GitLab

up

* use state dict when setting up LoRA.

* up

* up

* up

* comment

* up

* up

* feat: support lora in qwen image and training script

* up

* up

* up

* up

* up

* up

* add lora tests

* fix

* add tests

* fix

* reviewer feedback

* up[

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

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

* update

* try test fix

* add missing link

* fix tests

* Update src/diffusers/hooks/first_block_cache.py

* make style

fix: disabling hooks when loading loras.

* mark wanvace lora tests as flaky

* ability to apply is_flaky at a class-level

* update

* increase max_attempt.

* increase attemtp.

* update

* update

* fix

* actually, better fix

* empty commit; trigger tests again

* mark wanvace test as flaky

* FIX set_lora_device when target layers differ

Resolves #11833

Fixes a bug that occurs after calling set_lora_device when multiple LoRA
adapters are loaded that target different layers.

Note: Technically, the accompanying test does not require a GPU because
the bug is triggered even if the parameters are already on the
corresponding device, i.e. loading on CPU and then changing the device
to CPU is sufficient to cause the bug. However, this may be optimized
away in the future, so I decided to test with GPU.

* Update docstring to warn about device mismatch

* Extend docstring with an example

* Fix docstring

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

* wan vace.

* update

* update

* import problem

* feat: use exclude modules to loraconfig.

* version-guard.

* tests and version guard.

* remove print.

* describe the test

* more detailed warning message + shift to debug

* update

* update

* update

* remove test

* fix: lora unloading behvaiour

* fix

* update

* update

* add test

* address review comments

* update

* fixes

* change decorator order to fix tests

* try fix

* fight tests

* factor out stuff from load_lora_adapter().

* simplifying text encoder lora loading.

* fix peft.py

* fix logging locations.

* formatting

* fix

* update

* update

* update

change to 2025 licensing for remaining

* feat: parse metadata from lora state dicts.

* tests

* fix tests

* key renaming

* fix

* smol update

* smol updates

* load metadata.

* automatically save metadata in save_lora_adapter.

* propagate changes.

* changes

* add test to models too.

* tigher tests.

* updates

* fixes

* rename tests.

* sorted.

* Update src/diffusers/loaders/lora_base.py
Co-authored-by: Benjamin Bossan <BenjaminBossan@users.noreply.github.com>

* review suggestions.

* removeprefix.

* propagate changes.

* fix-copies

* sd

* docs.

* fixes

* get review ready.

* one more test to catch error.

* change to a different approach.

* fix-copies.

* todo

* sd3

* update

* revert changes in get_peft_kwargs.

* update

* fixes

* fixes

* simplify _load_sft_state_dict_metadata

* update

* style fix

* uipdate

* update

* update

* empty commit

* _pack_dict_with_prefix

* update

* TODO 1.

* todo: 2.

* todo: 3.

* update

* update

* Apply suggestions from code review
Co-authored-by: Benjamin Bossan <BenjaminBossan@users.noreply.github.com>

* reraise.

* move argument.

---------
Co-authored-by: Benjamin Bossan <BenjaminBossan@users.noreply.github.com>
Co-authored-by: Linoy Tsaban <57615435+linoytsaban@users.noreply.github.com>

* Fix typos in strings and comments
Signed-off-by: co63oc <co63oc@users.noreply.github.com>

* Update src/diffusers/hooks/hooks.py
Co-authored-by: Aryan <contact.aryanvs@gmail.com>

* Update src/diffusers/hooks/hooks.py
Co-authored-by: Aryan <contact.aryanvs@gmail.com>

* Update layerwise_casting.py

* Apply style fixes

* update

---------
Signed-off-by: co63oc <co63oc@users.noreply.github.com>
Co-authored-by: Aryan <contact.aryanvs@gmail.com>
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>

* improve lora fusion tests

* more improvements.

* remove comment

* update

* relax tolerance.

* num_fused_loras as a property
Co-authored-by: BenjaminBossan <benjamin.bossan@gmail.com>

* updates

* update

* fix

* fix
Co-authored-by: BenjaminBossan <benjamin.bossan@gmail.com>

* Update src/diffusers/loaders/lora_base.py
Co-authored-by: Benjamin Bossan <BenjaminBossan@users.noreply.github.com>

---------
Co-authored-by: BenjaminBossan <benjamin.bossan@gmail.com>
Co-authored-by: Benjamin Bossan <BenjaminBossan@users.noreply.github.com>

* fix peft delete adapters for flux.

* add test

* empty commit

* enable lora cases on XPU
Signed-off-by: Yao Matrix <matrix.yao@intel.com>

* remove hunyuanvideo xpu expectation
Signed-off-by: Yao Matrix <matrix.yao@intel.com>

---------
Signed-off-by: Yao Matrix <matrix.yao@intel.com>

* post release

* update

* fix deprecations

* remaining

* update

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

* Add AuraFlowLoraLoaderMixin

* Add comments, remove qkv fusion

* Add Tests

* Add AuraFlowLoraLoaderMixin to documentation

* Add Suggested changes

* Change attention_kwargs->joint_attention_kwargs

* Rebasing derp.

* fix

* fix

* Quality fixes.

* make style

* `make fix-copies`

* `ruff check --fix`

* Attept 1 to fix tests.

* Attept 2 to fix tests.

* Attept 3 to fix tests.

* Address review comments.

* Rebasing derp.

* Get more tests passing by copying from Flux. Address review comments.

* `joint_attention_kwargs`->`attention_kwargs`

* Add `lora_scale` property for te LoRAs.

* Make test better.

* Remove useless property.

* Skip TE-only tests for AuraFlow.

* Support LoRA for non-CLIP TEs.

* Restore LoRA tests.

* Undo adding LoRA support for non-CLIP TEs.

* Undo support for TE in AuraFlow LoRA.

* `make fix-copies`

* Sync with upstream changes.

* Remove unneeded stuff.

* Mirror `Lumina2`.

* Skip for MPS.

* Address review comments.

* Remove duplicated code.

* Remove unnecessary code.

* Remove repeated docs.

* Propagate attention.

* Fix TE target modules.

* MPS fix for LoRA tests.

* Unrelated TE LoRA tests fix.

* Fix AuraFlow LoRA tests by applying to the right denoiser layers.
Co-authored-by: AstraliteHeart <81396681+AstraliteHeart@users.noreply.github.com>

* Apply style fixes

* empty commit

* Fix the repo consistency issues.

* Remove unrelated changes.

* Style.

* Fix `test_lora_fuse_nan`.

* fix quality issues.

* `pytest.xfail` -> `ValueError`.

* Add back `skip_mps`.

* Apply style fixes

* `make fix-copies`

---------
Co-authored-by: Warlord-K <warlordk28@gmail.com>
Co-authored-by: hlky <hlky@hlky.ac>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: AstraliteHeart <81396681+AstraliteHeart@users.noreply.github.com>
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>

* start cleaning up lora test utils for reusability

* update

* updates

* updates

* fix test_vanilla_funetuning failure on XPU and A100
Signed-off-by: Matrix Yao <matrix.yao@intel.com>

* change back to 5e-2
Signed-off-by: Matrix Yao <matrix.yao@intel.com>

---------
Signed-off-by: Matrix Yao <matrix.yao@intel.com>

* move to warning.

* test related changes.

* update

* make fix-copies

* update

* 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>

* update

* refactor image-to-video pipeline

* update

* fix copied from

* use FP32LayerNorm

* 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

* add changes

* bug fix

* enable on xpu

* update more cases

* revert

* revert back

* Update test_stable_diffusion_xl.py

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

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

* Update tests/pipelines/stable_diffusion/test_stable_diffusion_img2img.py
Co-authored-by: hlky <hlky@hlky.ac>

* Update tests/pipelines/stable_diffusion/test_stable_diffusion_img2img.py
Co-authored-by: hlky <hlky@hlky.ac>

* Update tests/pipelines/stable_diffusion/test_stable_diffusion_img2img.py
Co-authored-by: hlky <hlky@hlky.ac>

* Apply suggestions from code review
Co-authored-by: hlky <hlky@hlky.ac>

* add test marker

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

fix: lumina2 lora fuse_nan test

* feat: lora support for Lumina2.

* fix-copies.

* updates

* updates

* docs.

* fix

* add: training script.

* tests

* updates

* updates

* major updates.

* updates

* fixes

* docs.

* updates

* updates

* make set_adapters() robust on silent failures.

* fixes to tests

* flaky decorator.

* fix

* flaky to sd3.

* remove warning.

* sort

* quality

* skip test_simple_inference_with_text_denoiser_multi_adapter_block_lora

* skip testing unsupported features.

* raise warning instead of error.

* disable peft input autocast

* use new peft method name; only disable peft input autocast if submodule layerwise casting active

* add test; reference PeftInputAutocastDisableHook in peft docs

* add load_lora_weights test

* casted -> cast

* Update tests/lora/utils.py

* 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>

* print

* remove print.

* print

* update slice.

* empty

* allow big lora tests to run on the CI.

* print

* print.

* print

* print

* print

* print

* more

* print

* remove print.

* remove print

* directly place on cuda.

* remove pipeline.

* remove

* fix

* fix

* spaces

* quality

* updates

* directly place flux controlnet pipeline on cuda.

* torch_device instead of cuda.

* style

* device placement.

* fixes

* add big gpu marker for mochi; rename test correctly

* address feedback

* fix

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

* update

* fix make copies

* update

* add relevant markers to the integration test suite.

* add copied.

* fox-copies

* temporarily add print.

* directly place on CUDA as CPU isn't that big on the CIO.

* fixes to fuse_lora, aryan was right.

* fixes

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

* fix: lora unloading when using expanded Flux LoRAs.

* fix argument name.
Co-authored-by: a-r-r-o-w <contact.aryanvs@gmail.com>

* docs.

---------
Co-authored-by: a-r-r-o-w <contact.aryanvs@gmail.com>

add slow and nightly markers to sd3 lora integation.