* fix(torchao): route root-level tensors around safetensors reconstruction
Models with parameters at the root of the module tree (e.g. Wan's
`scale_shift_table`) crashed torchao's `unflatten_tensor_state_dict`
when loading serialized checkpoints, since flattened tensor names are
assumed to carry a module prefix. Filter such tensors and their
metadata entries out of the reconstruction and merge them back
unchanged.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* fix(bnb): defer 8-bit weights split from their SCB stats across shards
Sharded serialization can place an 8-bit weight and its `SCB`
statistics in different shard files, in which case the shard-by-shard
loader failed with "Missing quantization component `SCB`". Hold the
incomplete half of the pair back until its counterpart arrives with a
later shard, mirroring the torchao pending mechanism, and disable
parallel shard loading for prequantized 8-bit checkpoints.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* [tests] extend model-level quantization tester mixins
Migrate remaining model-level coverage from tests/quantization into the
tester mixins so it runs for every wired model:
- base: buffer-placement assertions in the device-map test, and an
opt-in sharded-serialization test enabled by setting
`sharded_serialization_config`
- bnb: serialization across all configs (sharded included), dtype
assignment and adapter training for 8-bit, device moves preserving
the memory footprint, corrupted-state-dict loading error, and a fixed
modules-to-not-convert test (BitsAndBytesConfig only exposes
llm_int8_skip_modules; the old test passed an unsupported kwarg and
only survived by being skipped)
- torchao: custom device maps with cpu/disk offload, generalized from
the Flux-specific test
- gguf: the diffusers-format single-file loading path, wired into the
Flux model tests
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* [tests] fix model-level quantization test wiring
- SD3.5: the quantized testers reused the random-init dummy inputs
(4 latent channels, fp32) while the tiny Hub checkpoint has
in_channels=8 and the quantizers load the model in half precision;
give them matching inputs and relax the 4-bit memory expectation for
the tiny checkpoint.
- QwenImage / Flux2: the quantized testers had no Hub checkpoint wired
at all, so every test errored; point them at
hf-internal-testing/tiny-qwenimage-pipe and tiny-flux2 with matching
inputs.
- NucleusMoE: no tiny checkpoint exists on the Hub yet; comment the
testers out like the LTX ones.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* [tests] split tests/quantization into pipeline-level and backend-level tiers
Pipeline-level quantization tests (pipeline quality slices, cpu offload,
LoRA loading, compile, PipelineQuantizationConfig) move to
tests/pipelines/testing_utils/quantization.py, marked per backend so the
nightly CI can select them with `pytest -m`. tests/quantization keeps
only backend-level tests that fit neither tier: config validation,
utility warnings, and GGUF CUDA kernel correctness. Tests already
covered by the model-level mixins are dropped.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
* [ci] select nightly quantization tests by marker across test tiers
Each backend job now runs `pytest -m <marker>` over tests/models,
tests/quantization, and tests/pipelines/testing_utils/quantization.py,
giving the model-level mixin tests a nightly home with the backend
dependencies installed. The torchao job additionally installs mslk.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
---------
Co-authored-by: sayak@huggingface.co <sayak@ip-10-53-90-45.ec2.internal>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
* Reduce FLUX int8 test peak memory with sequential offload
* Gate FLUX int8 slow test with require_big_accelerator
---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
* Remove JAX/Flax support
Deletes all Flax models, schedulers, pipelines, and loading utilities,
the from_flax loading path, flax/jax packaging extras, Flax CI filters,
Flax training examples, and Flax content in translated docs.
Hub compatibility is preserved: Flax class names in old model_index.json
files are still stripped to their PyTorch equivalents, and *.msgpack
files in repos are still ignored during download.
* Drop Flax class-name remapping from model_index.json loading
Flax-saved checkpoint metadata is no longer recognized: class names like
FlaxStableDiffusionPipeline in model_index.json now fail to resolve
instead of being remapped to their PyTorch equivalents. *.msgpack files
in hub repos are still ignored during download.
* Restore Flax training examples
The example scripts are standalone and still work with diffusers<=0.39.x.
A warning note is added to each Flax README section pointing out the
version requirement now that the library itself no longer ships Flax.
* update
* Repoint scheduler default-config tests off the Flax fixture
* Repoint example training tests off the Flax fixture
* up
* up
* quantization level refactors.
* style
* up
* up
* use mixins and remove stale attributes
* fixture for the deprecated pipelines
* remove qkv
* remove lergacy for attention processor.
* use pytorch tensors exclusively.
* rejig dodgy test.
* improve how base pipeline output fixture is used.
* rename params.
* up
* use pipeline load api for ip adapter.
* move to flux specific.
* redesign config for caching
* remove eval.
* up
* up
* add a todo note on check_qkv_fusion_matches_attn_procs_length
* nan test in layerwise casting
* proper skipping
* skip properly.
* up
* up
**Summary:** TorchAO recently deprecated AffineQuantizedTensor
and related classes (https://github.com/pytorch/ao/issues/2752).
These will be removed in the next release. We should remove
references of these classes in diffusers before then.
**Test Plan:**
python -m pytest -s -v tests/quantization/torchao/test_torchao.py
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
* 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>
* Adding torchao version guard for floatx usage
Summary: TorchAO removing floatx support, added version guard in quantization_config.py
* Adding torchao version guard for floatx usage
Summary: TorchAO removing floatx support, added version guard in quantization_config.py
Altered tests in test_torchao.py to version guard floatx
Created new test to verify version guard of floatx support
* Adding torchao version guard for floatx usage
Summary: TorchAO removing floatx support, added version guard in quantization_config.py
Altered tests in test_torchao.py to version guard floatx
Created new test to verify version guard of floatx support
* Adding torchao version guard for floatx usage
Summary: TorchAO removing floatx support, added version guard in quantization_config.py
Altered tests in test_torchao.py to version guard floatx
Created new test to verify version guard of floatx support
* Adding torchao version guard for floatx usage
Summary: TorchAO removing floatx support, added version guard in quantization_config.py
Altered tests in test_torchao.py to version guard floatx
Created new test to verify version guard of floatx support
* Adding torchao version guard for floatx usage
Summary: TorchAO removing floatx support, added version guard in quantization_config.py
Altered tests in test_torchao.py to version guard floatx
Created new test to verify version guard of floatx support
---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
* extend TorchAoTest::test_model_memory_usage to other platform
Signe-off-by: Wang, Yi <yi.a.wang@inel.com>
* add some comments
Signed-off-by: Wang, Yi <yi.a.wang@intel.com>
---------
Signed-off-by: Wang, Yi <yi.a.wang@intel.com>
* purge HF_HUB_ENABLE_HF_TRANSFER; promote Xet
* purge HF_HUB_ENABLE_HF_TRANSFER; promote Xet x2
* restrict docker build test to the ones we actually use in CI.
---------
Co-authored-by: YiYi Xu <yixu310@gmail.com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
* feat: pipeline-level quant config.
Co-authored-by: SunMarc <marc.sun@hotmail.fr>
condition better.
support mapping.
improvements.
[Quantization] Add Quanto backend (#10756)
* update
* updaet
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* Update docs/source/en/quantization/quanto.md
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* Update src/diffusers/quantizers/quanto/utils.py
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
* update
* update
---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
[Single File] Add single file loading for SANA Transformer (#10947)
* added support for from_single_file
* added diffusers mapping script
* added testcase
* bug fix
* updated tests
* corrected code quality
* corrected code quality
---------
Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>
[LoRA] Improve warning messages when LoRA loading becomes a no-op (#10187)
* updates
* updates
* updates
* updates
* notebooks revert
* fix-copies.
* seeing
* fix
* revert
* fixes
* fixes
* fixes
* remove print
* fix
* conflicts ii.
* updates
* fixes
* better filtering of prefix.
---------
Co-authored-by: hlky <hlky@hlky.ac>
[LoRA] CogView4 (#10981)
* update
* make fix-copies
* update
[Tests] improve quantization tests by additionally measuring the inference memory savings (#11021)
* memory usage tests
* fixes
* gguf
[`Research Project`] Add AnyText: Multilingual Visual Text Generation And Editing (#8998)
* Add initial template
* Second template
* feat: Add TextEmbeddingModule to AnyTextPipeline
* feat: Add AuxiliaryLatentModule template to AnyTextPipeline
* Add bert tokenizer from the anytext repo for now
* feat: Update AnyTextPipeline's modify_prompt method
This commit adds improvements to the modify_prompt method in the AnyTextPipeline class. The method now handles special characters and replaces selected string prompts with a placeholder. Additionally, it includes a check for Chinese text and translation using the trans_pipe.
* Fill in the `forward` pass of `AuxiliaryLatentModule`
* `make style && make quality`
* `chore: Update bert_tokenizer.py with a TODO comment suggesting the use of the transformers library`
* Update error handling to raise and logging
* Add `create_glyph_lines` function into `TextEmbeddingModule`
* make style
* Up
* Up
* Up
* Up
* Remove several comments
* refactor: Remove ControlNetConditioningEmbedding and update code accordingly
* Up
* Up
* up
* refactor: Update AnyTextPipeline to include new optional parameters
* up
* feat: Add OCR model and its components
* chore: Update `TextEmbeddingModule` to include OCR model components and dependencies
* chore: Update `AuxiliaryLatentModule` to include VAE model and its dependencies for masked image in the editing task
* `make style`
* refactor: Update `AnyTextPipeline`'s docstring
* Update `AuxiliaryLatentModule` to include info dictionary so that text processing is done once
* simplify
* `make style`
* Converting `TextEmbeddingModule` to ordinary `encode_prompt()` function
* Simplify for now
* `make style`
* Up
* feat: Add scripts to convert AnyText controlnet to diffusers
* `make style`
* Fix: Move glyph rendering to `TextEmbeddingModule` from `AuxiliaryLatentModule`
* make style
* Up
* Simplify
* Up
* feat: Add safetensors module for loading model file
* Fix device issues
* Up
* Up
* refactor: Simplify
* refactor: Simplify code for loading models and handling data types
* `make style`
* refactor: Update to() method in FrozenCLIPEmbedderT3 and TextEmbeddingModule
* refactor: Update dtype in embedding_manager.py to match proj.weight
* Up
* Add attribution and adaptation information to pipeline_anytext.py
* Update usage example
* Will refactor `controlnet_cond_embedding` initialization
* Add `AnyTextControlNetConditioningEmbedding` template
* Refactor organization
* style
* style
* Move custom blocks from `AuxiliaryLatentModule` to `AnyTextControlNetConditioningEmbedding`
* Follow one-file policy
* style
* [Docs] Update README and pipeline_anytext.py to use AnyTextControlNetModel
* [Docs] Update import statement for AnyTextControlNetModel in pipeline_anytext.py
* [Fix] Update import path for ControlNetModel, ControlNetOutput in anytext_controlnet.py
* Refactor AnyTextControlNet to use configurable conditioning embedding channels
* Complete control net conditioning embedding in AnyTextControlNetModel
* up
* [FIX] Ensure embeddings use correct device in AnyTextControlNetModel
* up
* up
* style
* [UPDATE] Revise README and example code for AnyTextPipeline integration with DiffusionPipeline
* [UPDATE] Update example code in anytext.py to use correct font file and improve clarity
* down
* [UPDATE] Refactor BasicTokenizer usage to a new Checker class for text processing
* update pillow
* [UPDATE] Remove commented-out code and unnecessary docstring in anytext.py and anytext_controlnet.py for improved clarity
* [REMOVE] Delete frozen_clip_embedder_t3.py as it is in the anytext.py file
* [UPDATE] Replace edict with dict for configuration in anytext.py and RecModel.py for consistency
* 🆙
* style
* [UPDATE] Revise README.md for clarity, remove unused imports in anytext.py, and add author credits in anytext_controlnet.py
* style
* Update examples/research_projects/anytext/README.md
Co-authored-by: Aryan <contact.aryanvs@gmail.com>
* Remove commented-out image preparation code in AnyTextPipeline
* Remove unnecessary blank line in README.md
[Quantization] Allow loading TorchAO serialized Tensor objects with torch>=2.6 (#11018)
* update
* update
* update
* update
* update
* update
* update
* update
* update
fix: mixture tiling sdxl pipeline - adjust gerating time_ids & embeddings (#11012)
small fix on generating time_ids & embeddings
[LoRA] support wan i2v loras from the world. (#11025)
* support wan i2v loras from the world.
* remove copied from.
* upates
* add lora.
Fix SD3 IPAdapter feature extractor (#11027)
chore: fix help messages in advanced diffusion examples (#10923)
Fix missing **kwargs in lora_pipeline.py (#11011)
* Update lora_pipeline.py
* Apply style fixes
* fix-copies
---------
Co-authored-by: hlky <hlky@hlky.ac>
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Fix for multi-GPU WAN inference (#10997)
Ensure that hidden_state and shift/scale are on the same device when running with multiple GPUs
Co-authored-by: Jimmy <39@🇺🇸.com>
[Refactor] Clean up import utils boilerplate (#11026)
* update
* update
* update
Use `output_size` in `repeat_interleave` (#11030)
[hybrid inference 🍯🐝] Add VAE encode (#11017)
* [hybrid inference 🍯🐝] Add VAE encode
* _toctree: add vae encode
* Add endpoints, tests
* vae_encode docs
* vae encode benchmarks
* api reference
* changelog
* Update docs/source/en/hybrid_inference/overview.md
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
* update
---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Wan Pipeline scaling fix, type hint warning, multi generator fix (#11007)
* Wan Pipeline scaling fix, type hint warning, multi generator fix
* Apply suggestions from code review
[LoRA] change to warning from info when notifying the users about a LoRA no-op (#11044)
* move to warning.
* test related changes.
Rename Lumina(2)Text2ImgPipeline -> Lumina(2)Pipeline (#10827)
* Rename Lumina(2)Text2ImgPipeline -> Lumina(2)Pipeline
---------
Co-authored-by: YiYi Xu <yixu310@gmail.com>
making ```formatted_images``` initialization compact (#10801)
compact writing
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: YiYi Xu <yixu310@gmail.com>
Fix aclnnRepeatInterleaveIntWithDim error on NPU for get_1d_rotary_pos_embed (#10820)
* get_1d_rotary_pos_embed support npu
* Update src/diffusers/models/embeddings.py
---------
Co-authored-by: Kai zheng <kaizheng@KaideMacBook-Pro.local>
Co-authored-by: hlky <hlky@hlky.ac>
Co-authored-by: YiYi Xu <yixu310@gmail.com>
[Tests] restrict memory tests for quanto for certain schemes. (#11052)
* restrict memory tests for quanto for certain schemes.
* Apply suggestions from code review
Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>
* fixes
* style
---------
Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>
[LoRA] feat: support non-diffusers wan t2v loras. (#11059)
feat: support non-diffusers wan t2v loras.
[examples/controlnet/train_controlnet_sd3.py] Fixes#11050 - Cast prompt_embeds and pooled_prompt_embeds to weight_dtype to prevent dtype mismatch (#11051)
Fix: dtype mismatch of prompt embeddings in sd3 controlnet training
Co-authored-by: Andreas Jörg <andreasjoerg@MacBook-Pro-von-Andreas-2.fritz.box>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
reverts accidental change that removes attn_mask in attn. Improves fl… (#11065)
reverts accidental change that removes attn_mask in attn. Improves flux ptxla by using flash block sizes. Moves encoding outside the for loop.
Co-authored-by: Juan Acevedo <jfacevedo@google.com>
Fix deterministic issue when getting pipeline dtype and device (#10696)
Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>
[Tests] add requires peft decorator. (#11037)
* add requires peft decorator.
* install peft conditionally.
* conditional deps.
Co-authored-by: DN6 <dhruv.nair@gmail.com>
---------
Co-authored-by: DN6 <dhruv.nair@gmail.com>
CogView4 Control Block (#10809)
* cogview4 control training
---------
Co-authored-by: OleehyO <leehy0357@gmail.com>
Co-authored-by: yiyixuxu <yixu310@gmail.com>
[CI] pin transformers version for benchmarking. (#11067)
pin transformers version for benchmarking.
updates
Fix Wan I2V Quality (#11087)
* fix_wan_i2v_quality
* Update src/diffusers/pipelines/wan/pipeline_wan_i2v.py
Co-authored-by: YiYi Xu <yixu310@gmail.com>
* Update src/diffusers/pipelines/wan/pipeline_wan_i2v.py
Co-authored-by: YiYi Xu <yixu310@gmail.com>
* Update src/diffusers/pipelines/wan/pipeline_wan_i2v.py
Co-authored-by: YiYi Xu <yixu310@gmail.com>
* Update pipeline_wan_i2v.py
---------
Co-authored-by: YiYi Xu <yixu310@gmail.com>
Co-authored-by: hlky <hlky@hlky.ac>
LTX 0.9.5 (#10968)
* update
---------
Co-authored-by: YiYi Xu <yixu310@gmail.com>
Co-authored-by: hlky <hlky@hlky.ac>
make PR GPU tests conditioned on styling. (#11099)
Group offloading improvements (#11094)
update
Fix pipeline_flux_controlnet.py (#11095)
* Fix pipeline_flux_controlnet.py
* Fix style
update readme instructions. (#11096)
Co-authored-by: Juan Acevedo <jfacevedo@google.com>
Resolve stride mismatch in UNet's ResNet to support Torch DDP (#11098)
Modify UNet's ResNet implementation to resolve stride mismatch in Torch's DDP
Fix Group offloading behaviour when using streams (#11097)
* update
* update
Quality options in `export_to_video` (#11090)
* Quality options in `export_to_video`
* make style
improve more.
add placeholders for docstrings.
formatting.
smol fix.
solidify validation and annotation
* Revert "feat: pipeline-level quant config."
This reverts commit 316ff46b76.
* feat: implement pipeline-level quantization config
Co-authored-by: SunMarc <marc@huggingface.co>
* update
* fixes
* fix validation.
* add tests and other improvements.
* add tests
* import quality
* remove prints.
* add docs.
* fixes to docs.
* doc fixes.
* doc fixes.
* add validation to the input quantization_config.
* clarify recommendations.
* docs
* add to ci.
* todo.
---------
Co-authored-by: SunMarc <marc@huggingface.co>
