GitLab

feat(training-utils): support device and dtype params in compute_density_for_timestep_sampling (#10699)

* feat(training-utils): support device and dtype params in compute_density_for_timestep_sampling

* chore: update type hint

* refactor: use union for type hint

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

* fix enable memory efficient attention on ROCm

while calling CK implementation

* Update attention_processor.py

refactor of picking a set element

fix_shape_error

* support StableDiffusionAdapterPipeline.from_single_file

* make style

---------
Co-authored-by: Teriks <Teriks@users.noreply.github.com>
Co-authored-by: hlky <hlky@hlky.ac>

* conditionally check if compute capability is met.

* log info.

* fix condition.

* updates

* updates

* updates

* updates

* update

* remove unused fn

* apply suggestions based on review

* update + cleanup 🧹

* more cleanup 🧹

* make fix-copies

* update test

* fix: refer to use_framewise_encoding on AutoencoderKLHunyuanVideo._encode

* fix: comment about tile_sample_min_num_frames

---------
Co-authored-by: Aryan <aryan@huggingface.co>

* start pyramid attention broadcast

* add coauthor
Co-Authored-By: Xuanlei Zhao <43881818+oahzxl@users.noreply.github.com>

* update

* make style

* update

* make style

* add docs

* add tests

* update

* Update docs/source/en/api/pipelines/cogvideox.md
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* Update docs/source/en/api/pipelines/cogvideox.md
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* Pyramid Attention Broadcast rewrite + introduce hooks (#9826)

* rewrite implementation with hooks

* make style

* update

* merge pyramid-attention-rewrite-2

* make style

* remove changes from latte transformer

* revert docs changes

* better debug message

* add todos for future

* update tests

* make style

* cleanup

* fix

* improve log message; fix latte test

* refactor

* update

* update

* update

* revert changes to tests

* update docs

* update tests

* Apply suggestions from code review
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* update

* fix flux test

* reorder

* refactor

* make fix-copies

* update docs

* fixes

* more fixes

* make style

* update tests

* update code example

* make fix-copies

* refactor based on reviews

* use maybe_free_model_hooks

* CacheMixin

* make style

* update

* add current_timestep property; update docs

* make fix-copies

* update

* improve tests

* try circular import fix

* apply suggestions from review

* address review comments

* Apply suggestions from code review

* refactor hook implementation

* add test suite for hooks

* PAB Refactor (#10667)

* update

* update

* update

---------
Co-authored-by: DN6 <dhruv.nair@gmail.com>

* update

* fix remove hook behaviour

---------
Co-authored-by: Xuanlei Zhao <43881818+oahzxl@users.noreply.github.com>
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
Co-authored-by: DN6 <dhruv.nair@gmail.com>

Co-authored-by: Giuseppe Catalano <giuseppelorenzo.catalano@unito.it>

controlnet union XL, make control_image immutible

when this argument is passed a list, __call__
modifies its content, since it is pass by reference
the list passed by the caller gets its content
modified unexpectedly

make a copy at method intro so this does not happen
Co-authored-by: Teriks <Teriks@users.noreply.github.com>

Sigmoid scheduler in scheduling_ddpm.py docs

* NPU Adaption for Sanna


---------
Co-authored-by: J石页 <jiangshuo9@h-partners.com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

vars mixed-up

add onnxruntime-migraphx to import_utils.py
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

improve error message

* update

* update

* make style

* remove dynamo disable

* add coauthor
Co-Authored-By: Dhruv Nair <dhruv.nair@gmail.com>

* update

* update

* update

* update mixin

* add some basic tests

* update

* update

* non_blocking

* improvements

* update

* norm.* -> norm

* apply suggestions from review

* add example

* update hook implementation to the latest changes from pyramid attention broadcast

* deinitialize should raise an error

* update doc page

* Apply suggestions from code review
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* update docs

* update

* refactor

* fix _always_upcast_modules for asym ae and vq_model

* fix lumina embedding forward to not depend on weight dtype

* refactor tests

* add simple lora inference tests

* _always_upcast_modules -> _precision_sensitive_module_patterns

* remove todo comments about review; revert changes to self.dtype in unets because .dtype on ModelMixin should be able to handle fp8 weight case

* check layer dtypes in lora test

* fix UNet1DModelTests::test_layerwise_upcasting_inference

* _precision_sensitive_module_patterns -> _skip_layerwise_casting_patterns based on feedback

* skip test in NCSNppModelTests

* skip tests for AutoencoderTinyTests

* skip tests for AutoencoderOobleckTests

* skip tests for UNet1DModelTests - unsupported pytorch operations

* layerwise_upcasting -> layerwise_casting

* skip tests for UNetRLModelTests; needs next pytorch release for currently unimplemented operation support

* add layerwise fp8 pipeline test

* use xfail

* Apply suggestions from code review
Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>

* add assertion with fp32 comparison; add tolerance to fp8-fp32 vs fp32-fp32 comparison (required for a few models' test to pass)

* add note about memory consumption on tesla CI runner for failing test

---------
Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* add

* style

* initial comit

* fix empty cache

* fix one more

* fix style

* update device functions

* update

* update

* Update src/diffusers/utils/testing_utils.py
Co-authored-by: hlky <hlky@hlky.ac>

* Update src/diffusers/utils/testing_utils.py
Co-authored-by: hlky <hlky@hlky.ac>

* Update src/diffusers/utils/testing_utils.py
Co-authored-by: hlky <hlky@hlky.ac>

* Update tests/pipelines/controlnet/test_controlnet.py
Co-authored-by: hlky <hlky@hlky.ac>

* Update src/diffusers/utils/testing_utils.py
Co-authored-by: hlky <hlky@hlky.ac>

* Update src/diffusers/utils/testing_utils.py
Co-authored-by: hlky <hlky@hlky.ac>

* Update tests/pipelines/controlnet/test_controlnet.py
Co-authored-by: hlky <hlky@hlky.ac>

* with gc.collect

* update

* make style

* check_torch_dependencies

* add mps empty cache

* bug fix

* Apply suggestions from code review

---------
Co-authored-by: hlky <hlky@hlky.ac>

* enable dreambooth_lora on other devices
Signed-off-by: jiqing-feng <jiqing.feng@intel.com>

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

* check cuda device before empty cache
Signed-off-by: jiqing-feng <jiqing.feng@intel.com>

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

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

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

change licensing to 2025 from 2024.

* bugfix for npu not support float64

* is_mps is_npu

---------
Co-authored-by: 白超 <baichao19@huawei.com>
Co-authored-by: hlky <hlky@hlky.ac>

Signed-off-by: sunxunle <sunxunle@ampere.tech>

* Update __init__.py

* add consisid

* update consisid

* update consisid

* make style

* make_style

* Update src/diffusers/pipelines/consisid/pipeline_consisid.py
Co-authored-by: hlky <hlky@hlky.ac>

* Update src/diffusers/pipelines/consisid/pipeline_consisid.py
Co-authored-by: hlky <hlky@hlky.ac>

* Update src/diffusers/pipelines/consisid/pipeline_consisid.py
Co-authored-by: hlky <hlky@hlky.ac>

* Update src/diffusers/pipelines/consisid/pipeline_consisid.py
Co-authored-by: hlky <hlky@hlky.ac>

* Update src/diffusers/pipelines/consisid/pipeline_consisid.py
Co-authored-by: hlky <hlky@hlky.ac>

* Update src/diffusers/pipelines/consisid/pipeline_consisid.py
Co-authored-by: hlky <hlky@hlky.ac>

* add doc

* make style

* Rename consisid .md to consisid.md

* Update geodiff_molecule_conformation.ipynb

* Update geodiff_molecule_conformation.ipynb

* Update geodiff_molecule_conformation.ipynb

* Update demo.ipynb

* Update pipeline_consisid.py

* make fix-copies

* Update docs/source/en/using-diffusers/consisid.md
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* Update src/diffusers/pipelines/consisid/pipeline_consisid.py
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* Update src/diffusers/pipelines/consisid/pipeline_consisid.py
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* Update docs/source/en/using-diffusers/consisid.md
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* Update docs/source/en/using-diffusers/consisid.md
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* update doc & pipeline code

* fix typo

* make style

* update example

* Update docs/source/en/using-diffusers/consisid.md
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* update example

* update example

* Update src/diffusers/pipelines/consisid/pipeline_consisid.py
Co-authored-by: hlky <hlky@hlky.ac>

* Update src/diffusers/pipelines/consisid/pipeline_consisid.py
Co-authored-by: hlky <hlky@hlky.ac>

* update

* add test and update

* remove some changes from docs

* refactor

* fix

* undo changes to examples

* remove save/load and fuse methods

* update

* link hf-doc-img & make test extremely small

* update

* add lora

* fix test

* update

* update

* change expected_diff_max to 0.4

* fix typo

* fix link

* fix typo

* update docs

* update

* remove consisid lora tests

---------
Co-authored-by: hlky <hlky@hlky.ac>
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
Co-authored-by: Aryan <aryan@huggingface.co>

* implementing flux on TPUs with ptxla

* add xla flux attention class

* run make style/quality

* Update src/diffusers/models/attention_processor.py
Co-authored-by: YiYi Xu <yixu310@gmail.com>

* Update src/diffusers/models/attention_processor.py
Co-authored-by: YiYi Xu <yixu310@gmail.com>

* run style and quality

---------
Co-authored-by: Juan Acevedo <jfacevedo@google.com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: YiYi Xu <yixu310@gmail.com>

* NPU adaption for RMSNorm

* NPU adaption for RMSNorm

---------
Co-authored-by: J石页 <jiangshuo9@h-partners.com>

* use np.int32 in scheduling

* test_add_noise_device

* -np.int32, fixes

* Move buffers to device

* add test

* named_buffers

* autoencoder_dc tiling

* add tiling and slicing support in SANA pipelines

* create variables for padding length because the line becomes too long

* add tiling and slicing support in pag SANA pipelines

* revert changes to tile size

* make style

* add vae tiling test

* fix SanaMultiscaleLinearAttention apply_quadratic_attention bf16

---------
Co-authored-by: Aryan <aryan@huggingface.co>

Added support for IP-Adapter

fix vae annotation in mochi pipeline

* feat: support loading loras into 4bit quantized models.

* updates

* update

* remove weight check.

* Added support for IP-Adapter

* Added joint_attention_kwargs property

* [Sana 4K]
add 4K support for Sana

* [Sana-4K] fix SanaPAGPipeline

* add VAE automatically tiling function;

* set clean_caption to False;

* add warnings for VAE OOM.

* style

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

Co-authored-by: Teriks <Teriks@users.noreply.github.com>

* load and save dduf archive

* style

* switch to zip uncompressed

* updates

* Update src/diffusers/pipelines/pipeline_utils.py
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* Update src/diffusers/pipelines/pipeline_utils.py
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* first draft

* remove print

* switch to dduf_file for consistency

* switch to huggingface hub api

* fix log

* add a basic test

* Update src/diffusers/configuration_utils.py
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* Update src/diffusers/pipelines/pipeline_utils.py
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* Update src/diffusers/pipelines/pipeline_utils.py
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* fix

* fix variant

* change saving logic

* DDUF - Load transformers components manually (#10171)

* update hfh version

* Load transformers components manually

* load encoder from_pretrained with state_dict

* working version with transformers and tokenizer !

* add generation_config case

* fix tests

* remove saving for now

* typing

* need next version from transformers

* Update src/diffusers/configuration_utils.py
Co-authored-by: Lucain <lucain@huggingface.co>

* check path corectly

* Apply suggestions from code review
Co-authored-by: Lucain <lucain@huggingface.co>

* udapte

* typing

* remove check for subfolder

* quality

* revert setup changes

* oups

* more readable condition

* add loading from the hub test

* add basic docs.

* Apply suggestions from code review
Co-authored-by: Lucain <lucain@huggingface.co>

* add example

* add

* make functions private

* Apply suggestions from code review
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* minor.

* fixes

* fix

* change the precdence of parameterized.

* error out when custom pipeline is passed with dduf_file.

* updates

* fix

* updates

* fixes

* updates

* fix xfail condition.

* fix xfail

* fixes

* sharded checkpoint compat

* add test for sharded checkpoint

* add suggestions

* Update src/diffusers/models/model_loading_utils.py
Co-authored-by: YiYi Xu <yixu310@gmail.com>

* from suggestions

* add class attributes to flag dduf tests

* last one

* fix logic

* remove comment

* revert changes

---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: Lucain <lucain@huggingface.co>
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
Co-authored-by: YiYi Xu <yixu310@gmail.com>