- 30 Oct, 2025 1 commit
-
-
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 4 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:sayakpaul <spsayakpaul@gmail.com>
-
Wang, Yi authored
* fix crash in tiling mode is enabled Signed-off-by:
Wang, Yi A <yi.a.wang@intel.com> * fmt Signed-off-by:
-
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:
YiYi Xu <yixu310@gmail.com> * remove no_grad and simplified prompt paddings * 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:
github-actions[bot] <github-actions[bot]@users.noreply.github.com>
-
- 27 Oct, 2025 2 commits
-
-
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>
-
- 24 Oct, 2025 1 commit
-
-
YiYi Xu authored
* add hunyuanimage2.1 --------- Co-authored-by:
-
- 23 Oct, 2025 1 commit
-
-
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:
-
- 22 Oct, 2025 3 commits
-
-
YiYi Xu authored
add
-
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:
dg845 <58458699+dg845@users.noreply.github.com> * Add PhotonTransformer2DModel to TYPE_CHECKING imports * make fix-copies * Use Tuple instead of tuple 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:
-
- 20 Oct, 2025 1 commit
-
-
dg845 authored
Refactor QwenEmbedRope to only use the LRU cache for RoPE caching
-
- 18 Oct, 2025 1 commit
-
-
Lev Novitskiy authored
* add kandinsky5 transformer pipeline first version --------- Co-authored-by:
-
- 17 Oct, 2025 1 commit
-
-
Ali Imran authored
* cleanup of runway model * quality fixes
-
- 15 Oct, 2025 1 commit
-
-
Sayak Paul authored
-
- 05 Oct, 2025 1 commit
-
-
Vladimir Mandic authored
* wan fix scale_shift_factor being on cpu * apply device cast to ltx transformer * Apply style fixes --------- Co-authored-by:
-
- 02 Oct, 2025 1 commit
-
-
Sayak Paul authored
conditionally import torch distributed stuff.
-
- 30 Sep, 2025 1 commit
-
-
Steven Liu authored
* change syntax * make style
-
- 25 Sep, 2025 1 commit
-
-
Lucain authored
* Support huggingface_hub 0.x and 1.x * httpx
-
- 24 Sep, 2025 2 commits
-
-
Aryan authored
* update * update * add coauthor Co-Authored-By:
Aryan <aryan@huggingface.co> * up --------- Co-authored-by:
-
Dhruv Nair authored
* update * update * update
-
- 23 Sep, 2025 1 commit
-
-
Dhruv Nair authored
* update * update
-
- 22 Sep, 2025 2 commits
-
-
SahilCarterr authored
* FIxes enable_xformers_memory_efficient_attention() * Update attention.py
-
Chen Mingyi authored
-
- 17 Sep, 2025 1 commit
-
-
DefTruth authored
* fix hidream type hint * fix hunyuan-video type hint * fix many type hint * fix many type hint errors * fix many type hint errors * fix many type hint errors * make stype & make quality
-
- 16 Sep, 2025 2 commits
-
-
Zijian Zhou authored
* Update autoencoder_kl_wan.py When using the Wan2.2 VAE, the spatial compression ratio calculated here is incorrect. It should be 16 instead of 8. Pass it in directly via the config to ensure it’s correct here. * Update autoencoder_kl_wan.py
-
Samarth Agrawal authored
* fixed bug in defining embed dim * matched 1d temb process to 2d * Update src/diffusers/models/unets/unet_1d.py Co-authored-by:
-
- 03 Sep, 2025 2 commits
-
-
Ju Hoon Park authored
* Add AttentionMixin to WanVACETransformer3DModel to enable methods like `set_attn_processor()`. * Import AttentionMixin in transformer_wan_vace.py Special thanks to @tolgacangoz
🙇 ♂️ -
Sayak Paul authored
* feat: try loading fa3 using kernels when available. * up * change to Hub. * up * up * up * switch env var. * up * up * up * up * up * up
-
- 30 Aug, 2025 1 commit
-
-
Leo Jiang authored
Co-authored-by:
J石页 <jiangshuo9@h-partners.com> Co-authored-by:
-
- 26 Aug, 2025 3 commits
-
-
Sayak Paul authored
* start removing flax stuff. * add deprecation warning. * add warning messages. * more warnings. * remove dockerfiles. * remove more. * Update src/diffusers/models/attention_flax.py Co-authored-by:
-
Tolga Cangöz authored
* fix: update SkyReels-V2 documentation and moving into attn dispatcher * Refactors SkyReelsV2's attention implementation * style * up * Fixes formatting in SkyReels-V2 documentation Wraps the visual demonstration section in a Markdown code block. This change corrects the rendering of ASCII diagrams and examples, improving the overall readability of the document. * Docs: Condense example arrays in skyreels_v2 guide Improves the readability of the `step_matrix` examples by replacing long sequences of repeated numbers with a more compact `value×count` notation. This change makes the underlying data patterns in the examples easier to understand at a glance. * Add _repeated_blocks attribute to SkyReelsV2Transformer3DModel * Refactor rotary embedding calculations in SkyReelsV2 to separate cosine and sine frequencies * Enhance SkyReels-V2 documentation: update model loading for GPU support and remove outdated notes * up * up * Update model_id in SkyReels-V2 documentation * up * refactor: remove device_map parameter for model loading and add pipeline.to("cuda") for GPU allocation * fix: update copyright year to 2025 in skyreels_v2.md * docs: enhance parameter examples and formatting in skyreels_v2.md * docs: update example formatting and add notes on LoRA support in skyreels_v2.md * refactor: remove copied comments from transformer_wan in SkyReelsV2 classes * Clean up comments in skyreels_v2.md Removed comments about acceleration helpers and Flash Attention installation. * Add deprecation warning for `SkyReelsV2AttnProcessor2_0` class -
Leo Jiang authored
* NPU attention refactor for FLUX transformer * Apply style fixes --------- Co-authored-by:
-
- 23 Aug, 2025 1 commit
-
-
Aishwarya Badlani authored
* Fix PyTorch 2.3.1 compatibility: add version guard for torch.library.custom_op - Add hasattr() check for torch.library.custom_op and register_fake - These functions were added in PyTorch 2.4, causing import failures in 2.3.1 - Both decorators and functions are now properly guarded with version checks - Maintains backward compatibility while preserving functionality Fixes #12195 * Use dummy decorators approach for PyTorch version compatibility - Replace hasattr check with version string comparison - Add no-op decorator functions for PyTorch < 2.4.0 - Follows pattern from #11941 as suggested by reviewer - Maintains cleaner code structure without indentation changes * Update src/diffusers/models/attention_dispatch.py Update all the decorator usages Co-authored-by:
Aryan <contact.aryanvs@gmail.com> * Update src/diffusers/models/attention_dispatch.py Co-authored-by:
-
- 22 Aug, 2025 2 commits
-
-
Sayak Paul authored
-
Frank (Haofan) Wang authored
* support qwen-image-cn-union --------- Co-authored-by:
-
- 20 Aug, 2025 2 commits
-
-
Sayak Paul authored
remove extra validation check in determine_device_map
-
galbria authored
* Add Bria model and pipeline to diffusers - Introduced `BriaTransformer2DModel` and `BriaPipeline` for enhanced image generation capabilities. - Updated import structures across various modules to include the new Bria components. - Added utility functions and output classes specific to the Bria pipeline. - Implemented tests for the Bria pipeline to ensure functionality and output integrity. * with working tests * style and quality pass * adding docs * add to overview * fixes from "make fix-copies" * Refactor transformer_bria.py and pipeline_bria.py: Introduce new EmbedND class for rotary position embedding, and enhance Timestep and TimestepProjEmbeddings classes. Add utility functions for handling negative prompts and generating original sigmas in pipeline_bria.py. * remove redundent and duplicates tests and fix bf16 slow test * style fixes * small doc update * Enhance Bria 3.2 documentation and implementation - Updated the GitHub repository link for Bria 3.2. - Added usage instructions for the gated model access. - Introduced the BriaTransformerBlock and BriaAttention classes to the model architecture. - Refactored existing classes to integrate Bria-specific components, including BriaEmbedND and BriaPipeline. - Updated the pipeline output class to reflect Bria-specific functionality. - Adjusted test cases to align with the new Bria model structure. * Refactor Bria model components and update documentation - Removed outdated inference example from Bria 3.2 documentation. - Introduced the BriaTransformerBlock class to enhance model architecture. - Updated attention handling to use `attention_kwargs` instead of `joint_attention_kwargs`. - Improved import structure in the Bria pipeline to handle optional dependencies. - Adjusted test cases to reflect changes in model dtype assertions. * Update Bria model reference in documentation to reflect new file naming convention * Update docs/source/en/_toctree.yml * Refactor BriaPipeline to inherit from DiffusionPipeline instead of FluxPipeline, updating imports accordingly. * move the __call__ func to the end of file * Update BriaPipeline example to use bfloat16 for precision sensitivity for better result * make style && make quality && make fix-copiessource --------- Co-authored-by:
Linoy Tsaban <57615435+linoytsaban@users.noreply.github.com> Co-authored-by:
-
