* Fix QwenImage txt_seq_lens handling
* formatting
* formatting
* remove txt_seq_lens and use bool mask
* use compute_text_seq_len_from_mask
* add seq_lens to dispatch_attention_fn
* use joint_seq_lens
* remove unused index_block
* WIP: Remove seq_lens parameter and use mask-based approach
- Remove seq_lens parameter from dispatch_attention_fn
- Update varlen backends to extract seqlens from masks
- Update QwenImage to pass 2D joint_attention_mask
- Fix native backend to handle 2D boolean masks
- Fix sage_varlen seqlens_q to match seqlens_k for self-attention
Note: sage_varlen still producing black images, needs further investigation
* fix formatting
* undo sage changes
* xformers support
* hub fix
* fix torch compile issues
* fix tests
* use _prepare_attn_mask_native
* proper deprecation notice
* add deprecate to txt_seq_lens
* Update src/diffusers/models/transformers/transformer_qwenimage.py
Co-authored-by: YiYi Xu <yixu310@gmail.com>
* Update src/diffusers/models/transformers/transformer_qwenimage.py
Co-authored-by: YiYi Xu <yixu310@gmail.com>
* Only create the mask if there's actual padding
* fix order of docstrings
* Adds performance benchmarks and optimization details for QwenImage
Enhances documentation with comprehensive performance insights for QwenImage pipeline:
* rope_text_seq_len = text_seq_len
* rename to max_txt_seq_len
* removed deprecated args
* undo unrelated change
* Updates QwenImage performance documentation
Removes detailed attention backend benchmarks and simplifies torch.compile performance description
Focuses on key performance improvement with torch.compile, highlighting the specific speedup from 4.70s to 1.93s on an A100 GPU
Streamlines the documentation to provide more concise and actionable performance insights
* Updates deprecation warnings for txt_seq_lens parameter
Extends deprecation timeline for txt_seq_lens from version 0.37.0 to 0.39.0 across multiple Qwen image-related models
Adds a new unit test to verify the deprecation warning behavior for the txt_seq_lens parameter
* fix compile
* formatting
* fix compile tests
* rename helper
* remove duplicate
* smaller values
* removed
* use torch.cond for torch compile
* Construct joint attention mask once
* test different backends
* construct joint attention mask once to avoid reconstructing in every block
* Update src/diffusers/models/attention_dispatch.py
Co-authored-by: YiYi Xu <yixu310@gmail.com>
* formatting
* raising an error from the EditPlus pipeline when batch_size > 1
---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: YiYi Xu <yixu310@gmail.com>
Co-authored-by: cdutr <dutra_carlos@hotmail.com>
* add vae
* Initial commit for Flux 2 Transformer implementation
* add pipeline part
* small edits to the pipeline and conversion
* update conversion script
* fix
* up up
* finish pipeline
* Remove Flux IP Adapter logic for now
* Remove deprecated 3D id logic
* Remove ControlNet logic for now
* Add link to ViT-22B paper as reference for parallel transformer blocks such as the Flux 2 single stream block
* update pipeline
* Don't use biases for input projs and output AdaNorm
* up
* Remove bias for double stream block text QKV projections
* Add script to convert Flux 2 transformer to diffusers
* make style and make quality
* fix a few things.
* allow sft files to go.
* fix image processor
* fix batch
* style a bit
* Fix some bugs in Flux 2 transformer implementation
* Fix dummy input preparation and fix some test bugs
* fix dtype casting in timestep guidance module.
* resolve conflicts.,
* remove ip adapter stuff.
* Fix Flux 2 transformer consistency test
* Fix bug in Flux2TransformerBlock (double stream block)
* Get remaining Flux 2 transformer tests passing
* make style; make quality; make fix-copies
* remove stuff.
* fix type annotaton.
* remove unneeded stuff from tests
* tests
* up
* up
* add sf support
* Remove unused IP Adapter and ControlNet logic from transformer (#9)
* copied from
* Apply suggestions from code review
Co-authored-by: YiYi Xu <yixu310@gmail.com>
Co-authored-by: apolinário <joaopaulo.passos@gmail.com>
* up
* up
* up
* up
* up
* Refactor Flux2Attention into separate classes for double stream and single stream attention
* Add _supports_qkv_fusion to AttentionModuleMixin to allow subclasses to disable QKV fusion
* Have Flux2ParallelSelfAttention inherit from AttentionModuleMixin with _supports_qkv_fusion=False
* Log debug message when calling fuse_projections on a AttentionModuleMixin subclass that does not support QKV fusion
* Address review comments
* Update src/diffusers/pipelines/flux2/pipeline_flux2.py
Co-authored-by: YiYi Xu <yixu310@gmail.com>
* up
* Remove maybe_allow_in_graph decorators for Flux 2 transformer blocks (#12)
* up
* support ostris loras. (#13)
* up
* update schdule
* up
* up (#17)
* add training scripts (#16)
* add training scripts
Co-authored-by: Linoy Tsaban <linoytsaban@gmail.com>
* model cpu offload in validation.
* add flux.2 readme
* add img2img and tests
* cpu offload in log validation
* Apply suggestions from code review
* fix
* up
* fixes
* remove i2i training tests for now.
---------
Co-authored-by: Linoy Tsaban <linoytsaban@gmail.com>
Co-authored-by: linoytsaban <linoy@huggingface.co>
* up
---------
Co-authored-by: yiyixuxu <yixu310@gmail.com>
Co-authored-by: Daniel Gu <dgu8957@gmail.com>
Co-authored-by: yiyi@huggingface.co <yiyi@ip-10-53-87-203.ec2.internal>
Co-authored-by: dg845 <58458699+dg845@users.noreply.github.com>
Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>
Co-authored-by: apolinário <joaopaulo.passos@gmail.com>
Co-authored-by: yiyi@huggingface.co <yiyi@ip-26-0-160-103.ec2.internal>
Co-authored-by: Linoy Tsaban <linoytsaban@gmail.com>
Co-authored-by: linoytsaban <linoy@huggingface.co>
* fix bug when offload and cache_latents both enabled
* fix bug when offload and cache_latents both enabled
* fix bug when offload and cache_latents both enabled
* fix bug when offload and cache_latents both enabled
* fix bug when offload and cache_latents both enabled
* fix bug when offload and cache_latents both enabled
* fix bug when offload and cache_latents both enabled
* fix bug when offload and cache_latents both enabled
* fix bug when offload and cache_latents both enabled
* 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>
* 1. add pre-computation of prompt embeddings when custom prompts are used as well
2. save model card even if model is not pushed to hub
3. remove scheduler initialization from code example - not necessary anymore (it's now if the base model's config)
4. add skip_final_inference - to allow to run with validation, but skip the final loading of the pipeline with the lora weights to reduce memory reqs
* pre encode validation prompt as well
* Update examples/dreambooth/train_dreambooth_lora_hidream.py
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
* Update examples/dreambooth/train_dreambooth_lora_hidream.py
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
* Update examples/dreambooth/train_dreambooth_lora_hidream.py
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
* pre encode validation prompt as well
* Apply style fixes
* empty commit
* change default trained modules
* empty commit
* address comments + change encoding of validation prompt (before it was only pre-encoded if custom prompts are provided, but should be pre-encoded either way)
* Apply style fixes
* empty commit
* fix validation_embeddings definition
* fix final inference condition
* fix pipeline deletion in last inference
* Apply style fixes
* empty commit
* layers
* remove readme remarks on only pre-computing when instance prompt is provided and change example to 3d icons
* smol fix
* empty commit
---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
