Skip to content

GitLab

Switch branch/tag
  1. 14 Apr, 2025 1 commit
  3. 13 Apr, 2025 2 commits
    • Ishan Modi's avatar
      [ControlNet] Adds controlnet for SanaTransformer (#11040) · f1f38ffb
      Ishan Modi authored 
      

* added controlnet for sana transformer

* improve code quality

* addressed PR comments

* bug fixes

* added test cases

* update

* added dummy objects

* addressed PR comments

* update

* Forcing update

* add to docs

* code quality

* addressed PR comments

* addressed PR comments

* update

* addressed PR comments

* added proper styling

* update

* Revert "added proper styling"

This reverts commit 344ee8a7014ada095b295034ef84341f03b0e359.

* manually ordered

* Apply suggestions from code review

---------
Co-authored-by: default avatarAryan <contact.aryanvs@gmail.com>
      f1f38ffb
    • Adrien B's avatar
      Update autoencoderkl_allegro.md (#11303) · ed41db85
      Adrien B authored 
      Correction typo
      ed41db85
  5. 11 Apr, 2025 1 commit
  7. 09 Apr, 2025 3 commits
  9. 08 Apr, 2025 3 commits
    • Sayak Paul's avatar
      [feat] implement `record_stream` when using CUDA streams during group offloading (#11081) · 4b27c4a4
      Sayak Paul authored 
      

* implement record_stream for better performance.

* fix

* style.

* merge #11097

* Update src/diffusers/hooks/group_offloading.py
Co-authored-by: default avatarAryan <aryan@huggingface.co>

* fixes

* docstring.

* remaining todos in low_cpu_mem_usage

* tests

* updates to docs.

---------
Co-authored-by: default avatarAryan <aryan@huggingface.co>
      4b27c4a4
    • Benjamin Bossan's avatar
      [LoRA] Implement hot-swapping of LoRA (#9453) · fb544996
      Benjamin Bossan authored 
      * [WIP][LoRA] Implement hot-swapping of LoRA

This PR adds the possibility to hot-swap LoRA adapters. It is WIP.

Description

As of now, users can already load multiple LoRA adapters. They can
offload existing adapters or they can unload them (i.e. delete them).
However, they cannot "hotswap" adapters yet, i.e. substitute the weights
from one LoRA adapter with the weights of another, without the need to
create a separate LoRA adapter.

Generally, hot-swapping may not appear not super useful but when the
model is compiled, it is necessary to prevent recompilation. See #9279
for more context.

Caveats

To hot-swap a LoRA adapter for another, these two adapters should target
exactly the same layers and the "hyper-parameters" of the two adapters
should be identical. For instance, the LoRA alpha has to be the same:
Given that we keep the alpha from the first adapter, the LoRA scaling
would be incorrect for the second adapter otherwise.

Theoretically, we could override the scaling dict with the alpha values
derived from the second adapter's config, but changing the dict will
trigger a guard for recompilation, defeating the main purpose of the
feature.

I also found that compilation flags can have an impact on whether this
works or not. E.g. when passing "reduce-overhead", there will be errors
of the type:

> input name: arg861_1. data pointer changed from 139647332027392 to
139647331054592

I don't know enough about compilation to determine whether this is
problematic or not.

Current state

This is obviously WIP right now to collect feedback and discuss which
direction to take this. If this PR turns out to be useful, the
hot-swapping functions will be added to PEFT itself and can be imported
here (or there is a separate copy in diffusers to avoid the need for a
min PEFT version to use this feature).

Moreover, more tests need to be added to better cover this feature,
although we don't necessarily need tests for the hot-swapping
functionality itself, since those tests will be added to PEFT.

Furthermore, as of now, this is only implemented for the unet. Other
pipeline components have yet to implement this feature.

Finally, it should be properly documented.

I would like to collect feedback on the current state of the PR before
putting more time into finalizing it.

* Reviewer feedback

* Reviewer feedback, adjust test

* Fix, doc

* Make fix

* Fix for possible g++ error

* Add test for recompilation w/o hotswapping

* Make hotswap work

Requires https://github.com/huggingface/peft/pull/2366

More changes to make hotswapping work. Together with the mentioned PEFT
PR, the tests pass for me locally.

List of changes:

- docstring for hotswap
- remove code copied from PEFT, import from PEFT now
- adjustments to PeftAdapterMixin.load_lora_adapter (unfortunately, some
  state dict renaming was necessary, LMK if there is a better solution)
- adjustments to UNet2DConditionLoadersMixin._process_lora: LMK if this
  is even necessary or not, I'm unsure what the overall relationship is
  between this and PeftAdapterMixin.load_lora_adapter
- also in UNet2DConditionLoadersMixin._process_lora, I saw that there is
  no LoRA unloading when loading the adapter fails, so I added it
  there (in line with what happens in PeftAdapterMixin.load_lora_adapter)
- rewritten tests to avoid shelling out, make the test more precise by
  making sure that the outputs align, parametrize it
- also checked the pipeline code mentioned in this comment:
  https://github.com/huggingface/diffusers/pull/9453#issuecomment-2418508871;


  when running this inside the with
  torch._dynamo.config.patch(error_on_recompile=True) context, there is
  no error, so I think hotswapping is now working with pipelines.

* Address reviewer feedback:

- Revert deprecated method
- Fix PEFT doc link to main
- Don't use private function
- Clarify magic numbers
- Add pipeline test

Moreover:
- Extend docstrings
- Extend existing test for outputs != 0
- Extend existing test for wrong adapter name

* Change order of test decorators

parameterized.expand seems to ignore skip decorators if added in last
place (i.e. innermost decorator).

* Split model and pipeline tests

Also increase test coverage by also targeting conv2d layers (support of
which was added recently on the PEFT PR).

* Reviewer feedback: Move decorator to test classes

... instead of having them on each test method.

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

* Reviewer feedback: version check, TODO comment

* Add enable_lora_hotswap method

* Reviewer feedback: check _lora_loadable_modules

* Revert changes in unet.py

* Add possibility to ignore enabled at wrong time

* Fix docstrings

* Log possible PEFT error, test

* Raise helpful error if hotswap not supported

I.e. for the text encoder

* Formatting

* More linter

* More ruff

* Doc-builder complaint

* Update docstring:

- mention no text encoder support yet
- make it clear that LoRA is meant
- mention that same adapter name should be passed

* Fix error in docstring

* Update more methods with hotswap argument

- SDXL
- SD3
- Flux

No changes were made to load_lora_into_transformer.

* Add hotswap argument to load_lora_into_transformer

For SD3 and Flux. Use shorter docstring for brevity.

* Extend docstrings

* Add version guards to tests

* Formatting

* Fix LoRA loading call to add prefix=None

See:
https://github.com/huggingface/diffusers/pull/10187#issuecomment-2717571064



* Run make fix-copies

* Add hot swap documentation to the docs

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

---------
Co-authored-by: default avatarSayak Paul <spsayakpaul@gmail.com>
Co-authored-by: default avatarhlky <hlky@hlky.ac>
Co-authored-by: default avatarYiYi Xu <yixu310@gmail.com>
Co-authored-by: default avatarSteven Liu <59462357+stevhliu@users.noreply.github.com>
      fb544996
    • Steven Liu's avatar
      [docs] MPS update (#11212) · fc7a867a
      Steven Liu authored 
      mps
      fc7a867a
  11. 04 Apr, 2025 1 commit
    • Tolga Cangöz's avatar
      [LTX0.9.5] Refactor `LTXConditionPipeline` for text-only conditioning (#11174) · 13e48492
      Tolga Cangöz authored 
      * Refactor `LTXConditionPipeline` to add text-only conditioning

* style

* up

* Refactor `LTXConditionPipeline` to streamline condition handling and improve clarity

* Improve condition checks

* Simplify latents handling based on conditioning type

* Refactor rope_interpolation_scale preparation for clarity and efficiency

* Update LTXConditionPipeline docstring to clarify supported input types

* Add LTX Video 0.9.5 model to documentation

* Clarify documentation to indicate support for text-only conditioning without passing `conditions`

* refactor: comment out unused parameters in LTXConditionPipeline

* fix: restore previously commented parameters in LTXConditionPipeline

* fix: remove unused parameters from LTXConditionPipeline

* refactor: remove unnecessary lines in LTXConditionPipeline
      13e48492
  13. 02 Apr, 2025 1 commit
  15. 01 Apr, 2025 1 commit
    • Dhruv Nair's avatar
      [WIP] Add Wan Video2Video (#11053) · df1d7b01
      Dhruv Nair authored 
      * update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update
      df1d7b01
  17. 31 Mar, 2025 1 commit
  19. 28 Mar, 2025 1 commit
  21. 24 Mar, 2025 3 commits
  23. 21 Mar, 2025 2 commits
  25. 18 Mar, 2025 1 commit
  27. 13 Mar, 2025 1 commit
  29. 12 Mar, 2025 1 commit
  31. 11 Mar, 2025 2 commits
  33. 10 Mar, 2025 1 commit
  35. 07 Mar, 2025 2 commits
  37. 04 Mar, 2025 1 commit
  39. 03 Mar, 2025 2 commits
  41. 02 Mar, 2025 2 commits
    • hlky's avatar
      Add `remote_decode` to `remote_utils` (#10898) · fc4229a0
      hlky authored 
      

* Add `remote_decode` to `remote_utils`

* test dependency

* test dependency

* dependency

* dependency

* dependency

* docstrings

* changes

* make style

* apply

* revert, add new options

* Apply style fixes

* deprecate base64, headers not needed

* address comments

* add license header

* init test_remote_decode

* more

* more test

* more test

* skeleton for xl, flux

* more test

* flux test

* flux packed

* no scaling

* -save

* hunyuanvideo test

* Apply style fixes

* init docs

* Update src/diffusers/utils/remote_utils.py
Co-authored-by: default avatarSayak Paul <spsayakpaul@gmail.com>

* comments

* Apply style fixes

* comments

* hybrid_inference/vae_decode

* fix

* tip?

* tip

* api reference autodoc

* install tip

---------
Co-authored-by: default avatarsayakpaul <spsayakpaul@gmail.com>
Co-authored-by: default avatargithub-actions[bot] <github-actions[bot]@users.noreply.github.com>
      fc4229a0
    • YiYi Xu's avatar
      [Alibaba Wan Team] continue on #10921 Wan2.1 (#10922) · 2d8a41ca
      YiYi Xu authored 
      * Add wanx pipeline, model and example

* wanx_merged_v1

* change WanX into Wan

* fix i2v fp32 oom error

Link: https://code.alibaba-inc.com/open_wanx2/diffusers/codereview/20607813



* support t2v load fp32 ckpt

* add example

* final merge v1

* Update autoencoder_kl_wan.py

* up

* update middle, test up_block

* up up

* one less nn.sequential

* up more

* up

* more

* [refactor] [wip] Wan transformer/pipeline (#10926)

* update

* update

* refactor rope

* refactor pipeline

* make fix-copies

* add transformer test

* update

* update

* make style

* update tests

* tests

* conversion script

* conversion script

* update

* docs

* remove unused code

* fix _toctree.yml

* update dtype

* fix test

* fix tests: scale

* up

* more

* Apply suggestions from code review

* Apply suggestions from code review

* style

* Update scripts/convert_wan_to_diffusers.py

* update docs

* fix

---------
Co-authored-by: default avatarYitong Huang <huangyitong.hyt@alibaba-inc.com>
Co-authored-by: default avatar亚森 <wangjiayu.wjy@alibaba-inc.com>
Co-authored-by: default avatarAryan <aryan@huggingface.co>
      2d8a41ca
  43. 26 Feb, 2025 1 commit
  45. 24 Feb, 2025 4 commits
  47. 22 Feb, 2025 1 commit
  49. 21 Feb, 2025 1 commit