- 10 Nov, 2025 4 commits
-
-
Cesaryuan authored
Fix: update type hints for Tuple parameters across multiple files to support variable-length tuples (#12544) * Fix: update type hints for Tuple parameters across multiple files to support variable-length tuples * Apply style fixes --------- Co-authored-by:github-actions[bot] <github-actions[bot]@users.noreply.github.com>
-
Dhruv Nair authored
* update * update * update * update * update * update * update * update * update * update * update * update --------- Co-authored-by:Sayak Paul <spsayakpaul@gmail.com>
-
YiYi Xu authored
* update, remove intermediaate_inputs * support image2video * revert dynamic steps to simplify * refactor vae encoder block * support flf2video! * add support for wan2.2 14B * style * Apply suggestions from code review * input dynamic step -> additiional input step * up * fix init * update dtype
-
Jay Wu authored
* add ChronoEdit * add ref to original function & remove wan2.2 logics * Update src/diffusers/pipelines/chronoedit/pipeline_chronoedit.py Co-authored-by:
YiYi Xu <yixu310@gmail.com> * Update src/diffusers/pipelines/chronoedit/pipeline_chronoedit.py Co-authored-by:
wjay <wjay@nvidia.com> Co-authored-by:
-
- 07 Nov, 2025 2 commits
-
-
Wang, Yi authored
* fix the crash in Wan-AI/Wan2.2-TI2V-5B-Diffusers if CP is enabled Signed-off-by:
Wang, Yi <yi.a.wang@intel.com> * address review comment Signed-off-by:
-
DefTruth authored
* feat: enable attention dispatch for huanyuan video * feat: enable attention dispatch for huanyuan video
-
- 06 Nov, 2025 3 commits
-
-
Mohammad Sadegh Salehi authored
* Fix overflow in rgblike_to_depthmap by safe dtype casting (torch & NumPy) * Fix: store original dtype and cast back after safe computation * Apply style fixes --------- Co-authored-by: -
Junsong Chen authored
* 1. add `SanaVideoTransformer3DModel` in transformer_sana_video.py 2. add `SanaVideoPipeline` in pipeline_sana_video.py 3. add all code we need for import `SanaVideoPipeline` * add a sample about how to use sana-video; * code update; * update hf model path; * update code; * sana-video can run now; * 1. add aspect ratio in sana-video-pipeline; 2. add reshape function in sana-video-processor; 3. fix convert pth to safetensor bugs; * default to use `use_resolution_binning`; * make style; * remove unused code; * Update src/diffusers/models/transformers/transformer_sana_video.py Co-authored-by:
dg845 <58458699+dg845@users.noreply.github.com> * Update src/diffusers/models/transformers/transformer_sana_video.py Co-authored-by:
-
Dhruv Nair authored
* update * update * update * update --------- Co-authored-by:
-
- 04 Nov, 2025 1 commit
-
-
Linoy Tsaban authored
* fix bug when offload and cache_latents both enabled * fix
-
- 03 Nov, 2025 2 commits
-
-
Wang, Yi authored
* ulysses enabling in native attention path Signed-off-by:
-
YiYi Xu authored
pass hub_kwargs to load_config
-
- 02 Nov, 2025 3 commits
-
-
Sayak Paul authored
* start flux modular tests. * up * add kontext * up * up * up * Update src/diffusers/modular_pipelines/flux/denoise.py Co-authored-by:
-
YiYi Xu authored
better warn message
-
Dhruv Nair authored
update
-
- 31 Oct, 2025 2 commits
-
-
Friedrich Schöller authored
-
Dhruv Nair authored
update Co-authored-by:
-
- 30 Oct, 2025 2 commits
-
-
Dhruv Nair authored
update
-
Pavle Padjin authored
* Changing the way we infer dtype to avoid force evaluation of lazy tensors * changing way to infer dtype to ensure type consistency * more robust infering of dtype * removing the upscale dtype entirely
-
- 28 Oct, 2025 6 commits
-
-
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: -
Wang, Yi authored
* fix crash in tiling mode is enabled Signed-off-by:
-
Dhruv Nair authored
* update * update * update * update * update
-
Sayak Paul authored
* support latest few-step wan LoRA. * up * up
-
G.O.D authored
improve pos embed for ascend npu Co-authored-by:felix01.yu <felix01.yu@vipshop.com>
-
Lev Novitskiy authored
* add transformer pipeline first version * updates * fix 5sec generation * rewrite Kandinsky5T2VPipeline to diffusers style * add multiprompt support * remove prints in pipeline * add nabla attention * Wrap Transformer in Diffusers style * fix license * fix prompt type * add gradient checkpointing and peft support * add usage example * Update src/diffusers/pipelines/kandinsky5/pipeline_kandinsky.py Co-authored-by:
Álvaro Somoza <asomoza@users.noreply.github.com> * Update src/diffusers/pipelines/kandinsky5/pipeline_kandinsky.py Co-authored-by:
Charles <charles@huggingface.co> * more * Apply suggestions from code review * add lora loader doc * add compiled Nabla Attention * all needed changes for 10 sec models are added! * add docs * Apply style fixes * update docs * add kandinsky5 to toctree * add tests * fix tests * Apply style fixes * update tests --------- Co-authored-by:
-
- 27 Oct, 2025 3 commits
-
-
alirezafarashah authored
Fix small inconsistency in output dimension of "_get_t5_prompt_embeds" function in sd3 pipeline (#12531) * Fix small inconsistency in output dimension of t5 embeds when text_encoder_3 is None * first commit --------- Co-authored-by:
Alireza Farashah <alireza.farashah@cn-g017.server.mila.quebec> Co-authored-by:
Alireza Farashah <alireza.farashah@login-2.server.mila.quebec>
-
Mikko Lauri authored
* add aiter attention backend * Apply style fixes --------- Co-authored-by:
-
josephrocca authored
* [Fix] Move attention mask padding after T5 embedding * [Fix] Move attention mask padding after T5 embedding * Clean up whitespace in pipeline_chroma.py Removed unnecessary blank lines for cleaner code. * Fix * Fix * Update model to final Chroma1-HD checkpoint * Update to Chroma1-HD * Update model to Chroma1-HD * Update model to Chroma1-HD * Update Chroma model links to Chroma1-HD * Add comment about padding/masking * Fix checkpoint/repo references * Apply style fixes --------- Co-authored-by:
Dhruv Nair <dhruv.nair@gmail.com>
-
- 26 Oct, 2025 1 commit
-
-
Sayak Paul authored
* move guiders experimental warning to init. * up
-
- 24 Oct, 2025 3 commits
-
-
Dhruv Nair authored
* update * update --------- Co-authored-by: -
YiYi Xu authored
* add hunyuanimage2.1 --------- Co-authored-by: -
Sayak Paul authored
-
- 23 Oct, 2025 3 commits
-
-
Dhruv Nair authored
* update * update * update
-
Aishwarya Badlani authored
* Fix MPS compatibility in get_1d_sincos_pos_embed_from_grid #12432 * Fix trailing whitespace in docstring * Apply style fixes --------- Co-authored-by:
-
kaixuanliu authored
* fix CI bug for kandinsky3_img2img case Signed-off-by:
Liu, Kaixuan <kaixuan.liu@intel.com> * update code Signed-off-by:
-
- 22 Oct, 2025 4 commits
-
-
YiYi Xu authored
add
-
Álvaro Somoza authored
fix
-
Sayak Paul authored
* up * correct wording. * up * up * up
-
David Bertoin authored
* rename photon to prx * rename photon into prx * Revert .gitignore to state before commit b7fb0fe9d63bf766bbe3c42ac154a043796dd370 * rename photon to prx * rename photon into prx * Revert .gitignore to state before commit b7fb0fe9d63bf766bbe3c42ac154a043796dd370 * make fix-copies
-
- 21 Oct, 2025 1 commit
-
-
David Bertoin authored
* Add Photon model and pipeline support This commit adds support for the Photon image generation model: - PhotonTransformer2DModel: Core transformer architecture - PhotonPipeline: Text-to-image generation pipeline - Attention processor updates for Photon-specific attention mechanism - Conversion script for loading Photon checkpoints - Documentation and tests * just store the T5Gemma encoder * enhance_vae_properties if vae is provided only * remove autocast for text encoder forwad * BF16 example * conditioned CFG * remove enhance vae and use vae.config directly when possible * move PhotonAttnProcessor2_0 in transformer_photon * remove einops dependency and now inherits from AttentionMixin * unify the structure of the forward block * update doc * update doc * fix T5Gemma loading from hub * fix timestep shift * remove lora support from doc * Rename EmbedND for PhotoEmbedND * remove modulation dataclass * put _attn_forward and _ffn_forward logic in PhotonBlock's forward * renam LastLayer for FinalLayer * remove lora related code * rename vae_spatial_compression_ratio for vae_scale_factor * support prompt_embeds in call * move xattention conditionning out computation out of the denoising loop * add negative prompts * Use _import_structure for lazy loading * make quality + style * add pipeline test + corresponding fixes * utility function that determines the default resolution given the VAE * Refactor PhotonAttention to match Flux pattern * built-in RMSNorm * Revert accidental .gitignore change * parameter names match the standard diffusers conventions * renaming and remove unecessary attributes setting * Update docs/source/en/api/pipelines/photon.md Co-authored-by:
Steven Liu <59462357+stevhliu@users.noreply.github.com> * quantization example * added doc to toctree * Update docs/source/en/api/pipelines/photon.md Co-authored-by:
davidb <davidb@worker-10.soperator-worker-svc.soperator.svc.cluster.local> Co-authored-by:
David Briand <david@photoroom.com> Co-authored-by:
davidb <davidb@worker-8.soperator-worker-svc.soperator.svc.cluster.local> Co-authored-by:
-
