Skip to content

GitLab

Switch branch/tag
  1. 12 Nov, 2025 5 commits
    • Quentin Gallouédec's avatar
      ArXiv -> HF Papers (#12583) · f3db38c1
      Quentin Gallouédec authored 
      * Update pipeline_skyreels_v2_i2v.py

* Update README.md

* Update torch_utils.py

* Update torch_utils.py

* Update guider_utils.py

* Update pipeline_ltx.py

* Update pipeline_bria.py

* Apply suggestion from @qgallouedec

* Update autoencoder_kl_qwenimage.py

* Update pipeline_prx.py

* Update pipeline_wan_vace.py

* Update pipeline_skyreels_v2.py

* Update pipeline_skyreels_v2_diffusion_forcing.py

* Update pipeline_bria_fibo.py

* Update pipeline_skyreels_v2_diffusion_forcing_i2v.py

* Update pipeline_ltx_condition.py

* Update pipeline_ltx_image2video.py

* Update regional_prompting_stable_diffusion.py

* make style

* style

* style
      f3db38c1
    • Sayak Paul's avatar
      [modular] add tests for qwen modular (#12585) · f5e5f348
      Sayak Paul authored 
      * add tests for qwenimage modular.

* qwenimage edit.

* qwenimage edit plus.

* empty

* align with the latest structure

* up

* up

* reason

* up

* fix multiple issues.

* up

* up

* fix

* up

* make it similar to the original pipeline.
      f5e5f348
    • YiYi Xu's avatar
      fix dispatch_attention_fn check (#12636) · 093cd3f0
      YiYi Xu authored 
      * fix

* fix
      093cd3f0
    • a120092009's avatar
      Add MLU Support. (#12629) · aecf0c53
      a120092009 authored 
      

* Add MLU Support.

* fix comment.

* rename is_mlu_available to is_torch_mlu_available

* Apply style fixes

---------
Co-authored-by: default avatargithub-actions[bot] <github-actions[bot]@users.noreply.github.com>
      aecf0c53
    • YiYi Xu's avatar
      fix copies (#12637) · 0c758929
      YiYi Xu authored 
      * fix

* remoce cocpies instead
      0c758929
  3. 11 Nov, 2025 2 commits
  5. 10 Nov, 2025 8 commits
  7. 07 Nov, 2025 3 commits
  9. 06 Nov, 2025 4 commits
  11. 04 Nov, 2025 3 commits
  13. 03 Nov, 2025 2 commits
  15. 02 Nov, 2025 3 commits
  17. 31 Oct, 2025 2 commits
  19. 30 Oct, 2025 2 commits
  21. 28 Oct, 2025 6 commits
    • galbria's avatar
      Bria fibo (#12545) · 84e16575
      galbria authored 
      

* Bria FIBO pipeline

* style fixs

* fix CR

* Refactor BriaFibo classes and update pipeline parameters

- Updated BriaFiboAttnProcessor and BriaFiboAttention classes to reflect changes from Flux equivalents.
- Modified the _unpack_latents method in BriaFiboPipeline to improve clarity.
- Increased the default max_sequence_length to 3000 and added a new optional parameter do_patching.
- Cleaned up test_pipeline_bria_fibo.py by removing unused imports and skipping unsupported tests.

* edit the docs of FIBO

* Remove unused BriaFibo imports and update CPU offload method in BriaFiboPipeline

* Refactor FIBO classes to BriaFibo naming convention

- Updated class names from FIBO to BriaFibo for consistency across the module.
- Modified instances of FIBOEmbedND, FIBOTimesteps, TextProjection, and TimestepProjEmbeddings to reflect the new naming.
- Ensured all references in the BriaFiboTransformer2DModel are updated accordingly.

* Add BriaFiboTransformer2DModel import to transformers module

* Remove unused BriaFibo imports from modular pipelines and add BriaFiboTransformer2DModel and BriaFiboPipeline classes to dummy objects for enhanced compatibility with torch and transformers.

* Update BriaFibo classes with copied documentation and fix import typo in pipeline module

- Added documentation comments indicating the source of copied code in BriaFiboTransformerBlock and _pack_latents methods.
- Corrected the import statement for BriaFiboPipeline in the pipelines module.

* Remove unused BriaFibo imports from __init__.py to streamline modular pipelines.

* Refactor documentation comments in BriaFibo classes to indicate inspiration from existing implementations

- Updated comments in BriaFiboAttnProcessor, BriaFiboAttention, and BriaFiboPipeline to reflect that the code is inspired by other modules rather than copied.
- Enhanced clarity on the origins of the methods to maintain proper attribution.

* change Inspired by to Based on

* add reference link and fix trailing whitespace

* Add BriaFiboTransformer2DModel documentation and update comments in BriaFibo classes

- Introduced a new documentation file for BriaFiboTransformer2DModel.
- Updated comments in BriaFiboAttnProcessor, BriaFiboAttention, and BriaFiboPipeline to clarify the origins of the code, indicating copied sources for better attribution.

---------
Co-authored-by: default avatarsayakpaul <spsayakpaul@gmail.com>
      84e16575
    • Sayak Paul's avatar
      [ci] don't run sana layerwise casting tests in CI. (#12551) · 55d49d43
      Sayak Paul authored 
      * don't run sana layerwise casting tests in CI.

* up
      55d49d43
    • Meatfucker's avatar
      Fix typos in kandinsky5 docs (#12552) · 40528e9a
      Meatfucker authored 
      Update kandinsky5.md

Fix typos
      40528e9a
    • Wang, Yi's avatar
      fix crash if tiling mode is enabled (#12521) · dc622a95
      Wang, Yi authored 
      

* fix crash in tiling mode is enabled
Signed-off-by: default avatarWang, Yi A <yi.a.wang@intel.com>

* fmt
Signed-off-by: default avatarWang, Yi A <yi.a.wang@intel.com>

---------
Signed-off-by: default avatarWang, Yi A <yi.a.wang@intel.com>
Co-authored-by: default avatarSayak Paul <spsayakpaul@gmail.com>
      dc622a95
    • Dhruv Nair's avatar
      [Pipelines] Enable Wan VACE to run since single transformer (#12428) · ecfbc8f9
      Dhruv Nair authored 
      * update

* update

* update

* update

* update
      ecfbc8f9
    • Sayak Paul's avatar
      support latest few-step wan LoRA. (#12541) · df0e2a4f
      Sayak Paul authored 
      * support latest few-step wan LoRA.

* up

* up
      df0e2a4f