Merge branch 'main' into push-test-fixes

update to a place holder

.github/workflows/nightly_tests.yml

@@ -79,7 +79,7 @@ jobs:
           python utils/print_env.py
       - name: Pipeline CUDA Test
         env:
-          HF_TOKEN: ${{ secrets.HF_TOKEN }}
+          HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
           # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
           CUBLAS_WORKSPACE_CONFIG: :16:8
         run: |
@@ -139,7 +139,7 @@ jobs:
     - name: Run nightly PyTorch CUDA tests for non-pipeline modules
       if: ${{ matrix.module != 'examples'}}
       env:
-        HF_TOKEN: ${{ secrets.HF_TOKEN }}
+        HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
         # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
         CUBLAS_WORKSPACE_CONFIG: :16:8
       run: |
@@ -152,7 +152,7 @@ jobs:
     - name: Run nightly example tests with Torch
       if: ${{ matrix.module == 'examples' }}
       env:
-        HF_TOKEN: ${{ secrets.HF_TOKEN }}
+        HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
         # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
         CUBLAS_WORKSPACE_CONFIG: :16:8
       run: |
@@ -209,7 +209,7 @@ jobs:
 
     - name: Run nightly Flax TPU tests
       env:
-        HF_TOKEN: ${{ secrets.HF_TOKEN }}
+        HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
       run: |
         python -m pytest -n 0 \
           -s -v -k "Flax" \
@@ -264,7 +264,7 @@ jobs:
 
     - name: Run Nightly ONNXRuntime CUDA tests
       env:
-        HF_TOKEN: ${{ secrets.HF_TOKEN }}
+        HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
       run: |
         python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
           -s -v -k "Onnx" \

docs/source/en/api/pipelines/cogvideox.md

@@ -77,10 +77,21 @@ CogVideoX-2b requires about 19 GB of GPU memory to decode 49 frames (6 seconds o
 - `pipe.enable_model_cpu_offload()`:
   - Without enabling cpu offloading, memory usage is `33 GB`
   - With enabling cpu offloading, memory usage is `19 GB`
+- `pipe.enable_sequential_cpu_offload()`:
+  - Similar to `enable_model_cpu_offload` but can significantly reduce memory usage at the cost of slow inference
+  - When enabled, memory usage is under `4 GB`
 - `pipe.vae.enable_tiling()`:
   - With enabling cpu offloading and tiling, memory usage is `11 GB`
 - `pipe.vae.enable_slicing()`
 
+### Quantized inference
+
+[torchao](https://github.com/pytorch/ao) and [optimum-quanto](https://github.com/huggingface/optimum-quanto/) can be used to quantize the text encoder, transformer and VAE modules to lower the memory requirements. This makes it possible to run the model on a free-tier T4 Colab or lower VRAM GPUs!
+
+It is also worth noting that torchao quantization is fully compatible with [torch.compile](/optimization/torch2.0#torchcompile), which allows for much faster inference speed. Additionally, models can be serialized and stored in a quantized datatype to save disk space with torchao. Find examples and benchmarks in the gists below.
+- [torchao](https://gist.github.com/a-r-r-o-w/4d9732d17412888c885480c6521a9897)
+- [quanto](https://gist.github.com/a-r-r-o-w/31be62828b00a9292821b85c1017effa)
+
 ## CogVideoXPipeline
 
 [[autodoc]] CogVideoXPipeline

src/diffusers/loaders/single_file_utils.py

@@ -91,11 +91,11 @@ DIFFUSERS_DEFAULT_PIPELINE_PATHS = {
     "xl_inpaint": {"pretrained_model_name_or_path": "diffusers/stable-diffusion-xl-1.0-inpainting-0.1"},
     "playground-v2-5": {"pretrained_model_name_or_path": "playgroundai/playground-v2.5-1024px-aesthetic"},
     "upscale": {"pretrained_model_name_or_path": "stabilityai/stable-diffusion-x4-upscaler"},
-    "inpainting": {"pretrained_model_name_or_path": "runwayml/stable-diffusion-inpainting"},
+    "inpainting": {"pretrained_model_name_or_path": "Lykon/dreamshaper-8-inpainting"},
     "inpainting_v2": {"pretrained_model_name_or_path": "stabilityai/stable-diffusion-2-inpainting"},
     "controlnet": {"pretrained_model_name_or_path": "lllyasviel/control_v11p_sd15_canny"},
     "v2": {"pretrained_model_name_or_path": "stabilityai/stable-diffusion-2-1"},
-    "v1": {"pretrained_model_name_or_path": "runwayml/stable-diffusion-v1-5"},
+    "v1": {"pretrained_model_name_or_path": "Lykon/dreamshaper-8"},
     "stable_cascade_stage_b": {"pretrained_model_name_or_path": "stabilityai/stable-cascade", "subfolder": "decoder"},
     "stable_cascade_stage_b_lite": {
         "pretrained_model_name_or_path": "stabilityai/stable-cascade",

tests/models/test_modeling_common.py

@@ -417,6 +417,9 @@ class ModelTesterMixin:
 
     @require_torch_gpu
     def test_set_attn_processor_for_determinism(self):
+        if self.uses_custom_attn_processor:
+            return
+
         torch.use_deterministic_algorithms(False)
         if self.forward_requires_fresh_args:
             model = self.model_class(**self.init_dict)

tests/models/transformers/test_models_transformer_flux.py

@@ -32,6 +32,9 @@ class FluxTransformerTests(ModelTesterMixin, unittest.TestCase):
     # We override the items here because the transformer under consideration is small.
     model_split_percents = [0.7, 0.6, 0.6]
 
+    # Skip setting testing with default: AttnProcessor
+    uses_custom_attn_processor = True
+
     @property
     def dummy_input(self):
         batch_size = 1

tests/pipelines/flux/test_pipeline_flux.py

@@ -25,6 +25,9 @@ class FluxPipelineFastTests(unittest.TestCase, PipelineTesterMixin):
     params = frozenset(["prompt", "height", "width", "guidance_scale", "prompt_embeds", "pooled_prompt_embeds"])
     batch_params = frozenset(["prompt"])
 
+    # there is no xformers processor for Flux
+    test_xformers_attention = False
+
     def get_dummy_components(self):
         torch.manual_seed(0)
         transformer = FluxTransformer2DModel(

tests/pipelines/pag/test_pag_sd3.py

@@ -37,6 +37,7 @@ class StableDiffusion3PAGPipelineFastTests(unittest.TestCase, PipelineTesterMixi
         ]
     )
     batch_params = frozenset(["prompt", "negative_prompt"])
+    test_xformers_attention = False
 
     def get_dummy_components(self):
         torch.manual_seed(0)

tests/pipelines/stable_audio/test_stable_audio.py

@@ -68,6 +68,8 @@ class StableAudioPipelineFastTests(PipelineTesterMixin, unittest.TestCase):
             "callback_steps",
         ]
     )
+    # There is not xformers version of the StableAudioPipeline custom attention processor
+    test_xformers_attention = False
 
     def get_dummy_components(self):
         torch.manual_seed(0)