* 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>
* Initial LTX 2.0 transformer implementation
* Add tests for LTX 2 transformer model
* Get LTX 2 transformer tests working
* Rename LTX 2 compile test class to have LTX2
* Remove RoPE debug print statements
* Get LTX 2 transformer compile tests passing
* Fix LTX 2 transformer shape errors
* Initial script to convert LTX 2 transformer to diffusers
* Add more LTX 2 transformer audio arguments
* Allow LTX 2 transformer to be loaded from local path for conversion
* Improve dummy inputs and add test for LTX 2 transformer consistency
* Fix LTX 2 transformer bugs so consistency test passes
* Initial implementation of LTX 2.0 video VAE
* Explicitly specify temporal and spatial VAE scale factors when converting
* Add initial LTX 2.0 video VAE tests
* Add initial LTX 2.0 video VAE tests (part 2)
* Get diffusers implementation on par with official LTX 2.0 video VAE implementation
* Initial LTX 2.0 vocoder implementation
* Use RMSNorm implementation closer to original for LTX 2.0 video VAE
* start audio decoder.
* init registration.
* up
* simplify and clean up
* up
* Initial LTX 2.0 text encoder implementation
* Rough initial LTX 2.0 pipeline implementation
* up
* up
* up
* up
* Add imports for LTX 2.0 Audio VAE
* Conversion script for LTX 2.0 Audio VAE Decoder
* Add Audio VAE logic to T2V pipeline
* Duplicate scheduler for audio latents
* Support num_videos_per_prompt for prompt embeddings
* LTX 2.0 scheduler and full pipeline conversion
* Add script to test full LTX2Pipeline T2V inference
* Fix pipeline return bugs
* Add LTX 2 text encoder and vocoder to ltx2 subdirectory __init__
* Fix more bugs in LTX2Pipeline.__call__
* Improve CPU offload support
* Fix pipeline audio VAE decoding dtype bug
* Fix video shape error in full pipeline test script
* Get LTX 2 T2V pipeline to produce reasonable outputs
* Make LTX 2.0 scheduler more consistent with original code
* Fix typo when applying scheduler fix in T2V inference script
* Refactor Audio VAE to be simpler and remove helpers (#7)
* remove resolve causality axes stuff.
* remove a bunch of helpers.
* remove adjust output shape helper.
* remove the use of audiolatentshape.
* move normalization and patchify out of pipeline.
* fix
* up
* up
* Remove unpatchify and patchify ops before audio latents denormalization (#9)
---------
Co-authored-by: dg845 <58458699+dg845@users.noreply.github.com>
* Add support for I2V (#8)
* start i2v.
* up
* up
* up
* up
* up
* remove uniform strategy code.
* remove unneeded code.
* Denormalize audio latents in I2V pipeline (analogous to T2V change) (#11)
* test i2v.
* Move Video and Audio Text Encoder Connectors to Transformer (#12)
* Denormalize audio latents in I2V pipeline (analogous to T2V change)
* Initial refactor to put video and audio text encoder connectors in transformer
* Get LTX 2 transformer tests working after connector refactor
* precompute run_connectors,.
* fixes
* Address review comments
* Calculate RoPE double precisions freqs using torch instead of np
* Further simplify LTX 2 RoPE freq calc
* Make connectors a separate module (#18)
* remove text_encoder.py
* address yiyi's comments.
* up
* up
* up
* up
---------
Co-authored-by: sayakpaul <spsayakpaul@gmail.com>
* up (#19)
* address initial feedback from lightricks team (#16)
* cross_attn_timestep_scale_multiplier to 1000
* implement split rope type.
* up
* propagate rope_type to rope embed classes as well.
* up
* When using split RoPE, make sure that the output dtype is same as input dtype
* Fix apply split RoPE shape error when reshaping x to 4D
* Add export_utils file for exporting LTX 2.0 videos with audio
* Tests for T2V and I2V (#6)
* add ltx2 pipeline tests.
* up
* up
* up
* up
* remove content
* style
* Denormalize audio latents in I2V pipeline (analogous to T2V change)
* Initial refactor to put video and audio text encoder connectors in transformer
* Get LTX 2 transformer tests working after connector refactor
* up
* up
* i2v tests.
* up
* Address review comments
* Calculate RoPE double precisions freqs using torch instead of np
* Further simplify LTX 2 RoPE freq calc
* revert unneded changes.
* up
* up
* update to split style rope.
* up
---------
Co-authored-by: Daniel Gu <dgu8957@gmail.com>
* up
* use export util funcs.
* Point original checkpoint to LTX 2.0 official checkpoint
* Allow the I2V pipeline to accept image URLs
* make style and make quality
* remove function map.
* remove args.
* update docs.
* update doc entries.
* disable ltx2_consistency test
* Simplify LTX 2 RoPE forward by removing coords is None logic
* make style and make quality
* Support LTX 2.0 audio VAE encoder
* Apply suggestions from code review
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
* Remove print statement in audio VAE
* up
* Fix bug when calculating audio RoPE coords
* Ltx 2 latent upsample pipeline (#12922)
* Initial implementation of LTX 2.0 latent upsampling pipeline
* Add new LTX 2.0 spatial latent upsampler logic
* Add test script for LTX 2.0 latent upsampling
* Add option to enable VAE tiling in upsampling test script
* Get latent upsampler working with video latents
* Fix typo in BlurDownsample
* Add latent upsample pipeline docstring and example
* Remove deprecated pipeline VAE slicing/tiling methods
* make style and make quality
* When returning latents, return unpacked and denormalized latents for T2V and I2V
* Add model_cpu_offload_seq for latent upsampling pipeline
---------
Co-authored-by: Daniel Gu <dgu8957@gmail.com>
* Fix latent upsampler filename in LTX 2 conversion script
* Add latent upsample pipeline to LTX 2 docs
* Add dummy objects for LTX 2 latent upsample pipeline
* Set default FPS to official LTX 2 ckpt default of 24.0
* Set default CFG scale to official LTX 2 ckpt default of 4.0
* Update LTX 2 pipeline example docstrings
* make style and make quality
* Remove LTX 2 test scripts
* Fix LTX 2 upsample pipeline example docstring
* Add logic to convert and save a LTX 2 upsampling pipeline
* Document LTX2VideoTransformer3DModel forward pass
---------
Co-authored-by: sayakpaul <spsayakpaul@gmail.com>
* fix: group offloading to support standalone computational layers in block-level offloading
* test: for models with standalone and deeply nested layers in block-level offloading
* feat: support for block-level offloading in group offloading config
* fix: group offload block modules to AutoencoderKL and AutoencoderKLWan
* fix: update group offloading tests to use AutoencoderKL and adjust input dimensions
* refactor: streamline block offloading logic
* Apply style fixes
* update tests
* update
* fix for failing tests
* clean up
* revert to use skip_keys
* clean up
---------
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>
* start zimage model tests.
* up
* up
* up
* up
* up
* up
* up
* up
* up
* up
* up
* up
* Revert "up"
This reverts commit bca3e27c96.
* expand upon compilation failure reason.
* Update tests/models/transformers/test_models_transformer_z_image.py
Co-authored-by: dg845 <58458699+dg845@users.noreply.github.com>
* reinitialize the padding tokens to ones to prevent NaN problems.
* updates
* up
* skipping ZImage DiT tests
* up
* up
---------
Co-authored-by: dg845 <58458699+dg845@users.noreply.github.com>
* Fixes#12673.
Wrong default_stream is used. leading to wrong execution order when record_steram is enabled.
* update
* Update test
---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.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>
* 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>
* rename photon to prx
* rename photon into prx
* Revert .gitignore to state before commit b7fb0fe9d6
* rename photon to prx
* rename photon into prx
* Revert .gitignore to state before commit b7fb0fe9d6
* make fix-copies
* 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: Steven Liu <59462357+stevhliu@users.noreply.github.com>
* Update docs/source/en/api/pipelines/photon.md
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
* Update docs/source/en/api/pipelines/photon.md
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
* use dispatch_attention_fn for multiple attention backend support
* naming changes
* make fix copy
* 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: dg845 <58458699+dg845@users.noreply.github.com>
* restrict the version of transformers
Co-authored-by: dg845 <58458699+dg845@users.noreply.github.com>
* Update tests/pipelines/photon/test_pipeline_photon.py
Co-authored-by: dg845 <58458699+dg845@users.noreply.github.com>
* Update tests/pipelines/photon/test_pipeline_photon.py
Co-authored-by: dg845 <58458699+dg845@users.noreply.github.com>
* change | for Optional
* fix nits.
* use typing Dict
---------
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: Steven Liu <59462357+stevhliu@users.noreply.github.com>
Co-authored-by: dg845 <58458699+dg845@users.noreply.github.com>
Co-authored-by: sayakpaul <spsayakpaul@gmail.com>
I noticed that the test should be for the option check_compiled="ignore"
but it was using check_compiled="warn". This has been fixed, now the
correct argument is passed.
However, the fact that the test passed means that it was incorrect to
begin with. The way that logs are collected does not collect the
logger.warning call here (not sure why). To amend this, I'm now using
assertNoLogs. With this change, the test correctly fails when the wrong
argument is passed.
* 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: Aryan <contact.aryanvs@gmail.com>
