LLM/diffusers
1
0
Fork 0
mirror of https://github.com/huggingface/diffusers.git synced 2026-04-08 00:31:45 +08:00
Code Issues Packages Projects Releases Wiki Activity
6,383 Commits 803 Branches 96 Tags
modular-pipeline-docs
Commit Graph

6383 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
yiyi@huggingface.co
1c3b90986a [docs] add modular pipeline conventions and gotchas 
Create .ai/modular.md as a shared reference for modular pipeline
conventions, patterns, and common mistakes — parallel to the existing
models.md for model conventions.

Consolidates content from the former modular-conversion.md skill file
and adds gotchas identified from reviewing recent modular pipeline PRs
(LTX #13378, SD3 #13324).

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-04 08:26:54 +00:00
Sayak Paul
fbe8a75ad5 Update README.md of the profiling guide (#13400) 
Update README.md
 2026-04-03 18:54:27 +02:00
Sayak Paul
b114620d85 Add examples on how to profile a pipeline (#13356) 
* add a profiling worflow.

* fix

* fix

* more clarification

* add points.

* up

* cache hooks

* improve readme.

* propagate deletion.

* up

* up

* wan fixes.

* more

* up

* add more traces.

* up

* better title

* cuda graphs.

* up

* Apply suggestions from code review

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* add torch.compile link.

* approach -> How the tooling works

* table

* unavoidable gaps.

* make important

* note on regional compilation

* Apply suggestions from code review

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* make regional compilation note clearer.

* Apply suggestions from code review

Co-authored-by: dg845 <58458699+dg845@users.noreply.github.com>

* clarify scheduler related changes.

* Apply suggestions from code review

Co-authored-by: dg845 <58458699+dg845@users.noreply.github.com>

* Update examples/profiling/README.md

Co-authored-by: dg845 <58458699+dg845@users.noreply.github.com>

* up

* formatting

* benchmarking runtime

* up

* up

* up

* up

* Update examples/profiling/README.md

Co-authored-by: dg845 <58458699+dg845@users.noreply.github.com>

---------

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
Co-authored-by: dg845 <58458699+dg845@users.noreply.github.com>
 2026-04-03 16:13:01 +02:00
sippycoder
447e571ada NucleusMoE-Image (#13317) 
* adding NucleusMoE-Image model

* update system prompt

* Add text kv caching

* Class/function name changes

* add missing imports

* add RoPE credits

* Update src/diffusers/models/transformers/transformer_nucleusmoe_image.py

Co-authored-by: dg845 <58458699+dg845@users.noreply.github.com>

* Update src/diffusers/models/transformers/transformer_nucleusmoe_image.py

Co-authored-by: dg845 <58458699+dg845@users.noreply.github.com>

* Update src/diffusers/models/transformers/transformer_nucleusmoe_image.py

Co-authored-by: dg845 <58458699+dg845@users.noreply.github.com>

* Update src/diffusers/models/transformers/transformer_nucleusmoe_image.py

Co-authored-by: dg845 <58458699+dg845@users.noreply.github.com>

* update defaults

* Update src/diffusers/pipelines/nucleusmoe_image/pipeline_nucleusmoe_image.py

Co-authored-by: dg845 <58458699+dg845@users.noreply.github.com>

* review updates

* fix the tests

* clean up

* update apply_text_kv_cache

* SwiGLUExperts addition

* fuse SwiGLUExperts up and gate proj

* Update src/diffusers/hooks/text_kv_cache.py

Co-authored-by: dg845 <58458699+dg845@users.noreply.github.com>

* Update src/diffusers/hooks/text_kv_cache.py

Co-authored-by: dg845 <58458699+dg845@users.noreply.github.com>

* Update src/diffusers/hooks/text_kv_cache.py

Co-authored-by: dg845 <58458699+dg845@users.noreply.github.com>

* Update src/diffusers/hooks/text_kv_cache.py

Co-authored-by: dg845 <58458699+dg845@users.noreply.github.com>

* Update src/diffusers/models/transformers/transformer_nucleusmoe_image.py

Co-authored-by: dg845 <58458699+dg845@users.noreply.github.com>

* Update src/diffusers/models/transformers/transformer_nucleusmoe_image.py

Co-authored-by: dg845 <58458699+dg845@users.noreply.github.com>

* _SharedCacheKey -> TextKVCacheState

* Apply style fixes

* Run python utils/check_copies.py --fix_and_overwrite
python utils/check_dummies.py --fix_and_overwrite

* Apply style fixes

* run `make fix-copies`

* fix import

* refactor text KV cache to be managed by StateManager

---------

Co-authored-by: Murali Nandan Nagarapu <nmn@withnucleus.ai>
Co-authored-by: dg845 <58458699+dg845@users.noreply.github.com>
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
 2026-04-03 02:01:13 -07:00
Sayak Paul
5adc544b79 [tests] refactor wan autoencoder tests (#13371) 
* refactor wan autoencoder tests

* up

* address dhruv's feedback.
 2026-04-03 07:36:40 +02:00
jiqing-feng
a05c8e9452 Fix Dynamo lru_cache warnings during torch.compile (#13384) 
* fix compile issue

Signed-off-by: jiqing-feng <jiqing.feng@intel.com>

* compile friendly

Signed-off-by: jiqing-feng <jiqing.feng@intel.com>

* add comments

Signed-off-by: jiqing-feng <jiqing.feng@intel.com>

---------

Signed-off-by: jiqing-feng <jiqing.feng@intel.com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2026-04-03 07:12:54 +02:00
Zamuldinov Nikita
8070f6ec54 fix(ddim): validate eta is in [0, 1] in DDIMPipeline (#13367) 
* fix(ddim): validate eta is in [0, 1] in DDIMPipeline.__call__

The DDIM paper defines η (eta) as a value that must lie in [0, 1]:
η=0 corresponds to deterministic DDIM, η=1 corresponds to DDPM.
The docstring already documented this constraint, but no runtime
validation was in place, so users could silently pass out-of-range
values (e.g. negative or >1) without any error.

Add an explicit ValueError check before the denoising loop so that
invalid eta values are caught early with a clear message.

Fixes #13362

Signed-off-by: NIK-TIGER-BILL <nik.tiger.bill@github.com>

* fix(ddim): downgrade eta out-of-range from error to warning

Per maintainer feedback from @yiyixuxu — the documentation is
sufficient; a hard ValueError is too strict. Replace with a
UserWarning so callers are informed without breaking existing code
that passes eta outside [0, 1].

Signed-off-by: NIK-TIGER-BILL <nik.tiger.bill@github.com>

* fix(ddim): use logger.warning instead of warnings.warn for eta validation

Address review request from @yiyixuxu: switch from warnings.warn() to
logger.warning() to be consistent with all other diffusers pipelines.

The eta validation check itself (0.0 <= eta <= 1.0) is unchanged.

Signed-off-by: NIK-TIGER-BILL <nik.tiger.bill@github.com>

---------

Signed-off-by: NIK-TIGER-BILL <nik.tiger.bill@github.com>
Co-authored-by: NIK-TIGER-BILL <nik.tiger.bill@github.com>
Co-authored-by: YiYi Xu <yixu310@gmail.com>
 2026-04-02 16:07:28 -10:00
Samuel Meddin
3e53a383e1 Fix typos and grammar errors in documentation (#13391) 
- Fix 'allows to generate' -> 'allows you to generate' in controlling_generation.md
- Fix 'it's refiner' -> 'its refiner' (possessive) in sdxl.md
- Fix 'it's state' -> 'its state' (possessive) in reusing_seeds.md
- Fix missing word 'you'll a function' -> 'you'll create a function' in sdxl.md
 2026-04-02 13:42:32 -07:00
YiYi Xu
cf6af6b4f8 [docs] add auto docstring and parameter templates documentation for m… (#13382) 
* [docs] add auto docstring and parameter templates documentation for modular diffusers

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* Update docs/source/en/modular_diffusers/auto_docstring.md

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* Update docs/source/en/modular_diffusers/auto_docstring.md

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* Update docs/source/en/modular_diffusers/auto_docstring.md

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* Update docs/source/en/modular_diffusers/auto_docstring.md

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* Update docs/source/en/modular_diffusers/auto_docstring.md

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* Update docs/source/en/modular_diffusers/auto_docstring.md

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* Update docs/source/en/modular_diffusers/auto_docstring.md

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* Update docs/source/en/modular_diffusers/auto_docstring.md

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* Update docs/source/en/_toctree.yml

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* up

---------

Co-authored-by: yiyi@huggingface.co <yiyi@ip-26-0-161-123.ec2.internal>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
 2026-04-02 10:34:45 -10:00
Pauline Bailly-Masson
3211cd9df0 🔒 Pin GitHub Actions to commit SHAs (#13385) 
* 🔒 pin benchmark.yml actions to commit SHAs

* 🔒 pin nightly_tests.yml actions to commit SHAs

* 🔒 pin build_pr_documentation.yml actions to commit SHAs

* 🔒 pin typos.yml actions to commit SHAs

* 🔒 pin build_docker_images.yml actions to commit SHAs

* 🔒 pin build_documentation.yml actions to commit SHAs

* 🔒 pin upload_pr_documentation.yml actions to commit SHAs

* 🔒 pin pr_style_bot.yml actions to commit SHAs

* 🔒 pin codeql.yml actions to commit SHAs

* 🔒 pin ssh-pr-runner.yml actions to commit SHAs

* 🔒 pin trufflehog.yml actions to commit SHAs
 2026-04-02 21:04:45 +05:30
Steven Liu
e365d749a1 [docs] deprecate pipelines (#13157) 
* deprecate

* fix

* fix

* fix

* fix

* remove deprecated .md files

* update links

* fix
 2026-04-01 10:16:23 -07:00
Andrew Ross
b9353819a4 corrects single file path validation logic (#13363) 
* corrects single file path validation logic

* Update tests/modular_pipelines/test_modular_pipelines_common.py

Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>

---------

Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>
 2026-04-01 20:38:42 +05:30
hf-security-analysis[bot]
514bba0696 chore: update claude_review.yml (#13374) 
fix(security): remediate workflow vulnerability in .github/workflows/claude_review.yml

Co-authored-by: hf-security-analysis[bot] <265538906+hf-security-analysis[bot]@users.noreply.github.com>
 2026-04-01 10:18:29 +05:30
YangKai0616
0325ca4c59 Fix MotionConv2d to cast blur_kernel to input dtype instead of reverse (#13364) 
Co-authored-by: dg845 <58458699+dg845@users.noreply.github.com>
 2026-03-31 02:53:12 -07:00
Sayak Paul
a8075425d8 [ci] support claude reviewing on forks. (#13365) 
* support claude reviewing on forks.

* sanitization

* tighten system prompt.

* use latest checkout

* remove id-token
 2026-03-31 14:56:08 +05:30
YangKai0616
b88e60bd1b Fix: ensure consistent dtype and eval mode in pipeline save/load tests (#13339) 
* Fix: ensure consistent dtype and eval mode in pipeline save/load tests

* Modify according to the comments

* Update according to the comments

* Update comment

* Code quality

* cast buffers to torch.float16

* conflict

* Fix

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2026-03-31 14:21:28 +05:30
Pranav Thombre
7e463ea4cc [docs] Add NeMo Automodel training guide (#13306) 
* [docs] Add NeMo Automodel training guide

Signed-off-by: Pranav Prashant Thombre <pthombre@nvidia.com>

* Update docs/source/en/training/nemo_automodel.md

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* Update docs/source/en/training/nemo_automodel.md

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* adding contacts into the readme

* Apply suggestion from @stevhliu

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* Apply suggestion from @stevhliu

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* Apply suggestion from @stevhliu

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* Apply suggestion from @stevhliu

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* Apply suggestion from @stevhliu

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* Apply suggestion from @stevhliu

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* Apply suggestion from @stevhliu

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* Apply suggestion from @stevhliu

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* Apply suggestion from @stevhliu

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* Apply suggestion from @stevhliu

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* Apply suggestion from @stevhliu

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* Address CR comments

Signed-off-by: Pranav Prashant Thombre <pthombre@nvidia.com>

* Update docs/source/en/training/nemo_automodel.md

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* Update docs/source/en/training/nemo_automodel.md

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

---------

Signed-off-by: Pranav Prashant Thombre <pthombre@nvidia.com>
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
Co-authored-by: linnan wang <wangnan318@gmail.com>
 2026-03-30 10:21:58 -07:00
tcaimm
7f2b34bced Add train flux2 series lora config (#13011) 
* feat(lora): support FLUX.2 single blocks + update README

* add img2img config & add explanatory comments

* simple modify

---------

Co-authored-by: Linoy Tsaban <57615435+linoytsaban@users.noreply.github.com>
 2026-03-30 14:22:04 +03:00
Cheung Ka Wai
e1e7d58a4a Fix Ulysses SP backward with SDPA (#13328) 
* add UT for backward

* fix SDPA attention backward
 2026-03-30 15:15:27 +05:30
Steven Liu
a93f7f137a [docs] refactor model skill (#13334) 
* refactor

* feedback

* feedback

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2026-03-29 23:13:52 -07:00
Sayak Paul
10ec3040a2 [ci] move to assert instead of self.Assert* (#13366) 
move to assert instead of self.Assert*
 2026-03-30 11:09:14 +05:30
Howard Zhang
f2be8bd6b3 change minimum version guard for torchao to 0.15.0 (#13355) 2026-03-28 09:11:51 +05:30
Sayak Paul
7da22b9db5 [ci] include checkout step in claude review workflow (#13352) 
up
 2026-03-27 17:28:31 +05:30
Howard Zhang
1fe2125802 remove str option for quantization config in torchao (#13291) 
* remove str option for quantization config in torchao

* Apply style fixes

* minor fixes

* Added AOBaseConfig docs to torchao.md

* minor fixes for removing str option torchao

* minor change to add back int and uint check

* minor fixes

* minor fixes to tests

* Update tests/quantization/torchao/test_torchao.py

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* Update docs/source/en/quantization/torchao.md

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* Update tests/quantization/torchao/test_torchao.py

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* version=2 update to test_torchao.py

---------

Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2026-03-27 08:52:37 +05:30
dg845
7298f5be93 Update LTX-2 Docs to Cover LTX-2.3 Models (#13337) 
* Update LTX-2 docs to cover multimodal guidance and prompt enhancement

* Apply suggestions from code review

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* Apply reviewer feedback

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
 2026-03-26 17:51:29 -07:00
Sayak Paul
b757035df6 fix claude workflow to include id-token with write. (#13338) 2026-03-26 15:39:10 +05:30
kaixuanliu
41e1003316 avoid hardcode device in flux-control example (#13336) 
Signed-off-by: Liu, Kaixuan <kaixuan.liu@intel.com>
 2026-03-26 12:40:53 +05:30
Sayak Paul
85ffcf1db2 [tests] Tests for conditional pipeline blocks (#13247) 
* implement test suite for conditional blocks.

* remove

* another fix.

* Revert "another fix."

This reverts commit ab07b603ab.
 2026-03-26 08:48:16 +05:30
Steven Liu
cbf4d9a3c3 [docs] kernels (#13139) 
* kernels

* feedback
 2026-03-25 09:31:54 -07:00
Sayak Paul
426daabad9 [ci] claude in ci. (#13297) 
* claude in ci.

* review feedback.
 2026-03-25 21:30:06 +05:30
Kashif Rasul
762ae059fa [LLADA2] documentation fixes (#13333) 
documentation fixes
 2026-03-25 17:49:31 +05:30
Kashif Rasul
5d207e756e [Discrete Diffusion] Add LLaDA2 pipeline (#13226) 
* feat: add LLaDA2 and BlockRefinement pipelines for discrete text diffusion

Add support for LLaDA2/LLaDA2.1 discrete diffusion text generation:
- BlockRefinementPipeline: block-wise iterative refinement with confidence-based
  token commitment, supporting editing threshold for LLaDA2.1 models
- LLaDA2Pipeline: convenience wrapper with LLaDA2-specific defaults
- DiscreteDiffusionPipelineMixin: shared SAR sampling utilities (top-k, top-p,
  temperature) and prompt/prefix helpers
- compute_confidence_aware_loss: CAP-style training loss
- Examples: sampling scripts for LLaDA2 and block refinement, training scripts
  with Qwen causal LM
- Docs and tests included

* feat: add BlockRefinementScheduler for commit-by-confidence scheduling

Extract the confidence-based token commit logic from BlockRefinementPipeline
into a dedicated BlockRefinementScheduler, following diffusers conventions.

The scheduler owns:
- Transfer schedule computation (get_num_transfer_tokens)
- Timestep management (set_timesteps)
- Step logic: confidence-based mask-filling and optional token editing

The pipeline now delegates scheduling to self.scheduler.step() and accepts
a scheduler parameter in __init__.

* test: add unit tests for BlockRefinementScheduler

12 tests covering set_timesteps, get_num_transfer_tokens, step logic
(confidence-based commits, threshold behavior, editing, prompt masking,
batched inputs, tuple output).

* docs: add toctree entries and standalone scheduler doc page

- Add BlockRefinement and LLaDA2 to docs sidebar navigation
- Add BlockRefinementScheduler to schedulers sidebar navigation
- Move scheduler autodoc to its own page under api/schedulers/

* feat: add --revision flag and fix dtype deprecation in sample_llada2.py

- Add --revision argument for loading model revisions from the Hub
- Replace deprecated torch_dtype with dtype for transformers 5.x compat

* fix: use 1/0 attention mask instead of 0/-inf for LLaDA2 compat

LLaDA2 models expect a boolean-style (1/0) attention mask, not an
additive (0/-inf) mask. The model internally converts to additive,
so passing 0/-inf caused double-masking and gibberish output.

* refactor: consolidate training scripts into single train_block_refinement.py

- Remove toy train_block_refinement_cap.py (self-contained demo with tiny model)
- Rename train_block_refinement_qwen_cap.py to train_block_refinement.py
  (already works with any causal LM via AutoModelForCausalLM)
- Fix torch_dtype deprecation and update README with correct script names

* fix formatting

* docs: improve LLaDA2 and BlockRefinement documentation

- Add usage examples with real model IDs and working code
- Add recommended parameters table for LLaDA2.1 quality/speed modes
- Note that editing is LLaDA2.1-only (not for LLaDA2.0 models)
- Remove misleading config defaults section from BlockRefinement docs

* feat: set LLaDA2Pipeline defaults to recommended model parameters

- threshold: 0.95 -> 0.7 (quality mode)
- max_post_steps: 0 -> 16 (recommended for LLaDA2.1, harmless for 2.0)
- eos_early_stop: False -> True (stop at EOS token)

block_length=32, steps=32, temperature=0.0 were already correct.
editing_threshold remains None (users enable for LLaDA2.1 models).

* feat: default editing_threshold=0.5 for LLaDA2.1 quality mode

LLaDA2.1 is the current generation. Users with LLaDA2.0 models can
disable editing by passing editing_threshold=None.

* fix: align sampling utilities with official LLaDA2 implementation

- top_p filtering: add shift-right to preserve at least one token above
  threshold (matches official code line 1210)
- temperature ordering: apply scaling before top-k/top-p filtering so
  filtering operates on scaled logits (matches official code lines 1232-1235)
- greedy branch: return argmax directly when temperature=0 without
  filtering (matches official code lines 1226-1230)

* refactor: remove duplicate prompt encoding, reuse mixin's _prepare_input_ids

LLaDA2Pipeline._prepare_prompt_ids was a near-copy of
DiscreteDiffusionPipelineMixin._prepare_input_ids. Remove the duplicate
and call the mixin method directly. Also simplify _extract_input_ids
since we always pass return_dict=True.

* formatting

* fix: replace deprecated torch_dtype with dtype in examples and docstrings

- Update EXAMPLE_DOC_STRING to use dtype= and LLaDA2.1-mini model ID
- Fix sample_block_refinement.py to use dtype=

* remove BlockRefinementPipeline

* cleanup

* fix readme

* Update src/diffusers/pipelines/llada2/pipeline_llada2.py

Co-authored-by: YiYi Xu <yixu310@gmail.com>

* Update src/diffusers/pipelines/llada2/pipeline_llada2.py

Co-authored-by: YiYi Xu <yixu310@gmail.com>

* Update src/diffusers/pipelines/llada2/pipeline_llada2.py

Co-authored-by: YiYi Xu <yixu310@gmail.com>

* Update src/diffusers/pipelines/llada2/pipeline_llada2.py

Co-authored-by: YiYi Xu <yixu310@gmail.com>

* Update src/diffusers/pipelines/llada2/pipeline_llada2.py

Co-authored-by: YiYi Xu <yixu310@gmail.com>

* Update src/diffusers/pipelines/llada2/pipeline_llada2.py

Co-authored-by: YiYi Xu <yixu310@gmail.com>

* Update src/diffusers/pipelines/llada2/pipeline_llada2.py

Co-authored-by: YiYi Xu <yixu310@gmail.com>

* Update src/diffusers/pipelines/llada2/pipeline_llada2.py

Co-authored-by: YiYi Xu <yixu310@gmail.com>

* Update src/diffusers/pipelines/llada2/pipeline_llada2.py

Co-authored-by: YiYi Xu <yixu310@gmail.com>

* Update src/diffusers/pipelines/llada2/pipeline_llada2.py

Co-authored-by: YiYi Xu <yixu310@gmail.com>

* Update src/diffusers/pipelines/llada2/pipeline_llada2.py

Co-authored-by: YiYi Xu <yixu310@gmail.com>

* Update src/diffusers/pipelines/llada2/pipeline_llada2.py

Co-authored-by: YiYi Xu <yixu310@gmail.com>

* Update src/diffusers/pipelines/llada2/pipeline_llada2.py

Co-authored-by: YiYi Xu <yixu310@gmail.com>

* Update src/diffusers/pipelines/llada2/pipeline_llada2.py

Co-authored-by: YiYi Xu <yixu310@gmail.com>

* Update src/diffusers/pipelines/llada2/pipeline_llada2.py

Co-authored-by: YiYi Xu <yixu310@gmail.com>

* removed DiscreteDiffusionPipelineMixin

* add support for 2d masks for flash attn

* Update src/diffusers/training_utils.py

Co-authored-by: dg845 <58458699+dg845@users.noreply.github.com>

* Update src/diffusers/training_utils.py

Co-authored-by: dg845 <58458699+dg845@users.noreply.github.com>

* fix issues from review

* added tests

* formatting

* add check_eos_finished to scheduler

* Update src/diffusers/pipelines/llada2/pipeline_llada2.py

Co-authored-by: dg845 <58458699+dg845@users.noreply.github.com>

* Update src/diffusers/pipelines/llada2/pipeline_llada2.py

Co-authored-by: dg845 <58458699+dg845@users.noreply.github.com>

* Update src/diffusers/pipelines/llada2/pipeline_llada2.py

Co-authored-by: dg845 <58458699+dg845@users.noreply.github.com>

* Update src/diffusers/pipelines/llada2/pipeline_llada2.py

Co-authored-by: dg845 <58458699+dg845@users.noreply.github.com>

* Update src/diffusers/schedulers/scheduling_block_refinement.py

Co-authored-by: dg845 <58458699+dg845@users.noreply.github.com>

* Update src/diffusers/pipelines/llada2/pipeline_llada2.py

Co-authored-by: dg845 <58458699+dg845@users.noreply.github.com>

* Update src/diffusers/pipelines/llada2/pipeline_llada2.py

Co-authored-by: dg845 <58458699+dg845@users.noreply.github.com>

* Update src/diffusers/pipelines/llada2/pipeline_llada2.py

Co-authored-by: dg845 <58458699+dg845@users.noreply.github.com>

* Update src/diffusers/schedulers/scheduling_block_refinement.py

Co-authored-by: dg845 <58458699+dg845@users.noreply.github.com>

* fix renaming issues and types

* remove duplicate check

* Update docs/source/en/api/pipelines/llada2.md

Co-authored-by: dg845 <58458699+dg845@users.noreply.github.com>

* Update src/diffusers/pipelines/llada2/pipeline_llada2.py

Co-authored-by: dg845 <58458699+dg845@users.noreply.github.com>

* Update src/diffusers/pipelines/llada2/pipeline_llada2.py

Co-authored-by: dg845 <58458699+dg845@users.noreply.github.com>

---------

Co-authored-by: YiYi Xu <yixu310@gmail.com>
Co-authored-by: dg845 <58458699+dg845@users.noreply.github.com>
 2026-03-25 16:17:50 +05:30
Sayak Paul
e358ddcce6 fix to device and to dtype tests. (#13323) 2026-03-25 11:47:02 +05:30
Sayak Paul
153fcbc5a8 fix klein lora loading. (#13313) 2026-03-25 07:51:35 +05:30
Beinsezii
da6718f080 ZImageTransformer2D: Only build attention mask if seqlens are not equal (#12955) 2026-03-24 06:06:50 -10:00
Alexey Kirillov
832676d35e Use defaultdict for _SET_ADAPTER_SCALE_FN_MAPPING (#13320) 
refactor: use defaultdict for _SET_ADAPTER_SCALE_FN_MAPPING

Co-authored-by: Alexkkir <alexkkir@gmail.coom>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2026-03-24 17:49:50 +05:30
Dhruv Nair
7bbd96da5d [CI] Update fetching pipelines for latest HF Hub Version (#13322) 
update
 2026-03-24 16:42:32 +05:30
Dhruv Nair
62777fa819 Fix unguarded torchvision import in Cosmos (#13321) 
update
 2026-03-24 16:00:24 +05:30
Sayak Paul
f1fd515257 [tests] fix lora logging tests for models. (#13318) 
* fix lora logging tests for models.

* make style
 2026-03-24 15:48:03 +05:30
Cheung Ka Wai
afdda57f61 Fix the attention mask in ulysses SP for QwenImage (#13278) 
* fix mask in SP

* change the modification to qwen specific

* drop xfail since qwen-image mask is fixed

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2026-03-24 02:12:50 -07:00
YangKai0616
5fc2bd2c8f Stabilize low-precision custom autoencoder RMS normalization (#13316) 
* Stabilize low-precision custom autoencoder RMS normalization

* Add fp8/4

* Apply style fixes

---------

Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: dg845 <58458699+dg845@users.noreply.github.com>
 2026-03-24 02:00:05 -07:00
Sayak Paul
6350a7690a [chore] properly deprecate src.diffusers.utils.testing_utils. (#13314) 
properly deprecate src.diffusers.utils.testing_utils.
 2026-03-24 10:54:35 +05:30
Cheung Ka Wai
9d4c9dcf21 change QwenImageTransformer UT to batch inputs (#13312) 
* UT expands to batch inputs

* update according to suggestion

* update according to suggestion 2

* fix CI

* update according to suggestion 3

* clean line
 2026-03-24 08:56:40 +05:30
ddavidchick
ef309a1bb0 Add KVAE 1.0 (#13033) 
* add kvae2d

* add kvae3d video

* add docs for kvae2d and kvae3d video

* style fixes

* fix kvae3d docs

* fix normalzation

* fix kvae video for code style

* fix kvae video

* kvae minor fixes

* add gradient ckpting for kvaes

* get rid of inplace ops kvae video

* add tests for KVAEs

* kvae2d normalization style change

* kvaes fix style

* update dummy_pt_objects test for kvaes

---------

Co-authored-by: YiYi Xu <yixu310@gmail.com>
 2026-03-23 12:56:49 -10:00
Charles
b9761ce5a2 [export] Add export-safe LRU cache helper (#13290) 
* [core] Add export-safe LRU cache helper

* torch version check!

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2026-03-23 18:10:07 +05:30
Dhruv Nair
52558b45d8 [CI] Flux2 Model Test Refactor (#13071) 
* update

* update

* update

---------

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
 2026-03-23 16:56:08 +05:30
Sayak Paul
c02c17c6ee [tests] test load_components in modular (#13245) 
* test load_components.

* fix

* fix

* u[

* up
 2026-03-21 09:41:48 +05:30
Sayak Paul
a9855c4204 [tests] fix audioldm2 tests. (#13293) 
fix audioldm2 tests.
 2026-03-20 20:53:21 +05:30
Sayak Paul
0b35834351 [core] fa4 support. (#13280) 
* start fa4 support.

* up

* specify minimum version
 2026-03-20 17:28:09 +05:30
Sayak Paul
522b523e40 [ci] hoping to fix is_flaky with wanvace. (#13294) 
* hoping to fix is_flaky with wanvace.

* revert changes in src/diffusers/utils/testing_utils.py and propagate them to tests/testing_utils.py.

* up
 2026-03-20 16:02:16 +05:30