Hugging Face Hub.
+In this quicktour, you'll load the [`stable-diffusion-v1-5`](https://huggingface.co/runwayml/stable-diffusion-v1-5) checkpoint for text-to-image generation.
 
-As an example, start by creating an instance of [`DiffusionPipeline`] and specify which pipeline checkpoint you would like to download.
-You can use the [`DiffusionPipeline`] for any [Diffusers' checkpoint](https://huggingface.co/models?library=diffusers&sort=downloads).
-In this guide though, you'll use [`DiffusionPipeline`] for text-to-image generation with [Stable Diffusion](https://huggingface.co/CompVis/stable-diffusion).
+<Tip warning={true}>
 
-For [Stable Diffusion](https://huggingface.co/CompVis/stable-diffusion), please carefully read its [license](https://huggingface.co/spaces/CompVis/stable-diffusion-license) before running the model.
-This is due to the improved image generation capabilities of the model and the potentially harmful content that could be produced with it.
-Please, head over to your stable diffusion model of choice, *e.g.*  [`runwayml/stable-diffusion-v1-5`](https://huggingface.co/runwayml/stable-diffusion-v1-5), and read the license.
+For [Stable Diffusion](https://huggingface.co/CompVis/stable-diffusion) models, please carefully read the [license](https://huggingface.co/spaces/CompVis/stable-diffusion-license) first before running the model. 🧨 Diffusers implements a [`safety_checker`](https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/stable_diffusion/safety_checker.py) to prevent offensive or harmful content, but the model's improved image generation capabilities can still produce potentially harmful content.
 
-You can load the model as follows:
+</Tip>
+
+Load the model with the [`~DiffusionPipeline.from_pretrained`] method:
 
 ```python
 >>> from diffusers import DiffusionPipeline
@@ -54,77 +69,245 @@ You can load the model as follows:
 >>> pipeline = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5")
 ```
 
-The [`DiffusionPipeline`] downloads and caches all modeling, tokenization, and scheduling components. 
-Because the model consists of roughly 1.4 billion parameters, we strongly recommend running it on GPU.
-You can move the generator object to GPU, just like you would in PyTorch.
+The [`DiffusionPipeline`] downloads and caches all modeling, tokenization, and scheduling components. You'll see that the Stable Diffusion pipeline is composed of the [`UNet2DConditionModel`] and [`PNDMScheduler`] among other things:
+
+```py
+>>> pipeline
+StableDiffusionPipeline {
+  "_class_name": "StableDiffusionPipeline",
+  "_diffusers_version": "0.13.1",
+  ...,
+  "scheduler": [
+    "diffusers",
+    "PNDMScheduler"
+  ],
+  ...,
+  "unet": [
+    "diffusers",
+    "UNet2DConditionModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ]
+}
+```
+
+We strongly recommend running the pipeline on a GPU because the model consists of roughly 1.4 billion parameters.
+You can move the generator object to a GPU, just like you would in PyTorch:
 
 ```python
 >>> pipeline.to("cuda")
 ```
 
-Now you can use the `pipeline` on your text prompt:
+Now you can pass a text prompt to the `pipeline` to generate an image, and then access the denoised image. By default, the image output is wrapped in a [`PIL.Image`](https://pillow.readthedocs.io/en/stable/reference/Image.html?highlight=image#the-image-class) object.
 
 ```python
 >>> image = pipeline("An image of a squirrel in Picasso style").images[0]
+>>> image
 ```
 
-The output is by default wrapped into a [PIL Image object](https://pillow.readthedocs.io/en/stable/reference/Image.html?highlight=image#the-image-class).
+<div class="flex justify-center">
+    <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/image_of_squirrel_painting.png"/>
+</div>
 
-You can save the image by simply calling:
+Save the image by calling `save`:
 
 ```python
 >>> image.save("image_of_squirrel_painting.png")
 ```
 
-**Note**: You can also use the pipeline locally by downloading the weights via:
+### Local pipeline
+
+You can also use the pipeline locally. The only difference is you need to download the weights first:
 
 ```
 git lfs install
 git clone https://huggingface.co/runwayml/stable-diffusion-v1-5
 ```
 
-and then loading the saved weights into the pipeline. 
+Then load the saved weights into the pipeline:
 
 ```python
 >>> pipeline = DiffusionPipeline.from_pretrained("./stable-diffusion-v1-5")
 ```
 
-Running the pipeline is then identical to the code above as it's the same model architecture.
+Now you can run the pipeline as you would in the section above.
 
-```python
->>> generator.to("cuda")
->>> image = generator("An image of a squirrel in Picasso style").images[0]
->>> image.save("image_of_squirrel_painting.png")
-```
+### Swapping schedulers
 
-Diffusion systems can be used with multiple different [schedulers](./api/schedulers/overview) each with their
-pros and cons. By default, Stable Diffusion runs with [`PNDMScheduler`], but it's very simple to 
-use a different scheduler. *E.g.* if you would instead like to use the [`EulerDiscreteScheduler`] scheduler,
-you could use it as follows:
+Different schedulers come with different denoising speeds and quality trade-offs. The best way to find out which one works best for you is to try them out! One of the main features of 🧨 Diffusers is to allow you to easily switch between schedulers. For example, to replace the default [`PNDMScheduler`] with the [`EulerDiscreteScheduler`], load it with the [`~diffusers.ConfigMixin.from_config`] method:
 
-```python
+```py
 >>> from diffusers import EulerDiscreteScheduler
 
 >>> pipeline = StableDiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5")
-
->>> # change scheduler to Euler
 >>> pipeline.scheduler = EulerDiscreteScheduler.from_config(pipeline.scheduler.config)
 ```
 
-For more in-detail information on how to change between schedulers, please refer to the [Using Schedulers](./using-diffusers/schedulers) guide.
+Try generating an image with the new scheduler and see if you notice a difference!
 
-[Stability AI's](https://stability.ai/) Stable Diffusion model is an impressive image generation model
-and can do much more than just generating images from text. We have dedicated a whole documentation page,
-just for Stable Diffusion [here](./conceptual/stable_diffusion).
+In the next section, you'll take a closer look at the components - the model and scheduler - that make up the [`DiffusionPipeline`] and learn how to use these components to generate an image of a cat.
 
-If you want to know how to optimize Stable Diffusion to run on less memory, higher inference speeds, on specific hardware, such as Mac, or with [ONNX Runtime](https://onnxruntime.ai/), please have a look at our 
-optimization pages:
+## Models
 
-- [Optimized PyTorch on GPU](./optimization/fp16)
-- [Mac OS with PyTorch](./optimization/mps)
-- [ONNX](./optimization/onnx)
-- [OpenVINO](./optimization/open_vino)
+Most models take a noisy sample, and at each timestep it predicts the *noise residual* (other models learn to predict the previous sample directly or the velocity or [`v-prediction`](https://github.com/huggingface/diffusers/blob/5e5ce13e2f89ac45a0066cb3f369462a3cf1d9ef/src/diffusers/schedulers/scheduling_ddim.py#L110)), the difference between a less noisy image and the input image. You can mix and match models to create other diffusion systems.
 
-If you want to fine-tune or train your diffusion model, please have a look at the [**training section**](./training/overview)
+Models are initiated with the [`~ModelMixin.from_pretrained`] method which also locally caches the model weights so it is faster the next time you load the model. For the quicktour, you'll load the [`UNet2DModel`], a basic unconditional image generation model with a checkpoint trained on cat images:
 
-Finally, please be considerate when distributing generated images publicly 🤗.
+```py
+>>> from diffusers import UNet2DModel
+
+>>> repo_id = "google/ddpm-cat-256"
+>>> model = UNet2DModel.from_pretrained(repo_id)
+```
+
+To access the model parameters, call `model.config`:
+
+```py
+>>> model.config
+```
+
+The model configuration is a 🧊 frozen 🧊 dictionary, which means those parameters can't be changed after the model is created. This is intentional and ensures that the parameters used to define the model architecture at the start remain the same, while other parameters can still be adjusted during inference.
+
+Some of the most important parameters are:
+
+* `sample_size`: the height and width dimension of the input sample.
+* `in_channels`: the number of input channels of the input sample.
+* `down_block_types` and `up_block_types`: the type of down- and upsampling blocks used to create the UNet architecture.
+* `block_out_channels`: the number of output channels of the downsampling blocks; also used in reverse order for the number of input channels of the upsampling blocks.
+* `layers_per_block`: the number of ResNet blocks present in each UNet block.
+
+To use the model for inference, create the image shape with random Gaussian noise. It should have a `batch` axis because the model can receive multiple random noises, a `channel` axis corresponding to the number of input channels, and a `sample_size` axis for the height and width of the image:
+
+```py
+>>> import torch
+
+>>> torch.manual_seed(0)
+
+>>> noisy_sample = torch.randn(1, model.config.in_channels, model.config.sample_size, model.config.sample_size)
+>>> noisy_sample.shape
+torch.Size([1, 3, 256, 256])
+```
+
+For inference, pass the noisy image to the model and a `timestep`. The `timestep` indicates how noisy the input image is, with more noise at the beginning and less at the end. This helps the model determine its position in the diffusion process, whether it is closer to the start or the end. Use the `sample` method to get the model output:
+
+```py
+>>> with torch.no_grad():
+...     noisy_residual = model(sample=noisy_sample, timestep=2).sample
+```
+
+To generate actual examples though, you'll need a scheduler to guide the denoising process. In the next section, you'll learn how to couple a model with a scheduler.
+
+## Schedulers
+
+Schedulers manage going from a noisy sample to a less noisy sample given the model output - in this case, it is the `noisy_residual`.
+
+<Tip>
+
+🧨 Diffusers is a toolbox for building diffusion systems. While the [`DiffusionPipeline`] is a convenient way to get started with a pre-built diffusion system, you can also choose your own the model and scheduler components separately to build a custom diffusion system.
+
+</Tip>
+
+For the quicktour, you'll instantiate the [`DDPMScheduler`] with it's [`~diffusers.ConfigMixin.from_config`] method:
+
+```py
+>>> from diffusers import DDPMScheduler
+
+>>> scheduler = DDPMScheduler.from_config(repo_id)
+>>> scheduler
+DDPMScheduler {
+  "_class_name": "DDPMScheduler",
+  "_diffusers_version": "0.13.1",
+  "beta_end": 0.02,
+  "beta_schedule": "linear",
+  "beta_start": 0.0001,
+  "clip_sample": true,
+  "clip_sample_range": 1.0,
+  "num_train_timesteps": 1000,
+  "prediction_type": "epsilon",
+  "trained_betas": null,
+  "variance_type": "fixed_small"
+}
+```
+
+<Tip>
+
+💡 Notice how the scheduler is instantiated from a configuration. Unlike a model, a scheduler does not have trainable weights and is parameter-free!
+
+</Tip>
+
+Some of the most important parameters are:
+
+* `num_train_timesteps`: the length of the denoising process or in other words, the number of timesteps required to process random Gaussian noise into a data sample.
+* `beta_schedule`: the type of noise schedule to use for inference and training.
+* `beta_start` and `beta_end`: the start and end noise values for the noise schedule.
+
+To predict a slightly less noisy image, pass the following to the scheduler's [`~diffusers.DDPMScheduler.step`] method: model output, `timestep`, and current `sample`.
+
+```py
+>>> less_noisy_sample = scheduler.step(model_output=noisy_residual, timestep=2, sample=noisy_sample).prev_sample
+>>> less_noisy_sample.shape
+```
+
+The `less_noisy_sample` can be passed to the next `timestep` where it'll get even less noisier! Let's bring it all together now and visualize the entire denoising process. 
+
+First, create a function that postprocesses and displays the denoised image as a `PIL.Image`:
+
+```py
+>>> import PIL.Image
+>>> import numpy as np
+
+
+>>> def display_sample(sample, i):
+...     image_processed = sample.cpu().permute(0, 2, 3, 1)
+...     image_processed = (image_processed + 1.0) * 127.5
+...     image_processed = image_processed.numpy().astype(np.uint8)
+
+...     image_pil = PIL.Image.fromarray(image_processed[0])
+...     display(f"Image at step {i}")
+...     display(image_pil)
+```
+
+To speed up the denoising process, move the input and model to a GPU:
+
+```py
+>>> model.to("cuda")
+>>> noisy_sample = noisy_sample.to("cuda")
+```
+
+Now create a denoising loop that predicts the residual of the less noisy sample, and computes the less noisy sample with the scheduler:
+
+```py
+>>> import tqdm
+
+>>> sample = noisy_sample
+
+>>> for i, t in enumerate(tqdm.tqdm(scheduler.timesteps)):
+...     # 1. predict noise residual
+...     with torch.no_grad():
+...         residual = model(sample, t).sample
+
+...     # 2. compute less noisy image and set x_t -> x_t-1
+...     sample = scheduler.step(residual, t, sample).prev_sample
+
+...     # 3. optionally look at image
+...     if (i + 1) % 50 == 0:
+...         display_sample(sample, i + 1)
+```
+
+Sit back and watch as a cat is generated from nothing but noise! 😻
+
+<div class="flex justify-center">
+    <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/diffusion-quicktour.png"/>
+</div>
+
+## Next steps
+
+Hopefully you generated some cool images with 🧨 Diffusers in this quicktour! For your next steps, you can:
+
+* Train or finetune a model to generate your own images in the [training](./tutorials/basic_training) tutorial.
+* See example official and community [training or finetuning scripts](https://github.com/huggingface/diffusers/tree/main/examples#-diffusers-examples) for a variety of use cases.
+* Learn more about loading, accessing, changing and comparing schedulers in the [Using different Schedulers](./using-diffusers/schedulers) guide.
+* Explore prompt engineering, speed and memory optimizations, and tips and tricks for generating higher quality images with the [Stable Diffusion](./stable_diffusion) guide.
+* Dive deeper into speeding up 🧨 Diffusers with guides on [optimized PyTorch on a GPU](./optimization/fp16), and inference guides for running [Stable Diffusion on Apple Silicon (M1/M2)](./optimization/mps) and [ONNX Runtime](./optimization/onnx).

docs/source/en/stable_diffusion.mdx

@@ -1,4 +1,4 @@
-<!--Copyright 2022 The HuggingFace Team. All rights reserved.                                                                                                                                                                                 
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.                                                                                                                                                                                 
                                                                                                                                                                                                                                               
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with                                                                                                                           
 the License. You may obtain a copy of the License at                                                                                                                                                                                          

docs/source/en/training/dreambooth.mdx

@@ -1,4 +1,4 @@
-<!--Copyright 2022 The HuggingFace Team. All rights reserved.
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at
@@ -10,55 +10,67 @@ an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express o
 specific language governing permissions and limitations under the License.
 -->
 
-# DreamBooth fine-tuning example
+# DreamBooth
 
-[DreamBooth](https://arxiv.org/abs/2208.12242) is a method to personalize text-to-image models like stable diffusion given just a few (3~5) images of a subject.
+[[open-in-colab]]
+
+[DreamBooth](https://arxiv.org/abs/2208.12242) is a method to personalize text-to-image models like Stable Diffusion given just a few (3-5) images of a subject. It allows the model to generate contextualized images of the subject in different scenes, poses, and views.
 
 ![Dreambooth examples from the project's blog](https://dreambooth.github.io/DreamBooth_files/teaser_static.jpg)
-_Dreambooth examples from the [project's blog](https://dreambooth.github.io)._
+<small>Dreambooth examples from the <a href="https://dreambooth.github.io">project's blog.</a></small>
 
-The [Dreambooth training script](https://github.com/huggingface/diffusers/tree/main/examples/dreambooth) shows how to implement this training procedure on a pre-trained Stable Diffusion model.
+This guide will show you how to finetune DreamBooth with the [`CompVis/stable-diffusion-v1-4`](https://huggingface.co/CompVis/stable-diffusion-v1-4) model for various GPU sizes, and with Flax. All the training scripts for DreamBooth used in this guide can be found [here](https://github.com/huggingface/diffusers/tree/main/examples/dreambooth) if you're interested in digging deeper and seeing how things work.
 
-<Tip warning={true}>
-
-Dreambooth fine-tuning is very sensitive to hyperparameters and easy to overfit. We recommend you take a look at our [in-depth analysis](https://huggingface.co/blog/dreambooth) with recommended settings for different subjects, and go from there.
-
-</Tip>
-
-## Training locally 
-
-### Installing the dependencies
-
-Before running the scripts, make sure to install the library's training dependencies. We also recommend to install `diffusers` from the `main` github branch.
+Before running the scripts, make sure you install the library's training dependencies. We also recommend installing 🧨 Diffusers from the `main` GitHub branch:
 
 ```bash
 pip install git+https://github.com/huggingface/diffusers
 pip install -U -r diffusers/examples/dreambooth/requirements.txt
 ```
 
-xFormers is not part of the training requirements, but [we recommend you install it if you can](../optimization/xformers). It could make your training faster and less memory intensive.
+xFormers is not part of the training requirements, but we recommend you [install](../optimization/xformers) it if you can because it could make your training faster and less memory intensive.
 
-After all dependencies have been set up you can configure a [🤗 Accelerate](https://github.com/huggingface/accelerate/) environment with:
+After all the dependencies have been set up, initialize a [🤗 Accelerate](https://github.com/huggingface/accelerate/) environment with:
 
 ```bash
 accelerate config
 ```
 
-In this example we'll use model version `v1-4`, so please visit [its card](https://huggingface.co/CompVis/stable-diffusion-v1-4) and carefully read the license before proceeding. 
+To setup a default 🤗 Accelerate environment without choosing any configurations:
 
-The command below will download and cache the model weights from the Hub because we use the model's Hub id `CompVis/stable-diffusion-v1-4`. You may also clone the repo locally and use the local path in your system where the checkout was saved.
+```bash
+accelerate config default
+```
 
-### Dog toy example
+Or if your environment doesn't support an interactive shell like a notebook, you can use:
 
-In this example we'll use [these images](https://drive.google.com/drive/folders/1BO_dyz-p65qhBRRMRA4TbZ8qW4rB99JZ) to add a new concept to Stable Diffusion using the Dreambooth process. They will be our training data. Please, download them and place them somewhere in your system.
+```py
+from accelerate.utils import write_basic_config
 
-Then you can launch the training script using:
+write_basic_config()
+```
+
+## Finetuning
+
+<Tip warning={true}>
+
+DreamBooth finetuning is very sensitive to hyperparameters and easy to overfit. We recommend you take a look at our [in-depth analysis](https://huggingface.co/blog/dreambooth) with recommended settings for different subjects to help you choose the appropriate hyperparameters.
+
+</Tip>
+
+<frameworkcontent>
+<pt>
+Let's try DreamBooth with a [few images of a dog](https://drive.google.com/drive/folders/1BO_dyz-p65qhBRRMRA4TbZ8qW4rB99JZ); download and save them to a directory and then set the `INSTANCE_DIR` environment variable to that path:
 
 ```bash
 export MODEL_NAME="CompVis/stable-diffusion-v1-4"
 export INSTANCE_DIR="path_to_training_images"
 export OUTPUT_DIR="path_to_saved_model"
+```
 
+Then you can launch the training script (you can find the full training script [here](https://github.com/huggingface/diffusers/blob/main/examples/dreambooth/train_dreambooth.py)) with the following command:
+
+```bash
 accelerate launch train_dreambooth.py \
   --pretrained_model_name_or_path=$MODEL_NAME  \
   --instance_data_dir=$INSTANCE_DIR \
@@ -72,13 +84,44 @@ accelerate launch train_dreambooth.py \
   --lr_warmup_steps=0 \
   --max_train_steps=400
 ```
+</pt>
+<jax>
+If you have access to TPUs or want to train even faster, you can try out the [Flax training script](https://github.com/huggingface/diffusers/blob/main/examples/dreambooth/train_dreambooth_flax.py). The Flax training script doesn't support gradient checkpointing or gradient accumulation, so you'll need a GPU with at least 30GB of memory.
 
-### Training with a prior-preserving loss
+Before running the script, make sure you have the requirements installed:
 
-Prior preservation is used to avoid overfitting and language-drift. Please, refer to the paper to learn more about it if you are interested. For prior preservation, we use other images of the same class as part of the training process. The nice thing is that we can generate those images using the Stable Diffusion model itself! The training script will save the generated images to a local path we specify.
+```bash
+pip install -U -r requirements.txt
+```
 
-According to the paper, it's recommended to generate `num_epochs * num_samples` images for prior preservation. 200-300 works well for most cases.
+Now you can launch the training script with the following command:
 
+```bash
+export MODEL_NAME="duongna/stable-diffusion-v1-4-flax"
+export INSTANCE_DIR="path-to-instance-images"
+export OUTPUT_DIR="path-to-save-model"
+
+python train_dreambooth_flax.py \
+  --pretrained_model_name_or_path=$MODEL_NAME  \
+  --instance_data_dir=$INSTANCE_DIR \
+  --output_dir=$OUTPUT_DIR \
+  --instance_prompt="a photo of sks dog" \
+  --resolution=512 \
+  --train_batch_size=1 \
+  --learning_rate=5e-6 \
+  --max_train_steps=400
+```
+</jax>
+</frameworkcontent>
+
+## Finetuning with prior-preserving loss
+
+Prior preservation is used to avoid overfitting and language-drift (check out the [paper](https://arxiv.org/abs/2208.12242) to learn more if you're interested). For prior preservation, you use other images of the same class as part of the training process. The nice thing is that you can generate those images using the Stable Diffusion model itself! The training script will save the generated images to a local path you specify.
+
+The author's recommend generating `num_epochs * num_samples` images for prior preservation. In most cases, 200-300 images work well.
+
+<frameworkcontent>
+<pt>
 ```bash
 export MODEL_NAME="CompVis/stable-diffusion-v1-4"
 export INSTANCE_DIR="path_to_training_images"
@@ -102,32 +145,148 @@ accelerate launch train_dreambooth.py \
   --num_class_images=200 \
   --max_train_steps=800
 ```
+</pt>
+<jax>
+```bash
+export MODEL_NAME="duongna/stable-diffusion-v1-4-flax"
+export INSTANCE_DIR="path-to-instance-images"
+export CLASS_DIR="path-to-class-images"
+export OUTPUT_DIR="path-to-save-model"
 
-### Saving checkpoints while training
+python train_dreambooth_flax.py \
+  --pretrained_model_name_or_path=$MODEL_NAME  \
+  --instance_data_dir=$INSTANCE_DIR \
+  --class_data_dir=$CLASS_DIR \
+  --output_dir=$OUTPUT_DIR \
+  --with_prior_preservation --prior_loss_weight=1.0 \
+  --instance_prompt="a photo of sks dog" \
+  --class_prompt="a photo of dog" \
+  --resolution=512 \
+  --train_batch_size=1 \
+  --learning_rate=5e-6 \
+  --num_class_images=200 \
+  --max_train_steps=800
+```
+</jax>
+</frameworkcontent>
 
-It's easy to overfit while training with Dreambooth, so sometimes it's useful to save regular checkpoints during the process. One of the intermediate checkpoints might work better than the final model! To use this feature you need to pass the following argument to the training script:
+## Finetuning the text encoder and UNet
+
+The script also allows you to finetune the `text_encoder` along with the `unet`. In our experiments (check out the [Training Stable Diffusion with DreamBooth using 🧨 Diffusers](https://huggingface.co/blog/dreambooth) post for more details), this yields much better results, especially when generating images of faces.
+
+<Tip warning={true}>
+
+Training the text encoder requires additional memory and it won't fit on a 16GB GPU. You'll need at least 24GB VRAM to use this option.
+
+</Tip>
+
+Pass the `--train_text_encoder` argument to the training script to enable finetuning the `text_encoder` and `unet`:
+
+<frameworkcontent>
+<pt>
+```bash
+export MODEL_NAME="CompVis/stable-diffusion-v1-4"
+export INSTANCE_DIR="path_to_training_images"
+export CLASS_DIR="path_to_class_images"
+export OUTPUT_DIR="path_to_saved_model"
+
+accelerate launch train_dreambooth.py \
+  --pretrained_model_name_or_path=$MODEL_NAME  \
+  --train_text_encoder \
+  --instance_data_dir=$INSTANCE_DIR \
+  --class_data_dir=$CLASS_DIR \
+  --output_dir=$OUTPUT_DIR \
+  --with_prior_preservation --prior_loss_weight=1.0 \
+  --instance_prompt="a photo of sks dog" \
+  --class_prompt="a photo of dog" \
+  --resolution=512 \
+  --train_batch_size=1 \
+  --use_8bit_adam
+  --gradient_checkpointing \
+  --learning_rate=2e-6 \
+  --lr_scheduler="constant" \
+  --lr_warmup_steps=0 \
+  --num_class_images=200 \
+  --max_train_steps=800
+```
+</pt>
+<jax>
+```bash
+export MODEL_NAME="duongna/stable-diffusion-v1-4-flax"
+export INSTANCE_DIR="path-to-instance-images"
+export CLASS_DIR="path-to-class-images"
+export OUTPUT_DIR="path-to-save-model"
+
+python train_dreambooth_flax.py \
+  --pretrained_model_name_or_path=$MODEL_NAME  \
+  --train_text_encoder \
+  --instance_data_dir=$INSTANCE_DIR \
+  --class_data_dir=$CLASS_DIR \
+  --output_dir=$OUTPUT_DIR \
+  --with_prior_preservation --prior_loss_weight=1.0 \
+  --instance_prompt="a photo of sks dog" \
+  --class_prompt="a photo of dog" \
+  --resolution=512 \
+  --train_batch_size=1 \
+  --learning_rate=2e-6 \
+  --num_class_images=200 \
+  --max_train_steps=800
+```
+</jax>
+</frameworkcontent>
+
+## Finetuning with LoRA
+
+You can also use Low-Rank Adaptation of Large Language Models (LoRA), a fine-tuning technique for accelerating training large models, on DreamBooth. For more details, take a look at the [LoRA training](training/lora#dreambooth) guide.
+
+## Saving checkpoints while training
+
+It's easy to overfit while training with Dreambooth, so sometimes it's useful to save regular checkpoints during the training process. One of the intermediate checkpoints might actually work better than the final model! Pass the following argument to the training script to enable saving checkpoints:
 
 ```bash
   --checkpointing_steps=500
 ```
 
-This will save the full training state in subfolders of your `output_dir`. Subfolder names begin with the prefix `checkpoint-`, and then the number of steps performed so far; for example: `checkpoint-1500` would be a checkpoint saved after 1500 training steps.
+This saves the full training state in subfolders of your `output_dir`. Subfolder names begin with the prefix `checkpoint-`, followed by the number of steps performed so far; for example, `checkpoint-1500` would be a checkpoint saved after 1500 training steps.
 
-#### Resuming training from a saved checkpoint
+### Resume training from a saved checkpoint
 
-If you want to resume training from any of the saved checkpoints, you can pass the argument `--resume_from_checkpoint` and then indicate the name of the checkpoint you want to use. You can also use the special string `"latest"` to resume from the last checkpoint saved (i.e., the one with the largest number of steps). For example, the following would resume training from the checkpoint saved after 1500 steps:
+If you want to resume training from any of the saved checkpoints, you can pass the argument `--resume_from_checkpoint` to the script and specify the name of the checkpoint you want to use. You can also use the special string `"latest"` to resume from the last saved checkpoint (the one with the largest number of steps). For example, the following would resume training from the checkpoint saved after 1500 steps:
 
 ```bash
   --resume_from_checkpoint="checkpoint-1500"
 ```
 
-This would be a good opportunity to tweak some of your hyperparameters if you wish.
+This is a good opportunity to tweak some of your hyperparameters if you wish.
 
-#### Performing inference using a saved checkpoint
+### Inference from a saved checkpoint
 
-Saved checkpoints are stored in a format suitable for resuming training. They not only include the model weights, but also the state of the optimizer, data loaders and learning rate.
+Saved checkpoints are stored in a format suitable for resuming training. They not only include the model weights, but also the state of the optimizer, data loaders, and learning rate.
 
-You can use a checkpoint for inference, but first you need to convert it to an inference pipeline. This is how you could do it:
+If you have **`"accelerate>=0.16.0"`** installed, use the following code to run 
+inference from an intermediate checkpoint.
+
+```python
+from diffusers import DiffusionPipeline, UNet2DConditionModel
+from transformers import CLIPTextModel
+import torch
+
+# Load the pipeline with the same arguments (model, revision) that were used for training
+model_id = "CompVis/stable-diffusion-v1-4"
+
+unet = UNet2DConditionModel.from_pretrained("/sddata/dreambooth/daruma-v2-1/checkpoint-100/unet")
+
+# if you have trained with `--args.train_text_encoder` make sure to also load the text encoder
+text_encoder = CLIPTextModel.from_pretrained("/sddata/dreambooth/daruma-v2-1/checkpoint-100/text_encoder")
+
+pipeline = DiffusionPipeline.from_pretrained(model_id, unet=unet, text_encoder=text_encoder, dtype=torch.float16)
+pipeline.to("cuda")
+
+# Perform inference, or save, or push to the hub
+pipeline.save_pretrained("dreambooth-pipeline")
+```
+
+If you have **`"accelerate<0.16.0"`** installed, you need to convert it to an inference pipeline first:
 
 ```python
 from accelerate import Accelerator
@@ -156,15 +315,37 @@ pipeline = DiffusionPipeline.from_pretrained(
 pipeline.save_pretrained("dreambooth-pipeline")
 ```
 
-### Training on a 16GB GPU
+## Optimizations for different GPU sizes
 
-With the help of gradient checkpointing and the 8-bit optimizer from [bitsandbytes](https://github.com/TimDettmers/bitsandbytes), it's possible to train dreambooth on a 16GB GPU.
+Depending on your hardware, there are a few different ways to optimize DreamBooth on GPUs from 16GB to just 8GB! 
+
+### xFormers
+
+[xFormers](https://github.com/facebookresearch/xformers) is a toolbox for optimizing Transformers, and it include a [memory-efficient attention](https://facebookresearch.github.io/xformers/components/ops.html#module-xformers.ops) mechanism that is used in 🧨 Diffusers. You'll need to [install xFormers](./optimization/xformers) and then add the following argument to your training script:
+
+```bash
+  --enable_xformers_memory_efficient_attention
+```
+
+xFormers is not available in Flax.
+
+### Set gradients to none
+
+Another way you can lower your memory footprint is to [set the gradients](https://pytorch.org/docs/stable/generated/torch.optim.Optimizer.zero_grad.html) to `None` instead of zero. However, this may change certain behaviors, so if you run into any issues, try removing this argument. Add the following argument to your training script to set the gradients to `None`:
+
+```bash
+  --set_grads_to_none
+```
+
+### 16GB GPU
+
+With the help of gradient checkpointing and [bitsandbytes](https://github.com/TimDettmers/bitsandbytes) 8-bit optimizer, it's possible to train DreamBooth on a 16GB GPU. Make sure you have bitsandbytes installed:
 
 ```bash
 pip install bitsandbytes
 ```
 
-Then pass the `--use_8bit_adam` option to the training script.
+Then pass the `--use_8bit_adam` option to the training script:
 
 ```bash
 export MODEL_NAME="CompVis/stable-diffusion-v1-4"
@@ -191,25 +372,18 @@ accelerate launch train_dreambooth.py \
   --max_train_steps=800
 ```
 
-### Fine-tune the text encoder in addition to the UNet
+### 12GB GPU
 
-The script also allows to fine-tune the `text_encoder` along with the `unet`. It has been observed experimentally that this gives much better results, especially on faces. Please, refer to [our blog](https://huggingface.co/blog/dreambooth) for more details.
-
-To enable this option, pass the `--train_text_encoder` argument to the training script.
-
-<Tip>
-Training the text encoder requires additional memory, so training won't fit on a 16GB GPU. You'll need at least 24GB VRAM to use this option.
-</Tip>
+To run DreamBooth on a 12GB GPU, you'll need to enable gradient checkpointing, the 8-bit optimizer, xFormers, and set the gradients to `None`: 
 
 ```bash
 export MODEL_NAME="CompVis/stable-diffusion-v1-4"
-export INSTANCE_DIR="path_to_training_images"
-export CLASS_DIR="path_to_class_images"
-export OUTPUT_DIR="path_to_saved_model"
+export INSTANCE_DIR="path-to-instance-images"
+export CLASS_DIR="path-to-class-images"
+export OUTPUT_DIR="path-to-save-model"
 
 accelerate launch train_dreambooth.py \
   --pretrained_model_name_or_path=$MODEL_NAME  \
-  --train_text_encoder \
   --instance_data_dir=$INSTANCE_DIR \
   --class_data_dir=$CLASS_DIR \
   --output_dir=$OUTPUT_DIR \
@@ -218,8 +392,10 @@ accelerate launch train_dreambooth.py \
   --class_prompt="a photo of dog" \
   --resolution=512 \
   --train_batch_size=1 \
-  --use_8bit_adam
-  --gradient_checkpointing \
+  --gradient_accumulation_steps=1 --gradient_checkpointing \
+  --use_8bit_adam \
+  --enable_xformers_memory_efficient_attention \
+  --set_grads_to_none \
   --learning_rate=2e-6 \
   --lr_scheduler="constant" \
   --lr_warmup_steps=0 \
@@ -227,19 +403,25 @@ accelerate launch train_dreambooth.py \
   --max_train_steps=800
 ```
 
-### Training on a 8 GB GPU:
+### 8 GB GPU
 
-Using [DeepSpeed](https://www.deepspeed.ai/) it's even possible to offload some
-tensors from VRAM to either CPU or NVME, allowing training to proceed with less GPU memory.
+For 8GB GPUs, you'll need the help of [DeepSpeed](https://www.deepspeed.ai/) to offload some
+tensors from the VRAM to either the CPU or NVME, enabling training with less GPU memory.
 
-DeepSpeed needs to be enabled with `accelerate config`. During configuration,
-answer yes to "Do you want to use DeepSpeed?". Combining DeepSpeed stage 2, fp16
-mixed precision, and offloading both the model parameters and the optimizer state to CPU, it's
-possible to train on under 8 GB VRAM. The drawback is that this requires more system RAM (about 25 GB). See [the DeepSpeed documentation](https://huggingface.co/docs/accelerate/usage_guides/deepspeed) for more configuration options.
+Run the following command to configure your 🤗 Accelerate environment:
 
-Changing the default Adam optimizer to DeepSpeed's special version of Adam
-`deepspeed.ops.adam.DeepSpeedCPUAdam` gives a substantial speedup, but enabling
-it requires the system's CUDA toolchain version to be the same as the one installed with PyTorch. 8-bit optimizers don't seem to be compatible with DeepSpeed at the moment.
+```bash
+accelerate config
+```
+
+During configuration, confirm that you want to use DeepSpeed. Now it's possible to train on under 8GB VRAM by combining DeepSpeed stage 2, fp16 mixed precision, and offloading the model parameters and the optimizer state to the CPU. The drawback is that this requires more system RAM, about 25 GB. See [the DeepSpeed documentation](https://huggingface.co/docs/accelerate/usage_guides/deepspeed) for more configuration options.
+
+You should also change the default Adam optimizer to DeepSpeed's optimized version of Adam
+[`deepspeed.ops.adam.DeepSpeedCPUAdam`](https://deepspeed.readthedocs.io/en/latest/optimizers.html#adam-cpu) for a substantial speedup. Enabling `DeepSpeedCPUAdam` requires your system's CUDA toolchain version to be the same as the one installed with PyTorch. 
+
+8-bit optimizers don't seem to be compatible with DeepSpeed at the moment.
+
+Launch training with the following command:
 
 ```bash
 export MODEL_NAME="CompVis/stable-diffusion-v1-4"
@@ -269,7 +451,10 @@ accelerate launch train_dreambooth.py \
 
 ## Inference
 
-Once you have trained a model, inference can be done using the `StableDiffusionPipeline`, by simply indicating the path where the model was saved. Make sure that your prompts include the special `identifier` used during training (`sks` in the previous examples).
+Once you have trained a model, specify the path to where the model is saved, and use it for inference in the [`StableDiffusionPipeline`]. Make sure your prompts include the special `identifier` used during training (`sks` in the previous examples).
+
+If you have **`"accelerate>=0.16.0"`** installed, you can use the following code to run 
+inference from an intermediate checkpoint:
 
 ```python
 from diffusers import StableDiffusionPipeline
@@ -284,4 +469,4 @@ image = pipe(prompt, num_inference_steps=50, guidance_scale=7.5).images[0]
 image.save("dog-bucket.png")
 ```
 
-You may also run inference from [any of the saved training checkpoints](#performing-inference-using-a-saved-checkpoint).
+You may also run inference from any of the [saved training checkpoints](#inference-from-a-saved-checkpoint).

docs/source/en/training/lora.mdx

@@ -10,54 +10,151 @@ an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express o
 specific language governing permissions and limitations under the License.
 -->
 
-# LoRA Support in Diffusers 
+# Low-Rank Adaptation of Large Language Models (LoRA)
 
-Diffusers supports LoRA for faster fine-tuning of Stable Diffusion, allowing greater memory efficiency and easier portability. 
+[[open-in-colab]]
 
-Low-Rank Adaption of Large Language Models was first introduced by Microsoft in
-[LoRA: Low-Rank Adaptation of Large Language Models](https://arxiv.org/abs/2106.09685) by *Edward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen*.
+<Tip warning={true}>
 
-In a nutshell, LoRA allows adapting pretrained models by adding pairs of rank-decomposition weight matrices (called **update matrices**) 
-to existing weights and **only** training those newly added weights. This has a couple of advantages:
-
-- Previous pretrained weights are kept frozen so that the model is not so prone to [catastrophic forgetting](https://www.pnas.org/doi/10.1073/pnas.1611835114). 
-- Rank-decomposition matrices have significantly fewer parameters than the original model, which means that trained LoRA weights are easily portable.
-- LoRA matrices are generally added to the attention layers of the original model and they control to which extent the model is adapted toward new training images via a `scale` parameter.
-
-**__Note that the usage of LoRA is not just limited to attention layers. In the original LoRA work, the authors found out that just amending
-the attention layers of a language model is sufficient to obtain good downstream performance with great efficiency. This is why, it's common
-to just add the LoRA weights to the attention layers of a model.__**
-
-[cloneofsimo](https://github.com/cloneofsimo) was the first to try out LoRA training for Stable Diffusion in the popular [lora](https://github.com/cloneofsimo/lora) GitHub repository.
-
-<Tip>
-
-LoRA allows us to achieve greater memory efficiency since the pretrained weights are kept frozen and only the LoRA weights are trained, thereby
-allowing us to run fine-tuning on consumer GPUs like Tesla T4, RTX 3080 or even RTX 2080 Ti! One can get access to GPUs like T4 in the free 
-tiers of Kaggle Kernels and Google Colab Notebooks.
+Currently, LoRA is only supported for the attention layers of the [`UNet2DConditionalModel`].
 
 </Tip>
 
-## Getting started with LoRA for fine-tuning
+[Low-Rank Adaptation of Large Language Models (LoRA)](https://arxiv.org/abs/2106.09685) is a training method that accelerates the training of large models while consuming less memory. It adds pairs of rank-decomposition weight matrices (called **update matrices**) to existing weights, and **only** trains those newly added weights. This has a couple of advantages:
 
-Stable Diffusion can be fine-tuned in different ways:
+- Previous pretrained weights are kept frozen so the model is not as prone to [catastrophic forgetting](https://www.pnas.org/doi/10.1073/pnas.1611835114).
+- Rank-decomposition matrices have significantly fewer parameters than the original model, which means that trained LoRA weights are easily portable.
+- LoRA matrices are generally added to the attention layers of the original model. 🧨 Diffusers provides the [`~diffusers.loaders.UNet2DConditionLoadersMixin.load_attn_procs`] method to load the LoRA weights into a model's attention layers. You can control the extent to which the model is adapted toward new training images via a `scale` parameter. 
+- The greater memory-efficiency allows you to run fine-tuning on consumer GPUs like the Tesla T4, RTX 3080 or even the RTX 2080 Ti! GPUs like the T4 are free and readily accessible in Kaggle or Google Colab notebooks.
 
-* [Textual inversion](https://huggingface.co/docs/diffusers/main/en/training/text_inversion)
-* [DreamBooth](https://huggingface.co/docs/diffusers/main/en/training/dreambooth) 
-* [Text2Image fine-tuning](https://huggingface.co/docs/diffusers/main/en/training/text2image) 
+<Tip>
 
-We provide two end-to-end examples that show how to run fine-tuning with LoRA:
+💡 LoRA is not only limited to attention layers. The authors found that amending
+the attention layers of a language model is sufficient to obtain good downstream performance with great efficiency. This is why it's common to just add the LoRA weights to the attention layers of a model. Check out the [Using LoRA for efficient Stable Diffusion fine-tuning](https://huggingface.co/blog/lora) blog for more information about how LoRA works!
 
-* [DreamBooth](https://github.com/huggingface/diffusers/tree/main/examples/dreambooth#training-with-low-rank-adaptation-of-large-language-models-lora) 
-* [Text2Image](https://github.com/huggingface/diffusers/tree/main/examples/text_to_image#training-with-lora)
+</Tip>
 
-If you want to perform DreamBooth training with LoRA, for instance, you would run:
+[cloneofsimo](https://github.com/cloneofsimo) was the first to try out LoRA training for Stable Diffusion in the popular [lora](https://github.com/cloneofsimo/lora) GitHub repository. 🧨 Diffusers now supports finetuning with LoRA for [text-to-image generation](https://github.com/huggingface/diffusers/tree/main/examples/text_to_image#training-with-lora) and [DreamBooth](https://github.com/huggingface/diffusers/tree/main/examples/dreambooth#training-with-low-rank-adaptation-of-large-language-models-lora). This guide will show you how to do both.
+
+If you'd like to store or share your model with the community, login to your Hugging Face account (create [one](hf.co/join) if you don't have one already):
+
+```bash
+huggingface-cli login
+```
+
+## Text-to-image
+
+Finetuning a model like Stable Diffusion, which has billions of parameters, can be slow and difficult. With LoRA, it is much easier and faster to finetune a diffusion model. It can run on hardware with as little as 11GB of GPU RAM without resorting to tricks such as 8-bit optimizers.
+
+### Training[[text-to-image-training]]
+
+Let's finetune [`stable-diffusion-v1-5`](https://huggingface.co/runwayml/stable-diffusion-v1-5) on the [Pokémon BLIP captions](https://huggingface.co/datasets/lambdalabs/pokemon-blip-captions) dataset to generate your own Pokémon.
+
+To start, make sure you have the `MODEL_NAME` and `DATASET_NAME` environment variables set. The `OUTPUT_DIR` and `HUB_MODEL_ID` variables are optional and specify where to save the model to on the Hub:
+
+```bash
+export MODEL_NAME="runwayml/stable-diffusion-v1-5"
+export OUTPUT_DIR="/sddata/finetune/lora/pokemon"
+export HUB_MODEL_ID="pokemon-lora"
+export DATASET_NAME="lambdalabs/pokemon-blip-captions"
+```
+
+There are some flags to be aware of before you start training:
+
+* `--push_to_hub` stores the trained LoRA embeddings on the Hub.
+* `--report_to=wandb` reports and logs the training results to your Weights & Biases dashboard (as an example, take a look at this [report](https://wandb.ai/pcuenq/text2image-fine-tune/runs/b4k1w0tn?workspace=user-pcuenq)).
+* `--learning_rate=1e-04`, you can afford to use a higher learning rate than you normally would with LoRA.
+
+Now you're ready to launch the training (you can find the full training script [here](https://github.com/huggingface/diffusers/blob/main/examples/text_to_image/train_text_to_image_lora.py)):
+
+```bash
+accelerate launch --mixed_precision="fp16"  train_text_to_image_lora.py \
+  --pretrained_model_name_or_path=$MODEL_NAME \
+  --dataset_name=$DATASET_NAME \
+  --dataloader_num_workers=8 \
+  --resolution=512 --center_crop --random_flip \
+  --train_batch_size=1 \
+  --gradient_accumulation_steps=4 \
+  --max_train_steps=15000 \
+  --learning_rate=1e-04 \
+  --max_grad_norm=1 \
+  --lr_scheduler="cosine" --lr_warmup_steps=0 \
+  --output_dir=${OUTPUT_DIR} \
+  --push_to_hub \
+  --hub_model_id=${HUB_MODEL_ID} \
+  --report_to=wandb \
+  --checkpointing_steps=500 \
+  --validation_prompt="A pokemon with blue eyes." \
+  --seed=1337
+```
+
+### Inference[[text-to-image-inference]]
+
+Now you can use the model for inference by loading the base model in the [`StableDiffusionPipeline`] and then the [`DPMSolverMultistepScheduler`]:
+
+```py
+>>> import torch
+>>> from diffusers import StableDiffusionPipeline, DPMSolverMultistepScheduler
+
+>>> model_base = "runwayml/stable-diffusion-v1-5"
+
+>>> pipe = StableDiffusionPipeline.from_pretrained(model_base, torch_dtype=torch.float16)
+>>> pipe.scheduler = DPMSolverMultistepScheduler.from_config(pipe.scheduler.config)
+```
+
+Load the LoRA weights from your finetuned model *on top of the base model weights*, and then move the pipeline to a GPU for faster inference. When you merge the LoRA weights with the frozen pretrained model weights, you can optionally adjust how much of the weights to merge with the `scale` parameter:
+
+<Tip>
+
+💡 A `scale` value of `0` is the same as not using your LoRA weights and you're only using the base model weights, and a `scale` value of `1` means you're only using the fully finetuned LoRA weights. Values between `0` and `1` interpolates between the two weights.
+
+</Tip>
+
+```py
+>>> pipe.unet.load_attn_procs(model_path)
+>>> pipe.to("cuda")
+# use half the weights from the LoRA finetuned model and half the weights from the base model
+
+>>> image = pipe(
+...     "A pokemon with blue eyes.", num_inference_steps=25, guidance_scale=7.5, cross_attention_kwargs={"scale": 0.5}
+... ).images[0]
+# use the weights from the fully finetuned LoRA model
+
+>>> image = pipe("A pokemon with blue eyes.", num_inference_steps=25, guidance_scale=7.5).images[0]
+>>> image.save("blue_pokemon.png")
+```
+
+## DreamBooth
+
+[DreamBooth](https://arxiv.org/abs/2208.12242) is a finetuning technique for personalizing a text-to-image model like Stable Diffusion to generate photorealistic images of a subject in different contexts, given a few images of the subject. However, DreamBooth is very sensitive to hyperparameters and it is easy to overfit. Some important hyperparameters to consider include those that affect the training time (learning rate, number of training steps), and inference time (number of steps, scheduler type).
+
+<Tip>
+
+💡 Take a look at the [Training Stable Diffusion with DreamBooth using 🧨 Diffusers](https://huggingface.co/blog/dreambooth) blog for an in-depth analysis of DreamBooth experiments and recommended settings.
+
+</Tip>
+
+### Training[[dreambooth-training]]
+
+Let's finetune [`stable-diffusion-v1-5`](https://huggingface.co/runwayml/stable-diffusion-v1-5) with DreamBooth and LoRA with some 🐶 [dog images](https://drive.google.com/drive/folders/1BO_dyz-p65qhBRRMRA4TbZ8qW4rB99JZ). Download and save these images to a directory.
+
+To start, make sure you have the `MODEL_NAME` and `INSTANCE_DIR` (path to directory containing images) environment variables set. The `OUTPUT_DIR` variables is optional and specifies where to save the model to on the Hub:
 
 ```bash
 export MODEL_NAME="runwayml/stable-diffusion-v1-5"
 export INSTANCE_DIR="path-to-instance-images"
 export OUTPUT_DIR="path-to-save-model"
+```
 
+There are some flags to be aware of before you start training:
+
+* `--push_to_hub` stores the trained LoRA embeddings on the Hub.
+* `--report_to=wandb` reports and logs the training results to your Weights & Biases dashboard (as an example, take a look at this [report](https://wandb.ai/pcuenq/text2image-fine-tune/runs/b4k1w0tn?workspace=user-pcuenq)).
+* `--learning_rate=1e-04`, you can afford to use a higher learning rate than you normally would with LoRA.
+
+Now you're ready to launch the training (you can find the full training script [here](https://github.com/huggingface/diffusers/blob/main/examples/dreambooth/train_dreambooth_lora.py)):
+
+```bash
 accelerate launch train_dreambooth_lora.py \
   --pretrained_model_name_or_path=$MODEL_NAME  \
   --instance_data_dir=$INSTANCE_DIR \
@@ -78,101 +175,40 @@ accelerate launch train_dreambooth_lora.py \
   --push_to_hub
 ```
 
-A similar process can be followed to fully fine-tune Stable Diffusion on a custom dataset using the
-`examples/text_to_image/train_text_to_image_lora.py` script.
+### Inference[[dreambooth-inference]]
 
-Refer to the respective examples linked above to learn more. 
+Now you can use the model for inference by loading the base model in the [`StableDiffusionPipeline`]:
+
+```py
+>>> import torch
+>>> from diffusers import StableDiffusionPipeline
+
+>>> model_base = "runwayml/stable-diffusion-v1-5"
+
+>>> pipe = StableDiffusionPipeline.from_pretrained(model_base, torch_dtype=torch.float16)
+```
+
+Load the LoRA weights from your finetuned DreamBooth model *on top of the base model weights*, and then move the pipeline to a GPU for faster inference. When you merge the LoRA weights with the frozen pretrained model weights, you can optionally adjust how much of the weights to merge with the `scale` parameter:
 
 <Tip>
 
-When using LoRA we can use a much higher learning rate (typically 1e-4 as opposed to ~1e-6) compared to non-LoRA Dreambooth fine-tuning.
+💡 A `scale` value of `0` is the same as not using your LoRA weights and you're only using the base model weights, and a `scale` value of `1` means you're only using the fully finetuned LoRA weights. Values between `0` and `1` interpolates between the two weights.
 
 </Tip>
 
-But there is no free lunch. For the given dataset and expected generation quality, you'd still need to experiment with
-different hyperparameters. Here are some important ones:
-
-* Training time
-    * Learning rate 
-    * Number of training steps
-* Inference time 
-    * Number of steps 
-    * Scheduler type
-
-Additionally, you can follow [this blog](https://huggingface.co/blog/dreambooth) that documents some of our experimental
-findings for performing DreamBooth training of Stable Diffusion.
-
-When fine-tuning, the LoRA update matrices are only added to the attention layers. To enable this, we added new weight
-loading functionalities. Their details are available [here](https://huggingface.co/docs/diffusers/main/en/api/loaders).
-
-## Inference 
-
-Assuming you used the `examples/text_to_image/train_text_to_image_lora.py` to fine-tune Stable Diffusion on the [Pokemon
-dataset](https://huggingface.co/datasets/lambdalabs/pokemon-blip-captions), you can perform inference like so: 
-
-```py 
-from diffusers import StableDiffusionPipeline
-import torch
-
-model_path = "sayakpaul/sd-model-finetuned-lora-t4"
-pipe = StableDiffusionPipeline.from_pretrained("CompVis/stable-diffusion-v1-4", torch_dtype=torch.float16)
-pipe.unet.load_attn_procs(model_path)
-pipe.to("cuda")
-
-prompt = "A pokemon with blue eyes."
-image = pipe(prompt, num_inference_steps=30, guidance_scale=7.5).images[0]
-image.save("pokemon.png")
-```
-
-Here are some example images you can expect:
-
-<img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pokemon-collage.png"/>
-
-[`sayakpaul/sd-model-finetuned-lora-t4`](https://huggingface.co/sayakpaul/sd-model-finetuned-lora-t4) contains [LoRA fine-tuned update matrices](https://huggingface.co/sayakpaul/sd-model-finetuned-lora-t4/blob/main/pytorch_lora_weights.bin)
-which is only 3 MBs in size. During inference, the pre-trained Stable Diffusion checkpoints are loaded alongside these update
-matrices and then they are combined to run inference.
-
-You can use the [`huggingface_hub`](https://github.com/huggingface/huggingface_hub) library to retrieve the base model
-from [`sayakpaul/sd-model-finetuned-lora-t4`](https://huggingface.co/sayakpaul/sd-model-finetuned-lora-t4) like so:
-
 ```py
-from huggingface_hub.repocard import RepoCard
+>>> pipe.unet.load_attn_procs(model_path)
+>>> pipe.to("cuda")
+# use half the weights from the LoRA finetuned model and half the weights from the base model
 
-card = RepoCard.load("sayakpaul/sd-model-finetuned-lora-t4")
-base_model = card.data.to_dict()["base_model"]
-# 'CompVis/stable-diffusion-v1-4'
-```
+>>> image = pipe(
+...     "A picture of a sks dog in a bucket.",
+...     num_inference_steps=25,
+...     guidance_scale=7.5,
+...     cross_attention_kwargs={"scale": 0.5},
+... ).images[0]
+# use the weights from the fully finetuned LoRA model
 
-And then you can use `pipe = StableDiffusionPipeline.from_pretrained(base_model, torch_dtype=torch.float16)`.
-
-This is especially useful when you don't want to hardcode the base model identifier during initializing the `StableDiffusionPipeline`.
-
-Inference for DreamBooth training remains the same. Check
-[this section](https://github.com/huggingface/diffusers/tree/main/examples/dreambooth#inference-1) for more details. 
-
-### Merging LoRA with original model
-
-When performing inference, you can merge the trained LoRA weights with the frozen pre-trained model weights, to interpolate between the original model's inference result (as if no fine-tuning had occurred) and the fully fine-tuned version.
-
-You can adjust the merging ratio with a parameter called α (alpha) in the paper, or `scale` in our implementation. You can tweak it with the following code, that passes `scale` as `cross_attention_kwargs` in the pipeline call:
-
-```py 
-from diffusers import StableDiffusionPipeline
-import torch
-
-model_path = "sayakpaul/sd-model-finetuned-lora-t4"
-pipe = StableDiffusionPipeline.from_pretrained("CompVis/stable-diffusion-v1-4", torch_dtype=torch.float16)
-pipe.unet.load_attn_procs(model_path)
-pipe.to("cuda")
-
-prompt = "A pokemon with blue eyes."
-image = pipe(prompt, num_inference_steps=30, guidance_scale=7.5, cross_attention_kwargs={"scale": 0.5}).images[0]
-image.save("pokemon.png")
-```
-
-A value of `0` is the same as _not_ using the LoRA weights, whereas `1` means only the LoRA fine-tuned weights will be used. Values between 0 and 1 will interpolate between the two versions.
-
-
-## Known limitations 
-
-* Currently, we only support LoRA for the attention layers of [`UNet2DConditionModel`](https://huggingface.co/docs/diffusers/main/en/api/models#diffusers.UNet2DConditionModel).
+>>> image = pipe("A picture of a sks dog in a bucket.", num_inference_steps=25, guidance_scale=7.5).images[0]
+>>> image.save("bucket-dog.png")
+```

docs/source/en/training/overview.mdx

@@ -1,4 +1,4 @@
-<!--Copyright 2022 The HuggingFace Team. All rights reserved.
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at

docs/source/en/training/text2image.mdx

@@ -1,4 +1,4 @@
-<!--Copyright 2022 The HuggingFace Team. All rights reserved.
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at
@@ -11,20 +11,15 @@ specific language governing permissions and limitations under the License.
 -->
 
 
-# Stable Diffusion text-to-image fine-tuning
-
-The [`train_text_to_image.py`](https://github.com/huggingface/diffusers/tree/main/examples/text_to_image) script shows how to fine-tune the stable diffusion model on your own dataset.
+# Text-to-image
 
 <Tip warning={true}>
 
-The text-to-image fine-tuning script is experimental. It's easy to overfit and run into issues like catastrophic forgetting. We recommend to explore different hyperparameters to get the best results on your dataset.
+The text-to-image fine-tuning script is experimental. It's easy to overfit and run into issues like catastrophic forgetting. We recommend you explore different hyperparameters to get the best results on your dataset.
 
 </Tip>
 
-
-## Running locally 
-
-### Installing the dependencies
+Text-to-image models like Stable Diffusion generate an image from a text prompt. This guide will show you how to finetune the [`CompVis/stable-diffusion-v1-4`](https://huggingface.co/CompVis/stable-diffusion-v1-4) model on your own dataset with PyTorch and Flax. All the training scripts for text-to-image finetuning used in this guide can be found in this [repository](https://github.com/huggingface/diffusers/tree/main/examples/text_to_image) if you're interested in taking a closer look.
 
 Before running the scripts, make sure to install the library's training dependencies:
 
@@ -33,32 +28,51 @@ pip install git+https://github.com/huggingface/diffusers.git
 pip install -U -r requirements.txt
 ```
 
-And initialize an [🤗Accelerate](https://github.com/huggingface/accelerate/) environment with:
+And initialize an [🤗 Accelerate](https://github.com/huggingface/accelerate/) environment with:
 
 ```bash
 accelerate config
 ```
 
-You need to accept the model license before downloading or using the weights. In this example we'll use model version `v1-4`, so you'll need to visit [its card](https://huggingface.co/CompVis/stable-diffusion-v1-4), read the license and tick the checkbox if you agree. 
-
-You have to be a registered user in 🤗 Hugging Face Hub, and you'll also need to use an access token for the code to work. For more information on access tokens, please refer to [this section of the documentation](https://huggingface.co/docs/hub/security-tokens).
-
-Run the following command to authenticate your token
-
-```bash
-huggingface-cli login
-```
-
 If you have already cloned the repo, then you won't need to go through these steps. Instead, you can pass the path to your local checkout to the training script and it will be loaded from there.
 
-### Hardware Requirements for Fine-tuning
+## Hardware requirements
 
-Using `gradient_checkpointing` and `mixed_precision` it should be possible to fine tune the model on a single 24GB GPU. For higher `batch_size` and faster training it's better to use GPUs with more than 30GB of GPU memory. You can also use JAX / Flax for fine-tuning on TPUs or GPUs, see [below](#flax-jax-finetuning) for details.
+Using `gradient_checkpointing` and `mixed_precision`, it should be possible to finetune the model on a single 24GB GPU. For higher `batch_size`'s and faster training, it's better to use GPUs with more than 30GB of GPU memory. You can also use JAX/Flax for fine-tuning on TPUs or GPUs, which will be covered [below](#flax-jax-finetuning).
 
-### Fine-tuning Example
+You can reduce your memory footprint even more by enabling memory efficient attention with xFormers. Make sure you have [xFormers installed](./optimization/xformers) and pass the `--enable_xformers_memory_efficient_attention` flag to the training script.
 
-The following script will launch a fine-tuning run using [Justin Pinkneys' captioned Pokemon dataset](https://huggingface.co/datasets/lambdalabs/pokemon-blip-captions), available in Hugging Face Hub.
+xFormers is not available for Flax.
 
+## Upload model to Hub
+
+Store your model on the Hub by adding the following argument to the training script:
+
+```bash
+  --push_to_hub
+```
+
+## Save and load checkpoints
+
+It is a good idea to regularly save checkpoints in case anything happens during training. To save a checkpoint, pass the following argument to the training script:
+
+```bash
+  --checkpointing_steps=500
+```
+
+Every 500 steps, the full training state is saved in a subfolder in the `output_dir`. The checkpoint has the format `checkpoint-` followed by the number of steps trained so far. For example, `checkpoint-1500` is a checkpoint saved after 1500 training steps.
+
+To load a checkpoint to resume training, pass the argument `--resume_from_checkpoint` to the training script and specify the checkpoint you want to resume from. For example, the following argument resumes training from the checkpoint saved after 1500 training steps:
+
+```bash
+  --resume_from_checkpoint="checkpoint-1500"
+```
+
+## Fine-tuning
+
+<frameworkcontent>
+<pt>
+Launch the [PyTorch training script](https://github.com/huggingface/diffusers/blob/main/examples/text_to_image/train_text_to_image.py) for a fine-tuning run on the [Pokémon BLIP captions](https://huggingface.co/datasets/lambdalabs/pokemon-blip-captions) dataset like this:
 
 ```bash
 export MODEL_NAME="CompVis/stable-diffusion-v1-4"
@@ -80,9 +94,9 @@ accelerate launch train_text_to_image.py \
   --output_dir="sd-pokemon-model" 
 ```
 
-To run on your own training files you need to prepare the dataset according to the format required by `datasets`. You can upload your dataset to the Hub, or you can prepare a local folder with your files. [This documentation](https://huggingface.co/docs/datasets/v2.4.0/en/image_load#imagefolder-with-metadata) explains how to do it.
+To finetune on your own dataset, prepare the dataset according to the format required by 🤗 [Datasets](https://huggingface.co/docs/datasets/index). You can [upload your dataset to the Hub](https://huggingface.co/docs/datasets/image_dataset#upload-dataset-to-the-hub), or you can [prepare a local folder with your files](https://huggingface.co/docs/datasets/image_dataset#imagefolder).
 
-You should modify the script if you wish to use custom loading logic. We have left pointers in the code in the appropriate places :)
+Modify the script if you want to use custom loading logic. We left pointers in the code in the appropriate places to help you. 🤗 The example script below shows how to finetune on a local dataset in `TRAIN_DIR` and where to save the model to in `OUTPUT_DIR`:
 
 ```bash
 export MODEL_NAME="CompVis/stable-diffusion-v1-4"
@@ -104,25 +118,19 @@ accelerate launch train_text_to_image.py \
   --lr_scheduler="constant" --lr_warmup_steps=0 \
   --output_dir=${OUTPUT_DIR}
 ```
+</pt>
+<jax>
+With Flax, it's possible to train a Stable Diffusion model faster on TPUs and GPUs thanks to [@duongna211](https://github.com/duongna21). This is very efficient on TPU hardware but works great on GPUs too. The Flax training script doesn't support features like gradient checkpointing or gradient accumulation yet, so you'll need a GPU with at least 30GB of memory or a TPU v3.
 
-Once training is finished the model will be saved to the `OUTPUT_DIR` specified in the command. To load the fine-tuned model for inference, just pass that path to `StableDiffusionPipeline`:
+Before running the script, make sure you have the requirements installed:
 
-```python
-from diffusers import StableDiffusionPipeline
-
-model_path = "path_to_saved_model"
-pipe = StableDiffusionPipeline.from_pretrained(model_path, torch_dtype=torch.float16)
-pipe.to("cuda")
-
-image = pipe(prompt="yoda").images[0]
-image.save("yoda-pokemon.png")
+```bash
+pip install -U -r requirements_flax.txt
 ```
 
-### Flax / JAX fine-tuning
+Now you can launch the [Flax training script](https://github.com/huggingface/diffusers/blob/main/examples/text_to_image/train_text_to_image_flax.py) like this:
 
-Thanks to [@duongna211](https://github.com/duongna21) it's possible to fine-tune Stable Diffusion using Flax! This is very efficient on TPU hardware but works great on GPUs too. You can use the [Flax training script](https://github.com/huggingface/diffusers/blob/main/examples/text_to_image/train_text_to_image_flax.py) like this:
-
-```Python
+```bash
 export MODEL_NAME="runwayml/stable-diffusion-v1-5"
 export dataset_name="lambdalabs/pokemon-blip-captions"
 
@@ -136,3 +144,77 @@ python train_text_to_image_flax.py \
   --max_grad_norm=1 \
   --output_dir="sd-pokemon-model" 
 ```
+
+To finetune on your own dataset, prepare the dataset according to the format required by 🤗 [Datasets](https://huggingface.co/docs/datasets/index). You can [upload your dataset to the Hub](https://huggingface.co/docs/datasets/image_dataset#upload-dataset-to-the-hub), or you can [prepare a local folder with your files](https://huggingface.co/docs/datasets/image_dataset#imagefolder).
+
+Modify the script if you want to use custom loading logic. We left pointers in the code in the appropriate places to help you. 🤗 The example script below shows how to finetune on a local dataset in `TRAIN_DIR`:
+
+```bash
+export MODEL_NAME="duongna/stable-diffusion-v1-4-flax"
+export TRAIN_DIR="path_to_your_dataset"
+
+python train_text_to_image_flax.py \
+  --pretrained_model_name_or_path=$MODEL_NAME \
+  --train_data_dir=$TRAIN_DIR \
+  --resolution=512 --center_crop --random_flip \
+  --train_batch_size=1 \
+  --mixed_precision="fp16" \
+  --max_train_steps=15000 \
+  --learning_rate=1e-05 \
+  --max_grad_norm=1 \
+  --output_dir="sd-pokemon-model"
+```
+</jax>
+</frameworkcontent>
+
+## LoRA
+
+You can also use Low-Rank Adaptation of Large Language Models (LoRA), a fine-tuning technique for accelerating training large models, for fine-tuning text-to-image models. For more details, take a look at the [LoRA training](lora#text-to-image) guide.
+
+## Inference
+
+Now you can load the fine-tuned model for inference by passing the model path or model name on the Hub to the [`StableDiffusionPipeline`]:
+
+<frameworkcontent>
+<pt>
+```python
+from diffusers import StableDiffusionPipeline
+
+model_path = "path_to_saved_model"
+pipe = StableDiffusionPipeline.from_pretrained(model_path, torch_dtype=torch.float16)
+pipe.to("cuda")
+
+image = pipe(prompt="yoda").images[0]
+image.save("yoda-pokemon.png")
+```
+</pt>
+<jax>
+```python
+import jax
+import numpy as np
+from flax.jax_utils import replicate
+from flax.training.common_utils import shard
+from diffusers import FlaxStableDiffusionPipeline
+
+model_path = "path_to_saved_model"
+pipe, params = FlaxStableDiffusionPipeline.from_pretrained(model_path, dtype=jax.numpy.bfloat16)
+
+prompt = "yoda pokemon"
+prng_seed = jax.random.PRNGKey(0)
+num_inference_steps = 50
+
+num_samples = jax.device_count()
+prompt = num_samples * [prompt]
+prompt_ids = pipeline.prepare_inputs(prompt)
+
+# shard inputs and rng
+params = replicate(params)
+prng_seed = jax.random.split(prng_seed, jax.device_count())
+prompt_ids = shard(prompt_ids)
+
+images = pipeline(prompt_ids, params, prng_seed, num_inference_steps, jit=True).images
+images = pipeline.numpy_to_pil(np.asarray(images.reshape((num_samples,) + images.shape[-3:])))
+image.save("yoda-pokemon.png")
+```
+</jax>
+</frameworkcontent>

docs/source/en/training/text_inversion.mdx

@@ -1,4 +1,4 @@
-<!--Copyright 2022 The HuggingFace Team. All rights reserved.
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at
@@ -14,74 +14,85 @@ specific language governing permissions and limitations under the License.
 
 # Textual Inversion
 
-Textual Inversion is a technique for capturing novel concepts from a small number of example images in a way that can later be used to control text-to-image pipelines. It does so by learning new 'words' in the embedding space of the pipeline's text encoder. These special words can then be used within text prompts to achieve very fine-grained control of the resulting images. 
+[[open-in-colab]]
+
+[Textual Inversion](https://arxiv.org/abs/2208.01618) is a technique for capturing novel concepts from a small number of example images. While the technique was originally demonstrated with a [latent diffusion model](https://github.com/CompVis/latent-diffusion), it has since been applied to other model variants like [Stable Diffusion](https://huggingface.co/docs/diffusers/main/en/conceptual/stable_diffusion). The learned concepts can be used to better control the images generated from text-to-image pipelines. It learns new "words" in the text encoder's embedding space, which are used within text prompts for personalized image generation.
 
 ![Textual Inversion example](https://textual-inversion.github.io/static/images/editing/colorful_teapot.JPG)
-_By using just 3-5 images you can teach new concepts to a model such as Stable Diffusion for personalized image generation ([image source](https://github.com/rinongal/textual_inversion))._
+<small>By using just 3-5 images you can teach new concepts to a model such as Stable Diffusion for personalized image generation <a href="https://github.com/rinongal/textual_inversion">(image source)</a></small>
 
-This technique was introduced in [An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion](https://arxiv.org/abs/2208.01618). The paper demonstrated the concept using a [latent diffusion model](https://github.com/CompVis/latent-diffusion) but the idea has since been applied to other variants such as [Stable Diffusion](https://huggingface.co/docs/diffusers/main/en/conceptual/stable_diffusion).
+This guide will show you how to train a [`runwayml/stable-diffusion-v1-5`](https://huggingface.co/runwayml/stable-diffusion-v1-5) model with Textual Inversion. All the training scripts for Textual Inversion used in this guide can be found [here](https://github.com/huggingface/diffusers/tree/main/examples/textual_inversion) if you're interested in taking a closer look at how things work under the hood.
 
+<Tip>
 
-## How It Works
+There is a community-created collection of trained Textual Inversion models in the [Stable Diffusion Textual Inversion Concepts Library](https://huggingface.co/sd-concepts-library) which are readily available for inference. Over time, this'll hopefully grow into a useful resource as more concepts are added!
 
-![Diagram from the paper showing overview](https://textual-inversion.github.io/static/images/training/training.JPG)
-_Architecture Overview from the [textual inversion blog post](https://textual-inversion.github.io/)_
+</Tip>
 
-Before a text prompt can be used in a diffusion model, it must first be processed into a numerical representation. This typically involves tokenizing the text, converting each token to an embedding and then feeding those embeddings through a model (typically a transformer) whose output will be used as the conditioning for the diffusion model. 
-
-Textual inversion learns a new token embedding (v* in the diagram above). A prompt (that includes a token which will be mapped to this new embedding) is used in conjunction with a noised version of one or more training images as inputs to the generator model, which attempts to predict the denoised version of the image. The embedding is optimized based on how well the model does at this task - an embedding that better captures the object or style shown by the training images will give more useful information to the diffusion model and thus result in a lower denoising loss. After many steps (typically several thousand) with a variety of prompt and image variants the learned embedding should hopefully capture the essence of the new concept being taught.
-
-## Usage
-
-To train your own textual inversions, see the [example script here](https://github.com/huggingface/diffusers/tree/main/examples/textual_inversion). 
-
-There is also a notebook for training:
-[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/sd_textual_inversion_training.ipynb)
-
-And one for inference:
-[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/stable_conceptualizer_inference.ipynb)
-
-In addition to using concepts you have trained yourself, there is a community-created collection of trained textual inversions in the new [Stable Diffusion public concepts library](https://huggingface.co/sd-concepts-library) which you can also use from the inference notebook above. Over time this will hopefully grow into a useful resource as more examples are added.
-
-## Example: Running locally 
-
-The `textual_inversion.py` script [here](https://github.com/huggingface/diffusers/blob/main/examples/textual_inversion) shows how to implement the training procedure and adapt it for stable diffusion.
-
-### Installing the dependencies
-
-Before running the scripts, make sure to install the library's training dependencies.
+Before you begin, make sure you install the library's training dependencies:
 
 ```bash
-pip install diffusers[training] accelerate transformers
+pip install diffusers accelerate transformers
 ```
 
-And initialize an [🤗Accelerate](https://github.com/huggingface/accelerate/) environment with:
+After all the dependencies have been set up, initialize a [🤗Accelerate](https://github.com/huggingface/accelerate/) environment with:
 
 ```bash
 accelerate config
 ```
 
-
-### Cat toy example
-
-You need to accept the model license before downloading or using the weights. In this example we'll use model version `v1-4`, so you'll need to visit [its card](https://huggingface.co/CompVis/stable-diffusion-v1-4), read the license and tick the checkbox if you agree.
-
-You have to be a registered user in 🤗 Hugging Face Hub, and you'll also need to use an access token for the code to work. For more information on access tokens, please refer to [this section of the documentation](https://huggingface.co/docs/hub/security-tokens).
-
-Run the following command to authenticate your token
+To setup a default 🤗 Accelerate environment without choosing any configurations:
 
 ```bash
-huggingface-cli login
+accelerate config default
 ```
 
-If you have already cloned the repo, then you won't need to go through these steps.
+Or if your environment doesn't support an interactive shell like a notebook, you can use:
 
-<br>
+```bash
+from accelerate.utils import write_basic_config
 
-Now let's get our dataset.Download 3-4 images from [here](https://drive.google.com/drive/folders/1fmJMs25nxS_rSNqS5hTcRdLem_YQXbq5) and save them in a directory. This will be our training data.
+write_basic_config()
+```
 
-And launch the training using
+Finally, you try and [install xFormers](https://huggingface.co/docs/diffusers/main/en/training/optimization/xformers) to reduce your memory footprint with xFormers memory-efficient attention. Once you have xFormers installed, add the `--enable_xformers_memory_efficient_attention` argument to the training script. xFormers is not supported for Flax.
 
+## Upload model to Hub
+
+If you want to store your model on the Hub, add the following argument to the training script:
+
+```bash
+--push_to_hub
+```
+
+## Save and load checkpoints
+
+It is often a good idea to regularly save checkpoints of your model during training. This way, you can resume training from a saved checkpoint if your training is interrupted for any reason. To save a checkpoint, pass the following argument to the training script to save the full training state in a subfolder in `output_dir` every 500 steps:
+
+```bash
+--checkpointing_steps=500
+```
+
+To resume training from a saved checkpoint, pass the following argument to the training script and the specific checkpoint you'd like to resume from:
+
+```bash
+--resume_from_checkpoint="checkpoint-1500"
+```
+
+## Finetuning
+
+For your training dataset, download these [images of a cat statue](https://drive.google.com/drive/folders/1fmJMs25nxS_rSNqS5hTcRdLem_YQXbq5) and store them in a directory. 
+
+Set the `MODEL_NAME` environment variable to the model repository id, and the `DATA_DIR` environment variable to the path of the directory containing the images. Now you can launch the [training script](https://github.com/huggingface/diffusers/blob/main/examples/textual_inversion/textual_inversion.py):
+
+<Tip>
+
+💡 A full training run takes ~1 hour on one V100 GPU. While you're waiting for the training to complete, feel free to check out [how Textual Inversion works](#how-it-works) in the section below if you're curious!
+
+</Tip>
+
+<frameworkcontent>
+<pt>
 ```bash
 export MODEL_NAME="runwayml/stable-diffusion-v1-5"
 export DATA_DIR="path-to-dir-containing-images"
@@ -100,14 +111,56 @@ accelerate launch textual_inversion.py \
   --lr_warmup_steps=0 \
   --output_dir="textual_inversion_cat"
 ```
+</pt>
+<jax>
+If you have access to TPUs, try out the [Flax training script](https://github.com/huggingface/diffusers/blob/main/examples/textual_inversion/textual_inversion_flax.py) to train even faster (this'll also work for GPUs). With the same configuration settings, the Flax training script should be at least 70% faster than the PyTorch training script! ⚡️
 
-A full training run takes ~1 hour on one V100 GPU.
+Before you begin, make sure you install the Flax specific dependencies:
 
+```bash
+pip install -U -r requirements_flax.txt
+```
 
-### Inference
+Then you can launch the [training script](https://github.com/huggingface/diffusers/blob/main/examples/textual_inversion/textual_inversion_flax.py):
 
-Once you have trained a model using above command, the inference can be done simply using the `StableDiffusionPipeline`. Make sure to include the `placeholder_token` in your prompt.
+```bash
+export MODEL_NAME="duongna/stable-diffusion-v1-4-flax"
+export DATA_DIR="path-to-dir-containing-images"
 
+python textual_inversion_flax.py \
+  --pretrained_model_name_or_path=$MODEL_NAME \
+  --train_data_dir=$DATA_DIR \
+  --learnable_property="object" \
+  --placeholder_token="<cat-toy>" --initializer_token="toy" \
+  --resolution=512 \
+  --train_batch_size=1 \
+  --max_train_steps=3000 \
+  --learning_rate=5.0e-04 --scale_lr \
+  --output_dir="textual_inversion_cat"
+```
+</jax>
+</frameworkcontent>
+
+### Intermediate logging
+
+If you're interested in following along with your model training progress, you can save the generated images from the training process. Add the following arguments to the training script to enable intermediate logging:
+
+- `validation_prompt`, the prompt used to generate samples (this is set to `None` by default and intermediate logging is disabled)
+- `num_validation_images`, the number of sample images to generate
+- `validation_steps`, the number of steps before generating `num_validation_images` from the `validation_prompt`
+
+```bash
+--validation_prompt="A <cat-toy> backpack"
+--num_validation_images=4
+--validation_steps=100
+```
+
+## Inference
+
+Once you have trained a model, you can use it for inference with the [`StableDiffusionPipeline]. Make sure you include the `placeholder_token` in your prompt, in this case, it is `<cat-toy>`.
+
+<frameworkcontent>
+<pt>
 ```python
 from diffusers import StableDiffusionPipeline
 
@@ -120,3 +173,43 @@ image = pipe(prompt, num_inference_steps=50, guidance_scale=7.5).images[0]
 
 image.save("cat-backpack.png")
 ```
+</pt>
+<jax>
+```python
+import jax
+import numpy as np
+from flax.jax_utils import replicate
+from flax.training.common_utils import shard
+from diffusers import FlaxStableDiffusionPipeline
+
+model_path = "path-to-your-trained-model"
+pipe, params = FlaxStableDiffusionPipeline.from_pretrained(model_path, dtype=jax.numpy.bfloat16)
+
+prompt = "A <cat-toy> backpack"
+prng_seed = jax.random.PRNGKey(0)
+num_inference_steps = 50
+
+num_samples = jax.device_count()
+prompt = num_samples * [prompt]
+prompt_ids = pipeline.prepare_inputs(prompt)
+
+# shard inputs and rng
+params = replicate(params)
+prng_seed = jax.random.split(prng_seed, jax.device_count())
+prompt_ids = shard(prompt_ids)
+
+images = pipeline(prompt_ids, params, prng_seed, num_inference_steps, jit=True).images
+images = pipeline.numpy_to_pil(np.asarray(images.reshape((num_samples,) + images.shape[-3:])))
+image.save("cat-backpack.png")
+```
+</jax>
+</frameworkcontent>
+
+## How it works
+
+![Diagram from the paper showing overview](https://textual-inversion.github.io/static/images/training/training.JPG)
+<small>Architecture overview from the Textual Inversion <a href="https://textual-inversion.github.io/">blog post.</a></small>
+
+Usually, text prompts are tokenized into an embedding before being passed to a model, which is often a transformer. Textual Inversion does something similar, but it learns a new token embedding, `v*`, from a special token `S*` in the diagram above. The model output is used to condition the diffusion model, which helps the diffusion model understand the prompt and new concepts from just a few example images.
+
+To do this, Textual Inversion uses a generator model and noisy versions of the training images. The generator tries to predict less noisy versions of the images, and the token embedding `v*` is optimized based on how well the generator does. If the token embedding successfully captures the new concept, it gives more useful information to the diffusion model and helps create clearer images with less noise. This optimization process typically occurs after several thousand steps of exposure to a variety of prompt and image variants.

docs/source/en/training/unconditional_training.mdx

@@ -1,4 +1,4 @@
-<!--Copyright 2022 The HuggingFace Team. All rights reserved.
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at

docs/source/en/tutorials/basic_training.mdx

@@ -0,0 +1,414 @@
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
+
+Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
+the License. You may obtain a copy of the License at
+
+http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
+an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
+specific language governing permissions and limitations under the License.
+-->
+
+[[open-in-colab]]
+
+# Train a diffusion model
+
+Unconditional image generation is a popular application of diffusion models that generates images that look like those in the dataset used for training. Typically, the best results are obtained from finetuning a pretrained model on a specific dataset. You can find many of these checkpoints on the [Hub](https://huggingface.co/search/full-text?q=unconditional-image-generation&type=model), but if you can't find one you like, you can always train your own!
+
+This tutorial will teach you how to train a [`UNet2DModel`] from scratch on a subset of the [Smithsonian Butterflies](https://huggingface.co/datasets/huggan/smithsonian_butterflies_subset) dataset to generate your own 🦋 butterflies 🦋.
+
+<Tip>
+
+💡 This training tutorial is based on the [Training with 🧨 Diffusers](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/training_example.ipynb) notebook. For additional details and context about diffusion models like how they work, check out the notebook!
+
+</Tip>
+
+Before you begin, make sure you have 🤗 Datasets installed to load and preprocess image datasets, and 🤗 Accelerate, to simplify training on any number of GPUs. The following command will also install [TensorBoard](https://www.tensorflow.org/tensorboard) to visualize training metrics (you can also use [Weights & Biases](https://docs.wandb.ai/) to track your training).
+
+```bash
+!pip install diffusers[training]
+```
+
+We encourage you to share your model with the community, and in order to do that, you'll need to login to your Hugging Face account (create one [here](https://hf.co/join) if you don't already have one!). You can login from a notebook and enter your token when prompted:
+
+```py
+>>> from huggingface_hub import notebook_login
+
+>>> notebook_login()
+```
+
+Or login in from the terminal:
+
+```bash
+huggingface-cli login
+```
+
+Since the model checkpoints are quite large, install [Git-LFS](https://git-lfs.com/) to version these large files:
+
+```bash
+!sudo apt -qq install git-lfs
+!git config --global credential.helper store
+```
+
+## Training configuration
+
+For convenience, create a `TrainingConfig` class containing the training hyperparameters (feel free to adjust them):
+
+```py
+>>> from dataclasses import dataclass
+
+
+>>> @dataclass
+... class TrainingConfig:
+...     image_size = 128  # the generated image resolution
+...     train_batch_size = 16
+...     eval_batch_size = 16  # how many images to sample during evaluation
+...     num_epochs = 50
+...     gradient_accumulation_steps = 1
+...     learning_rate = 1e-4
+...     lr_warmup_steps = 500
+...     save_image_epochs = 10
+...     save_model_epochs = 30
+...     mixed_precision = "fp16"  # `no` for float32, `fp16` for automatic mixed precision
+...     output_dir = "ddpm-butterflies-128"  # the model name locally and on the HF Hub
+
+...     push_to_hub = True  # whether to upload the saved model to the HF Hub
+...     hub_private_repo = False
+...     overwrite_output_dir = True  # overwrite the old model when re-running the notebook
+...     seed = 0
+
+
+>>> config = TrainingConfig()
+```
+
+## Load the dataset
+
+You can easily load the [Smithsonian Butterflies](https://huggingface.co/datasets/huggan/smithsonian_butterflies_subset) dataset with the 🤗 Datasets library:
+
+```py
+>>> from datasets import load_dataset
+
+>>> config.dataset_name = "huggan/smithsonian_butterflies_subset"
+>>> dataset = load_dataset(config.dataset_name, split="train")
+```
+
+<Tip>
+
+💡 You can find additional datasets from the [HugGan Community Event](https://huggingface.co/huggan) or you can use your own dataset by creating a local [`ImageFolder`](https://huggingface.co/docs/datasets/image_dataset#imagefolder). Set `config.dataset_name` to the repository id of the dataset if it is from the HugGan Community Event, or `imagefolder` if you're using your own images.
+
+</Tip>
+
+🤗 Datasets uses the [`~datasets.Image`] feature to automatically decode the image data and load it as a [`PIL.Image`](https://pillow.readthedocs.io/en/stable/reference/Image.html) which we can visualize:
+
+```py
+>>> import matplotlib.pyplot as plt
+
+>>> fig, axs = plt.subplots(1, 4, figsize=(16, 4))
+>>> for i, image in enumerate(dataset[:4]["image"]):
+...     axs[i].imshow(image)
+...     axs[i].set_axis_off()
+>>> fig.show()
+```
+
+<div class="flex justify-center">
+    <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/butterflies_ds.png"/>
+</div>
+
+The images are all different sizes though, so you'll need to preprocess them first:
+
+* `Resize` changes the image size to the one defined in `config.image_size`.
+* `RandomHorizontalFlip` augments the dataset by randomly mirroring the images.
+* `Normalize` is important to rescale the pixel values into a [-1, 1] range, which is what the model expects.
+
+```py
+>>> from torchvision import transforms
+
+>>> preprocess = transforms.Compose(
+...     [
+...         transforms.Resize((config.image_size, config.image_size)),
+...         transforms.RandomHorizontalFlip(),
+...         transforms.ToTensor(),
+...         transforms.Normalize([0.5], [0.5]),
+...     ]
+... )
+```
+
+Use 🤗 Datasets' [`~datasets.Dataset.set_transform`] method to apply the `preprocess` function on the fly during training:
+
+```py
+>>> def transform(examples):
+...     images = [preprocess(image.convert("RGB")) for image in examples["image"]]
+...     return {"images": images}
+
+
+>>> dataset.set_transform(transform)
+```
+
+Feel free to visualize the images again to confirm that they've been resized. Now you're ready to wrap the dataset in a [DataLoader](https://pytorch.org/docs/stable/data#torch.utils.data.DataLoader) for training!
+
+```py
+>>> import torch
+
+>>> train_dataloader = torch.utils.data.DataLoader(dataset, batch_size=config.train_batch_size, shuffle=True)
+```
+
+## Create a UNet2DModel
+
+Pretrained models in 🧨 Diffusers are easily created from their model class with the parameters you want. For example, to create a [`UNet2DModel`]:
+
+```py
+>>> from diffusers import UNet2DModel
+
+>>> model = UNet2DModel(
+...     sample_size=config.image_size,  # the target image resolution
+...     in_channels=3,  # the number of input channels, 3 for RGB images
+...     out_channels=3,  # the number of output channels
+...     layers_per_block=2,  # how many ResNet layers to use per UNet block
+...     block_out_channels=(128, 128, 256, 256, 512, 512),  # the number of output channels for each UNet block
+...     down_block_types=(
+...         "DownBlock2D",  # a regular ResNet downsampling block
+...         "DownBlock2D",
+...         "DownBlock2D",
+...         "DownBlock2D",
+...         "AttnDownBlock2D",  # a ResNet downsampling block with spatial self-attention
+...         "DownBlock2D",
+...     ),
+...     up_block_types=(
+...         "UpBlock2D",  # a regular ResNet upsampling block
+...         "AttnUpBlock2D",  # a ResNet upsampling block with spatial self-attention
+...         "UpBlock2D",
+...         "UpBlock2D",
+...         "UpBlock2D",
+...         "UpBlock2D",
+...     ),
+... )
+```
+
+It is often a good idea to quickly check the sample image shape matches the model output shape:
+
+```py
+>>> sample_image = dataset[0]["images"].unsqueeze(0)
+>>> print("Input shape:", sample_image.shape)
+Input shape: torch.Size([1, 3, 128, 128])
+
+>>> print("Output shape:", model(sample_image, timestep=0).sample.shape)
+Output shape: torch.Size([1, 3, 128, 128])
+```
+
+Great! Next, you'll need a scheduler to add some noise to the image.
+
+## Create a scheduler
+
+The scheduler behaves differently depending on whether you're using the model for training or inference. During inference, the scheduler generates image from the noise. During training, the scheduler takes a model output - or a sample - from a specific point in the diffusion process and applies noise to the image according to a *noise schedule* and an *update rule*.
+
+Let's take a look at the [`DDPMScheduler`] and use the `add_noise` method to add some random noise to the `sample_image` from before:
+
+```py
+>>> import torch
+>>> from PIL import Image
+>>> from diffusers import DDPMScheduler
+
+>>> noise_scheduler = DDPMScheduler(num_train_timesteps=1000)
+>>> noise = torch.randn(sample_image.shape)
+>>> timesteps = torch.LongTensor([50])
+>>> noisy_image = noise_scheduler.add_noise(sample_image, noise, timesteps)
+
+>>> Image.fromarray(((noisy_image.permute(0, 2, 3, 1) + 1.0) * 127.5).type(torch.uint8).numpy()[0])
+```
+
+<div class="flex justify-center">
+    <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/noisy_butterfly.png"/>
+</div>
+
+The training objective of the model is to predict the noise added to the image. The loss at this step can be calculated by:
+
+```py
+>>> import torch.nn.functional as F
+
+>>> noise_pred = model(noisy_image, timesteps).sample
+>>> loss = F.mse_loss(noise_pred, noise)
+```
+
+## Train the model
+
+By now, you have most of the pieces to start training the model and all that's left is putting everything together.
+
+First, you'll need an optimizer and a learning rate scheduler:
+
+```py
+>>> from diffusers.optimization import get_cosine_schedule_with_warmup
+
+>>> optimizer = torch.optim.AdamW(model.parameters(), lr=config.learning_rate)
+>>> lr_scheduler = get_cosine_schedule_with_warmup(
+...     optimizer=optimizer,
+...     num_warmup_steps=config.lr_warmup_steps,
+...     num_training_steps=(len(train_dataloader) * config.num_epochs),
+... )
+```
+
+Then, you'll need a way to evaluate the model. For evaluation, you can use the [`DDPMPipeline`] to generate a batch of sample images and save it as a grid:
+
+```py
+>>> from diffusers import DDPMPipeline
+>>> import math
+
+
+>>> def make_grid(images, rows, cols):
+...     w, h = images[0].size
+...     grid = Image.new("RGB", size=(cols * w, rows * h))
+...     for i, image in enumerate(images):
+...         grid.paste(image, box=(i % cols * w, i // cols * h))
+...     return grid
+
+
+>>> def evaluate(config, epoch, pipeline):
+...     # Sample some images from random noise (this is the backward diffusion process).
+...     # The default pipeline output type is `List[PIL.Image]`
+...     images = pipeline(
+...         batch_size=config.eval_batch_size,
+...         generator=torch.manual_seed(config.seed),
+...     ).images
+
+...     # Make a grid out of the images
+...     image_grid = make_grid(images, rows=4, cols=4)
+
+...     # Save the images
+...     test_dir = os.path.join(config.output_dir, "samples")
+...     os.makedirs(test_dir, exist_ok=True)
+...     image_grid.save(f"{test_dir}/{epoch:04d}.png")
+```
+
+Now you can wrap all these components together in a training loop with 🤗 Accelerate for easy TensorBoard logging, gradient accumulation, and mixed precision training. To upload the model to the Hub, write a function to get your repository name and information and then push it to the Hub.
+
+<Tip>
+
+💡 The training loop below may look intimidating and long, but it'll be worth it later when you launch your training in just one line of code! If you can't wait and want to start generating images, feel free to copy and run the code below. You can always come back and examine the training loop more closely later, like when you're waiting for your model to finish training. 🤗
+
+</Tip>
+
+```py
+>>> from accelerate import Accelerator
+>>> from huggingface_hub import HfFolder, Repository, whoami
+>>> from tqdm.auto import tqdm
+>>> from pathlib import Path
+>>> import os
+
+
+>>> def get_full_repo_name(model_id: str, organization: str = None, token: str = None):
+...     if token is None:
+...         token = HfFolder.get_token()
+...     if organization is None:
+...         username = whoami(token)["name"]
+...         return f"{username}/{model_id}"
+...     else:
+...         return f"{organization}/{model_id}"
+
+
+>>> def train_loop(config, model, noise_scheduler, optimizer, train_dataloader, lr_scheduler):
+...     # Initialize accelerator and tensorboard logging
+...     accelerator = Accelerator(
+...         mixed_precision=config.mixed_precision,
+...         gradient_accumulation_steps=config.gradient_accumulation_steps,
+...         log_with="tensorboard",
+...         logging_dir=os.path.join(config.output_dir, "logs"),
+...     )
+...     if accelerator.is_main_process:
+...         if config.push_to_hub:
+...             repo_name = get_full_repo_name(Path(config.output_dir).name)
+...             repo = Repository(config.output_dir, clone_from=repo_name)
+...         elif config.output_dir is not None:
+...             os.makedirs(config.output_dir, exist_ok=True)
+...         accelerator.init_trackers("train_example")
+
+...     # Prepare everything
+...     # There is no specific order to remember, you just need to unpack the
+...     # objects in the same order you gave them to the prepare method.
+...     model, optimizer, train_dataloader, lr_scheduler = accelerator.prepare(
+...         model, optimizer, train_dataloader, lr_scheduler
+...     )
+
+...     global_step = 0
+
+...     # Now you train the model
+...     for epoch in range(config.num_epochs):
+...         progress_bar = tqdm(total=len(train_dataloader), disable=not accelerator.is_local_main_process)
+...         progress_bar.set_description(f"Epoch {epoch}")
+
+...         for step, batch in enumerate(train_dataloader):
+...             clean_images = batch["images"]
+...             # Sample noise to add to the images
+...             noise = torch.randn(clean_images.shape).to(clean_images.device)
+...             bs = clean_images.shape[0]
+
+...             # Sample a random timestep for each image
+...             timesteps = torch.randint(
+...                 0, noise_scheduler.num_train_timesteps, (bs,), device=clean_images.device
+...             ).long()
+
+...             # Add noise to the clean images according to the noise magnitude at each timestep
+...             # (this is the forward diffusion process)
+...             noisy_images = noise_scheduler.add_noise(clean_images, noise, timesteps)
+
+...             with accelerator.accumulate(model):
+...                 # Predict the noise residual
+...                 noise_pred = model(noisy_images, timesteps, return_dict=False)[0]
+...                 loss = F.mse_loss(noise_pred, noise)
+...                 accelerator.backward(loss)
+
+...                 accelerator.clip_grad_norm_(model.parameters(), 1.0)
+...                 optimizer.step()
+...                 lr_scheduler.step()
+...                 optimizer.zero_grad()
+
+...             progress_bar.update(1)
+...             logs = {"loss": loss.detach().item(), "lr": lr_scheduler.get_last_lr()[0], "step": global_step}
+...             progress_bar.set_postfix(**logs)
+...             accelerator.log(logs, step=global_step)
+...             global_step += 1
+
+...         # After each epoch you optionally sample some demo images with evaluate() and save the model
+...         if accelerator.is_main_process:
+...             pipeline = DDPMPipeline(unet=accelerator.unwrap_model(model), scheduler=noise_scheduler)
+
+...             if (epoch + 1) % config.save_image_epochs == 0 or epoch == config.num_epochs - 1:
+...                 evaluate(config, epoch, pipeline)
+
+...             if (epoch + 1) % config.save_model_epochs == 0 or epoch == config.num_epochs - 1:
+...                 if config.push_to_hub:
+...                     repo.push_to_hub(commit_message=f"Epoch {epoch}", blocking=True)
+...                 else:
+...                     pipeline.save_pretrained(config.output_dir)
+```
+
+Phew, that was quite a bit of code! But you're finally ready to launch the training with 🤗 Accelerate's [`~accelerate.notebook_launcher`] function. Pass the function the training loop, all the training arguments, and the number of processes (you can change this value to the number of GPUs available to you) to use for training:
+
+```py
+>>> from accelerate import notebook_launcher
+
+>>> args = (config, model, noise_scheduler, optimizer, train_dataloader, lr_scheduler)
+
+>>> notebook_launcher(train_loop, args, num_processes=1)
+```
+
+Once training is complete, take a look at the final 🦋 images 🦋 generated by your diffusion model!
+
+```py
+>>> import glob
+
+>>> sample_images = sorted(glob.glob(f"{config.output_dir}/samples/*.png"))
+>>> Image.open(sample_images[-1])
+```
+
+<div class="flex justify-center">
+    <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/butterflies_final.png"/>
+</div>
+
+## Next steps
+
+Unconditional image generation is one example of a task that can be trained. You can explore other tasks and training techniques by visiting the [🧨 Diffusers Training Examples](./training/overview) page. Here are some examples of what you can learn:
+
+* [Textual Inversion](./training/text_inversion), an algorithm that teaches a model a specific visual concept and integrates it into the generated image.
+* [DreamBooth](./training/dreambooth), a technique for generating personalized images of a subject given several input images of the subject.
+* [Guide](./training/text2image) to finetuning a Stable Diffusion model on your own dataset.
+* [Guide](./training/lora) to using LoRA, a memory-efficient technique for finetuning really large models faster.

docs/source/en/using-diffusers/audio.mdx

@@ -1,4 +1,4 @@
-<!--Copyright 2022 The HuggingFace Team. All rights reserved.
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at

docs/source/en/using-diffusers/conditional_image_generation.mdx

@@ -1,4 +1,4 @@
-<!--Copyright 2022 The HuggingFace Team. All rights reserved.
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at

docs/source/en/using-diffusers/configuration.mdx

@@ -1,4 +1,4 @@
-<!--Copyright 2022 The HuggingFace Team. All rights reserved.
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at

docs/source/en/using-diffusers/contribute_pipeline.mdx

@@ -1,4 +1,4 @@
-<!--Copyright 2022 The HuggingFace Team. All rights reserved.
+<!--Copyright 2023 The HuggingFace Team. All rights reserved.
 
 Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
 the License. You may obtain a copy of the License at