* 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>
* 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>
* style
* Fix class name casing for SkyReelsV2 components in multiple files to ensure consistency and correct functionality.
* cleaning
* cleansing
* Refactor `get_timestep_embedding` to move modifications into `SkyReelsV2TimeTextImageEmbedding`.
* Remove unnecessary line break in `get_timestep_embedding` function for cleaner code.
* Remove `skyreels_v2` entry from `_import_structure` and update its initialization to directly assign the list of SkyReelsV2 components.
* cleansing
* Refactor attention processing in `SkyReelsV2AttnProcessor2_0` to always convert query, key, and value to `torch.bfloat16`, simplifying the code and improving clarity.
* Enhance example usage in `pipeline_skyreels_v2_diffusion_forcing.py` by adding VAE initialization and detailed prompt for video generation, improving clarity and usability of the documentation.
* Refactor import structure in `__init__.py` for SkyReelsV2 components and improve formatting in `pipeline_skyreels_v2_diffusion_forcing.py` to enhance code readability and maintainability.
* Update `guidance_scale` parameter in `SkyReelsV2DiffusionForcingPipeline` from 5.0 to 6.0 to enhance video generation quality.
* Update `guidance_scale` parameter in example documentation and class definition of `SkyReelsV2DiffusionForcingPipeline` to ensure consistency and improve video generation quality.
* Update `causal_block_size` parameter in `SkyReelsV2DiffusionForcingPipeline` to default to `None`.
* up
* Fix dtype conversion for `timestep_proj` in `SkyReelsV2Transformer3DModel` to *ensure* correct tensor operations.
* Optimize causal mask generation by replacing repeated tensor with `repeat_interleave` for improved efficiency in `SkyReelsV2Transformer3DModel`.
* style
* Enhance example documentation in `SkyReelsV2DiffusionForcingPipeline` with guidance scale and shift parameters for T2V and I2V. Remove unused `retrieve_latents` function to streamline the code.
* Refactor sample scheduler creation in `SkyReelsV2DiffusionForcingPipeline` to use `deepcopy` for improved state management during inference steps.
* Enhance error handling and documentation in `SkyReelsV2DiffusionForcingPipeline` for `overlap_history` and `addnoise_condition` parameters to improve long video generation guidance.
* Update documentation and progress bar handling in `SkyReelsV2DiffusionForcingPipeline` to clarify asynchronous inference settings and improve progress tracking during denoising steps.
* Refine progress bar calculation in `SkyReelsV2DiffusionForcingPipeline` by rounding the step size to one decimal place for improved readability during denoising steps.
* Update import statements in `SkyReelsV2DiffusionForcingPipeline` documentation for improved clarity and organization.
* Refactor progress bar handling in `SkyReelsV2DiffusionForcingPipeline` to use total steps instead of calculated step size.
* update templates for i2v, v2v
* Add `retrieve_latents` function to streamline latent retrieval in `SkyReelsV2DiffusionForcingPipeline`. Update video latent processing to utilize this new function for improved clarity and maintainability.
* Add `retrieve_latents` function to both i2v and v2v pipelines for consistent latent retrieval. Update video latent processing to utilize this function, enhancing clarity and maintainability across the SkyReelsV2DiffusionForcingPipeline implementations.
* Remove redundant ValueError for `overlap_history` in `SkyReelsV2DiffusionForcingPipeline` to streamline error handling and improve user guidance for long video generation.
* Update default video dimensions and flow matching scheduler parameter in `SkyReelsV2DiffusionForcingPipeline` to enhance video generation capabilities.
* Refactor `SkyReelsV2DiffusionForcingPipeline` to support Image-to-Video (i2v) generation. Update class name, add image encoding functionality, and adjust parameters for improved video generation. Enhance error handling for image inputs and update documentation accordingly.
* Improve organization for image-last_image condition.
* Refactor `SkyReelsV2DiffusionForcingImageToVideoPipeline` to improve latent preparation and video condition handling integration.
* style
* style
* Add example usage of PIL for image input in `SkyReelsV2DiffusionForcingImageToVideoPipeline` documentation.
* Refactor `SkyReelsV2DiffusionForcingPipeline` to `SkyReelsV2DiffusionForcingVideoToVideoPipeline`, enhancing support for Video-to-Video (v2v) generation. Introduce video input handling, update latent preparation logic, and improve error handling for input parameters.
* Refactor `SkyReelsV2DiffusionForcingImageToVideoPipeline` by removing the `image_encoder` and `image_processor` dependencies. Update the CPU offload sequence accordingly.
* Refactor `SkyReelsV2DiffusionForcingImageToVideoPipeline` to enhance latent preparation logic and condition handling. Update image input type to `Optional`, streamline video condition processing, and improve handling of `last_image` during latent generation.
* Enhance `SkyReelsV2DiffusionForcingPipeline` by refining latent preparation for long video generation. Introduce new parameters for video handling, overlap history, and causal block size. Update logic to accommodate both short and long video scenarios, ensuring compatibility and improved processing.
* refactor
* fix num_frames
* fix prefix_video_latents
* up
* refactor
* Fix typo in scheduler method call within `SkyReelsV2DiffusionForcingVideoToVideoPipeline` to ensure proper noise scaling during latent generation.
* up
* Enhance `SkyReelsV2DiffusionForcingImageToVideoPipeline` by adding support for `last_image` parameter and refining latent frame calculations. Update preprocessing logic.
* add statistics
* Refine latent frame handling in `SkyReelsV2DiffusionForcingImageToVideoPipeline` by correcting variable names and reintroducing latent mean and standard deviation calculations. Update logic for frame preparation and sampling to ensure accurate video generation.
* up
* refactor
* up
* Refactor `SkyReelsV2DiffusionForcingVideoToVideoPipeline` to improve latent handling by enforcing tensor input for video, updating frame preparation logic, and adjusting default frame count. Enhance preprocessing and postprocessing steps for better integration.
* style
* fix vae output indexing
* upup
* up
* Fix tensor concatenation and repetition logic in `SkyReelsV2DiffusionForcingImageToVideoPipeline` to ensure correct dimensionality for video conditions and latent conditions.
* Refactor latent retrieval logic in `SkyReelsV2DiffusionForcingVideoToVideoPipeline` to handle tensor dimensions more robustly, ensuring compatibility with both 3D and 4D video inputs.
* Enhance logging in `SkyReelsV2DiffusionForcing` pipelines by adding iteration print statements for better debugging. Clean up unused code related to prefix video latents length calculation in `SkyReelsV2DiffusionForcingImageToVideoPipeline`.
* Update latent handling in `SkyReelsV2DiffusionForcingImageToVideoPipeline` to conditionally set latents based on video iteration state, improving flexibility for video input processing.
* Refactor `SkyReelsV2TimeTextImageEmbedding` to utilize `get_1d_sincos_pos_embed_from_grid` for timestep projection.
* Enhance `get_1d_sincos_pos_embed_from_grid` function to include an optional parameter `flip_sin_to_cos` for flipping sine and cosine embeddings, improving flexibility in positional embedding generation.
* Update timestep projection in `SkyReelsV2TimeTextImageEmbedding` to include `flip_sin_to_cos` parameter, enhancing the flexibility of time embedding generation.
* Refactor tensor type handling in `SkyReelsV2AttnProcessor2_0` and `SkyReelsV2TransformerBlock` to ensure consistent use of `torch.float32` and `torch.bfloat16`, improving integration.
* Update tensor type in `SkyReelsV2RotaryPosEmbed` to use `torch.float32` for frequency calculations, ensuring consistency in data types across the model.
* Refactor `SkyReelsV2TimeTextImageEmbedding` to utilize automatic mixed precision for timestep projection.
* down
* down
* style
* Add debug tensor tracking to `SkyReelsV2Transformer3DModel` for enhanced debugging and output analysis; update `Transformer2DModelOutput` to include debug tensors.
* up
* Refactor indentation in `SkyReelsV2AttnProcessor2_0` to improve code readability and maintain consistency in style.
* Convert query, key, and value tensors to bfloat16 in `SkyReelsV2AttnProcessor2_0` for improved performance.
* Add debug print statements in `SkyReelsV2TransformerBlock` to track tensor shapes and values for improved debugging and analysis.
* debug
* debug
* Remove commented-out debug tensor tracking from `SkyReelsV2TransformerBlock`
* Add functionality to save processed video latents as a Safetensors file in `SkyReelsV2DiffusionForcingPipeline`.
* up
* Add functionality to save output latents as a Safetensors file in `SkyReelsV2DiffusionForcingPipeline`.
* up
* Remove additional commented-out debug tensor tracking from `SkyReelsV2TransformerBlock` and `SkyReelsV2Transformer3DModel` for cleaner code.
* style
* cleansing
* Update example documentation and parameters in `SkyReelsV2Pipeline`. Adjusted example code for loading models, modified default values for height, width, num_frames, and guidance_scale, and improved output video quality settings.
* Update shift parameter in example documentation and default values across SkyReels V2 pipelines. Adjusted shift values for I2V from 3.0 to 5.0 and updated related example code for consistency.
* Update example documentation in SkyReels V2 pipelines to include available model options and update model references for loading. Adjusted model names to reflect the latest versions across I2V, V2V, and T2V pipelines.
* Add test templates
* style
* Add docs template
* Add SkyReels V2 Diffusion Forcing Video-to-Video Pipeline to imports
* style
* fix-copies
* convert i2v 1.3b
* Update transformer configuration to include `image_dim` for SkyReels V2 models and refactor imports to use `SkyReelsV2Transformer3DModel`.
* Refactor transformer import in SkyReels V2 pipeline to use `SkyReelsV2Transformer3DModel` for consistency.
* Update transformer configuration in SkyReels V2 to increase `in_channels` from 16 to 36 for i2v conf.
* Update transformer configuration in SkyReels V2 to set `added_kv_proj_dim` values for different model types.
* up
* up
* up
* Add SkyReelsV2Pipeline support for T2V model type in conversion script
* upp
* Refactor model type checks in conversion script to use substring matching for improved flexibility
* upp
* Fix shard path formatting in conversion script to accommodate varying model types by dynamically adjusting zero padding.
* Update sharded safetensors loading logic in conversion script to use substring matching for model directory checks
* Update scheduler parameters in SkyReels V2 test files for consistency across image and video pipelines
* Refactor conversion script to initialize text encoder, tokenizer, and scheduler for SkyReels pipelines, enhancing model integration
* style
* Update documentation for SkyReels-V2, introducing the Infinite-length Film Generative model, enhancing text-to-video generation examples, and updating model references throughout the API documentation.
* Add SkyReelsV2Transformer3DModel and FlowMatchUniPCMultistepScheduler documentation, updating TOC and introducing new model and scheduler files.
* style
* Update documentation for SkyReelsV2DiffusionForcingPipeline to correct flow matching scheduler parameter for I2V from 3.0 to 5.0, ensuring clarity in usage examples.
* Add documentation for causal_block_size parameter in SkyReelsV2DF pipelines, clarifying its role in asynchronous inference.
* Simplify min_ar_step calculation in SkyReelsV2DiffusionForcingPipeline to improve clarity.
* style and fix-copies
* style
* Add documentation for SkyReelsV2Transformer3DModel
Introduced a new markdown file detailing the SkyReelsV2Transformer3DModel, including usage instructions and model output specifications.
* Update test configurations for SkyReelsV2 pipelines
- Adjusted `in_channels` from 36 to 16 in `test_skyreels_v2_df_image_to_video.py`.
- Added new parameters: `overlap_history`, `num_frames`, and `base_num_frames` in `test_skyreels_v2_df_video_to_video.py`.
- Updated expected output shape in video tests from (17, 3, 16, 16) to (41, 3, 16, 16).
* Refines SkyReelsV2DF test parameters
* Update src/diffusers/models/modeling_outputs.py
Co-authored-by: Aryan <contact.aryanvs@gmail.com>
* Refactor `grid_sizes` processing by using already-calculated post-patch parameters to simplify
* Update docs/source/en/api/pipelines/skyreels_v2.md
Co-authored-by: Aryan <contact.aryanvs@gmail.com>
* Refactor parameter naming for diffusion forcing in SkyReelsV2 pipelines
- Changed `flag_df` to `enable_diffusion_forcing` for clarity in the SkyReelsV2Transformer3DModel and associated pipelines.
- Updated all relevant method calls to reflect the new parameter name.
* Revert _toctree.yml to adjust section expansion states
* style
* Update docs/source/en/api/models/skyreels_v2_transformer_3d.md
Co-authored-by: YiYi Xu <yixu310@gmail.com>
* Add copying label to SkyReelsV2ImageEmbedding from WanImageEmbedding.
* Refactor transformer block processing in SkyReelsV2Transformer3DModel
- Ensured proper handling of hidden states during both gradient checkpointing and standard processing.
* Update SkyReels V2 documentation to remove VRAM requirement and streamline imports
- Removed the mention of ~13GB VRAM requirement for the SkyReels-V2 model.
- Simplified import statements by removing unused `load_image` import.
* Add SkyReelsV2LoraLoaderMixin for loading and managing LoRA layers in SkyReelsV2Transformer3DModel
- Introduced SkyReelsV2LoraLoaderMixin class to handle loading, saving, and fusing of LoRA weights specific to the SkyReelsV2 model.
- Implemented methods for state dict management, including compatibility checks for various LoRA formats.
- Enhanced functionality for loading weights with options for low CPU memory usage and hotswapping.
- Added detailed docstrings for clarity on parameters and usage.
* Update SkyReelsV2 documentation and loader mixin references
- Corrected the documentation to reference the new `SkyReelsV2LoraLoaderMixin` for loading LoRA weights.
- Updated comments in the `SkyReelsV2LoraLoaderMixin` class to reflect changes in model references from `WanTransformer3DModel` to `SkyReelsV2Transformer3DModel`.
* Enhance SkyReelsV2 integration by adding SkyReelsV2LoraLoaderMixin references
- Added `SkyReelsV2LoraLoaderMixin` to the documentation and loader imports for improved LoRA weight management.
- Updated multiple pipeline classes to inherit from `SkyReelsV2LoraLoaderMixin` instead of `WanLoraLoaderMixin`.
* Update SkyReelsV2 model references in documentation
- Replaced placeholder model paths with actual paths for SkyReels-V2 models in multiple pipeline files.
- Ensured consistency across the documentation for loading models in the SkyReelsV2 pipelines.
* style
* fix-copies
* Refactor `fps_projection` in `SkyReelsV2Transformer3DModel`
- Replaced the sequential linear layers for `fps_projection` with a `FeedForward` layer using `SiLU` activation for better integration.
* Update docs
* Refactor video processing in SkyReelsV2DiffusionForcingPipeline
- Renamed parameters for clarity: `video` to `video_latents` and `overlap_history` to `overlap_history_latent_frames`.
- Updated logic for handling long video generation, including adjustments to latent frame calculations and accumulation.
- Consolidated handling of latents for both long and short video generation scenarios.
- Final decoding step now consistently converts latents to pixels, ensuring proper output format.
* Update activation function in `fps_projection` of `SkyReelsV2Transformer3DModel`
- Changed activation function from `silu` to `linear-silu` in the `fps_projection` layer for improved performance and integration.
* Add fps_projection layer renaming in convert_skyreelsv2_to_diffusers.py
- Updated key mappings for the `fps_projection` layer to align with new naming conventions, ensuring consistency in model integration.
* Fix fps_projection assignment in SkyReelsV2Transformer3DModel
- Corrected the assignment of the `fps_projection` layer to ensure it is properly cast to the appropriate data type, enhancing model functionality.
* Update _keep_in_fp32_modules in SkyReelsV2Transformer3DModel
- Added `fps_projection` to the list of modules that should remain in FP32 precision, ensuring proper handling of data types during model operations.
* Remove integration test classes from SkyReelsV2 test files
- Deleted the `SkyReelsV2DiffusionForcingPipelineIntegrationTests` and `SkyReelsV2PipelineIntegrationTests` classes along with their associated setup, teardown, and test methods, as they were not implemented and not needed for current testing.
* style
* Refactor: Remove hardcoded `torch.bfloat16` cast in attention
* Refactor: Simplify data type handling in transformer model
Removes unnecessary data type conversions for the FPS embedding and timestep projection.
This change simplifies the forward pass by relying on the inherent data types of the tensors.
* Refactor: Remove `fps_projection` from `_keep_in_fp32_modules` in `SkyReelsV2Transformer3DModel`
* Update src/diffusers/models/transformers/transformer_skyreels_v2.py
Co-authored-by: Aryan <contact.aryanvs@gmail.com>
* Refactor: Remove unused flags and simplify attention mask handling in SkyReelsV2AttnProcessor2_0 and SkyReelsV2Transformer3DModel
Refactor: Simplify causal attention logic in SkyReelsV2
Removes the `flag_causal_attention` and `_flag_ar_attention` flags to simplify the implementation.
The decision to apply a causal attention mask is now based directly on the `num_frame_per_block` configuration, eliminating redundant flags and conditional checks. This streamlines the attention mechanism and simplifies the `set_ar_attention` methods.
* Refactor: Clarify variable names for latent frames
Renames `base_num_frames` to `base_latent_num_frames` to make it explicit that the variable refers to the number of frames in the latent space.
This change improves code readability and reduces potential confusion between latent frames and decoded video frames.
The `num_frames` parameter in `generate_timestep_matrix` is also renamed to `num_latent_frames` for consistency.
* Enhance documentation: Add detailed docstring for timestep matrix generation in SkyReelsV2DiffusionForcingPipeline
* Docs: Clarify long video chunking in pipeline docstring
Improves the explanation of long video processing within the pipeline's docstring.
The update replaces the abstract description with a concrete example, illustrating how the sliding window mechanism works with overlapping chunks. This makes the roles of `base_num_frames` and `overlap_history` clearer for users.
* Docs: Move visual demonstration and processing details for SkyReelsV2DiffusionForcingPipeline to docs page from the code
* Docs: Update asynchronous processing timeline and examples for long video handling in SkyReels-V2 documentation
* Enhance timestep matrix generation documentation and logic for synchronous/asynchronous video processing
* Update timestep matrix documentation and enhance analysis for clarity in SkyReelsV2DiffusionForcingPipeline
* Docs: Update visual demonstration section and add detailed step matrix construction example for asynchronous processing in SkyReelsV2DiffusionForcingPipeline
* style
* fix-copies
* Refactor parameter names for clarity in SkyReelsV2DiffusionForcingImageToVideoPipeline and SkyReelsV2DiffusionForcingVideoToVideoPipeline
* Refactor: Avoid VAE roundtrip in long video generation
Improves performance and quality for long video generation by operating entirely in latent space during the iterative generation process.
Instead of decoding latents to video and then re-encoding the overlapping section for the next chunk, this change passes the generated latents directly between iterations.
This avoids a computationally expensive and potentially lossy VAE decode/encode cycle within the loop. The full video is now decoded only once from the accumulated latents at the end of the process.
* Refactor: Rename prefix_video_latents_length to prefix_video_latents_frames for clarity
* Refactor: Rename num_latent_frames to current_num_latent_frames for clarity in SkyReelsV2DiffusionForcingImageToVideoPipeline
* Refactor: Enhance long video generation logic and improve latent handling in SkyReelsV2DiffusionForcingImageToVideoPipeline
Refactor: Unify video generation and pass latents directly
Unifies the separate code paths for short and long video generation into a single, streamlined loop.
This change eliminates the inefficient decode-encode cycle during long video generation. Instead of converting latents to pixel-space video between chunks, the pipeline now passes the generated latents directly to the next iteration.
This improves performance, avoids potential quality loss from intermediate VAE steps, and enhances code maintainability by removing significant duplication.
* style
* Refactor: Remove overlap_history parameter and streamline long video generation logic in SkyReelsV2DiffusionForcingImageToVideoPipeline
Refactor: Streamline long video generation logic
Removes the `overlap_history` parameter and simplifies the conditioning process for long video generation.
This change avoids a redundant VAE encoding step by directly using latent frames from the previous chunk for conditioning. It also moves image preprocessing outside the main generation loop to prevent repeated computations and clarifies the handling of prefix latents.
* style
* Refactor latent handling in i2v diffusion forcing pipeline
Improves the latent conditioning and accumulation logic within the image-to-video diffusion forcing loop.
- Corrects the splitting of the initial conditioning tensor to robustly handle both even and odd lengths.
- Simplifies how latents are accumulated across iterations for long video generation.
- Ensures the final latents are trimmed correctly before decoding only when a `last_image` is provided.
* Refactor: Remove overlap_history parameter from SkyReelsV2DiffusionForcingImageToVideoPipeline
* Refactor: Adjust video_latents parameter handling in prepare_latents method
* style
* Refactor: Update long video iteration print statements for clarity
* Fix: Update transformer config with dynamic causal block size
Updates the SkyReelsV2 pipelines to correctly set the `causal_block_size` in the transformer's configuration when it's provided during a pipeline call.
This ensures the model configuration reflects the user's specified setting for the inference run. The `set_ar_attention` method is also renamed to `_set_ar_attention` to mark it as an internal helper.
* style
* Refactor: Adjust video input size and expected output shape in inference test
* Refactor: Rename video variables for clarity in SkyReelsV2DiffusionForcingVideoToVideoPipeline
* Docs: Clarify time embedding logic in SkyReelsV2
Adds comments to explain the handling of different time embedding tensor dimensions.
A 2D tensor is used for standard models with a single time embedding per batch, while a 3D tensor is used for Diffusion Forcing models where each frame has its own time embedding. This clarifies the expected input for different model variations.
* Docs: Update SkyReels V2 pipeline examples
Updates the docstring examples for the SkyReels V2 pipelines to reflect current best practices and API changes.
- Removes the `shift` parameter from pipeline call examples, as it is now configured directly on the scheduler.
- Replaces the `set_ar_attention` method call with the `causal_block_size` argument in the pipeline call for diffusion forcing examples.
- Adjusts recommended parameters for I2V and V2V examples, including inference steps, guidance scale, and `ar_step`.
* Refactor: Remove `shift` parameter from SkyReelsV2 pipelines
Removes the `shift` parameter from the call signature of all SkyReelsV2 pipelines.
This parameter is a scheduler-specific configuration and should be set directly on the scheduler during its initialization, rather than being passed at runtime through the pipeline. This change simplifies the pipeline API.
Usage examples are updated to reflect that the `shift` value should now be passed when creating the `FlowMatchUniPCMultistepScheduler`.
* Refactors SkyReelsV2 image-to-video tests and adds last image case
Simplifies the test suite by removing a duplicated test class and streamlining the dummy component and input generation.
Adds a new test to verify the pipeline's behavior when a `last_image` is provided as input for conditioning.
* test: Add image components to SkyReelsV2 pipeline test
Adds the `image_encoder` and `image_processor` to the test components for the image-to-video pipeline.
Also replaces a hardcoded value for the positional embedding sequence length with a more descriptive calculation, improving clarity.
* test: Add callback configuration test for SkyReelsV2DiffusionForcingVideoToVideoPipeline
test: Add callback test for SkyReelsV2DFV2V pipeline
Adds a test to validate the callback functionality for the `SkyReelsV2DiffusionForcingVideoToVideoPipeline`.
This test confirms that `callback_on_step_end` is invoked correctly and can modify the pipeline's state during inference. It uses a callback to dynamically increase the `guidance_scale` and asserts that the final value is as expected.
The implementation correctly accounts for the nested denoising loops present in diffusion forcing pipelines.
* style
* fix: Update image_encoder type to CLIPVisionModelWithProjection in SkyReelsV2ImageToVideoPipeline
* UP
* Add conversion support for SkyReels-V2-FLF2V models
Adds configurations for three new FLF2V model variants (1.3B-540P, 14B-540P, and 14B-720P) to the conversion script.
This change also introduces specific handling to zero out the image positional embeddings for these models and updates the main script to correctly initialize the image-to-video pipeline.
* Docs: Update and simplify SkyReels V2 usage examples
Simplifies the text-to-video example by removing the manual group offloading configuration, making it more straightforward.
Adds comments to pipeline parameters to clarify their purpose and provides guidance for different resolutions and long video generation.
Introduces a new section with a code example for the video-to-video pipeline.
* style
* docs: Add SkyReels-V2 FLF2V 1.3B model to supported models list
* docs: Update SkyReels-V2 documentation
* Move the initialization of the `gradient_checkpointing` attribute to its suggested location.
* Refactor: Use logger for long video progress messages
Replaces `print()` calls with `logger.debug()` for reporting progress during long video generation in SkyReelsV2DF pipelines.
This change reduces console output verbosity for standard runs while allowing developers to view progress by enabling debug-level logging.
* Refactor SkyReelsV2 timestep embedding into a module
Extract the sinusoidal timestep embedding logic into a new `SkyReelsV2Timesteps` `nn.Module`.
This change encapsulates the embedding generation, which simplifies the `SkyReelsV2TimeTextImageEmbedding` class and improves code modularity.
* Fix: Preserve original shape in timestep embeddings
Reshapes the timestep embedding tensor to match the original input shape.
This ensures that batched timestep inputs retain their batch dimension after embedding, preventing potential shape mismatches.
* style
* Refactor: Move SkyReelsV2Timesteps to model file
Colocates the `SkyReelsV2Timesteps` class with the SkyReelsV2 transformer model.
This change moves model-specific timestep embedding logic from the general embeddings module to the transformer's own file, improving modularity and making the model more self-contained.
* Refactor parameter dtype retrieval to use utility function
Replaces manual parameter iteration with the `get_parameter_dtype` helper to determine the time embedder's data type.
This change improves code readability and centralizes the logic.
* Add comments to track the tensor shape transformations
* Add copied froms
* style
* fix-copies
* up
* Remove FlowMatchUniPCMultistepScheduler
Deletes the `FlowMatchUniPCMultistepScheduler` as it is no longer being used.
* Refactor: Replace FlowMatchUniPC scheduler with UniPC
Removes the `FlowMatchUniPCMultistepScheduler` and integrates its functionality into the existing `UniPCMultistepScheduler`.
This consolidation is achieved by using the `use_flow_sigmas=True` parameter in `UniPCMultistepScheduler`, simplifying the scheduler API and reducing code duplication. All usages, documentation, and tests are updated accordingly.
* style
* Remove text_encoder parameter from SkyReelsV2DiffusionForcingPipeline initialization
* Docs: Rename `pipe` to `pipeline` in SkyReels examples
Updates the variable name from `pipe` to `pipeline` across all SkyReels V2 documentation examples. This change improves clarity and consistency.
* Fix: Rename shift parameter to flow_shift in SkyReels-V2 examples
* Fix: Rename shift parameter to flow_shift in example documentation across SkyReels-V2 files
* Fix: Rename shift parameter to flow_shift in UniPCMultistepScheduler initialization across SkyReels test files
* Removes unused generator argument from scheduler step
The `generator` parameter is not used by the scheduler's `step` method within the SkyReelsV2 diffusion forcing pipelines. This change removes the unnecessary argument from the method call for code clarity and consistency.
* Fix: Update time_embedder_dtype assignment to use the first parameter's dtype in SkyReelsV2TimeTextImageEmbedding
* style
* Refactor: Use get_parameter_dtype utility function
Replaces manual parameter iteration with the `get_parameter_dtype` helper.
* Fix: Prevent (potential) error in parameter dtype check
Adds a check to ensure the `_keep_in_fp32_modules` attribute exists on a parameter before it is accessed.
This prevents a potential `AttributeError`, making the utility function more robust when used with models that do not define this attribute.
---------
Co-authored-by: YiYi Xu <yixu310@gmail.com>
Co-authored-by: Aryan <contact.aryanvs@gmail.com>
* begin transformer conversion
* refactor
* refactor
* refactor
* refactor
* refactor
* refactor
* update
* add conversion script
* add pipeline
* make fix-copies
* remove einops
* update docs
* gradient checkpointing
* add transformer test
* update
* debug
* remove prints
* match sigmas
* add vae pt. 1
* finish CV* vae
* update
* update
* update
* update
* update
* update
* make fix-copies
* update
* make fix-copies
* fix
* update
* update
* make fix-copies
* update
* update tests
* handle device and dtype for safety checker; required in latest diffusers
* remove enable_gqa and use repeat_interleave instead
* enforce safety checker; use dummy checker in fast tests
* add review suggestion for ONNX export
Co-Authored-By: Asfiya Baig <asfiyab@nvidia.com>
* fix safety_checker issues when not passed explicitly
We could either do what's done in this commit, or update the Cosmos examples to explicitly pass the safety checker
* use cosmos guardrail package
* auto format docs
* update conversion script to support 14B models
* update name CosmosPipeline -> CosmosTextToWorldPipeline
* update docs
* fix docs
* fix group offload test failing for vae
---------
Co-authored-by: Asfiya Baig <asfiyab@nvidia.com>
* init
* encode with glm
* draft schedule
* feat(scheduler): Add CogView scheduler implementation
* feat(embeddings): add CogView 2D rotary positional embedding
* 1
* Update pipeline_cogview4.py
* fix the timestep init and sigma
* update latent
* draft patch(not work)
* fix
* [WIP][cogview4]: implement initial CogView4 pipeline
Implement the basic CogView4 pipeline structure with the following changes:
- Add CogView4 pipeline implementation
- Implement DDIM scheduler for CogView4
- Add CogView3Plus transformer architecture
- Update embedding models
Current limitations:
- CFG implementation uses padding for sequence length alignment
- Need to verify transformer inference alignment with Megatron
TODO:
- Consider separate forward passes for condition/uncondition
instead of padding approach
* [WIP][cogview4][refactor]: Split condition/uncondition forward pass in CogView4 pipeline
Split the forward pass for conditional and unconditional predictions in the CogView4 pipeline to match the original implementation. The noise prediction is now done separately for each case before combining them for guidance. However, the results still need improvement.
This is a work in progress as the generated images are not yet matching expected quality.
* use with -2 hidden state
* remove text_projector
* 1
* [WIP] Add tensor-reload to align input from transformer block
* [WIP] for older glm
* use with cogview4 transformers forward twice of u and uc
* Update convert_cogview4_to_diffusers.py
* remove this
* use main example
* change back
* reset
* setback
* back
* back 4
* Fix qkv conversion logic for CogView4 to Diffusers format
* back5
* revert to sat to cogview4 version
* update a new convert from megatron
* [WIP][cogview4]: implement CogView4 attention processor
Add CogView4AttnProcessor class for implementing scaled dot-product attention
with rotary embeddings for the CogVideoX model. This processor concatenates
encoder and hidden states, applies QKV projections and RoPE, but does not
include spatial normalization.
TODO:
- Fix incorrect QKV projection weights
- Resolve ~25% error in RoPE implementation compared to Megatron
* [cogview4] implement CogView4 transformer block
Implement CogView4 transformer block following the Megatron architecture:
- Add multi-modulate and multi-gate mechanisms for adaptive layer normalization
- Implement dual-stream attention with encoder-decoder structure
- Add feed-forward network with GELU activation
- Support rotary position embeddings for image tokens
The implementation follows the original CogView4 architecture while adapting
it to work within the diffusers framework.
* with new attn
* [bugfix] fix dimension mismatch in CogView4 attention
* [cogview4][WIP]: update final normalization in CogView4 transformer
Refactored the final normalization layer in CogView4 transformer to use separate layernorm and AdaLN operations instead of combined AdaLayerNormContinuous. This matches the original implementation but needs validation.
Needs verification against reference implementation.
* 1
* put back
* Update transformer_cogview4.py
* change time_shift
* Update pipeline_cogview4.py
* change timesteps
* fix
* change text_encoder_id
* [cogview4][rope] align RoPE implementation with Megatron
- Implement apply_rope method in attention processor to match Megatron's implementation
- Update position embeddings to ensure compatibility with Megatron-style rotary embeddings
- Ensure consistent rotary position encoding across attention layers
This change improves compatibility with Megatron-based models and provides
better alignment with the original implementation's positional encoding approach.
* [cogview4][bugfix] apply silu activation to time embeddings in CogView4
Applied silu activation to time embeddings before splitting into conditional
and unconditional parts in CogView4Transformer2DModel. This matches the
original implementation and helps ensure correct time conditioning behavior.
* [cogview4][chore] clean up pipeline code
- Remove commented out code and debug statements
- Remove unused retrieve_timesteps function
- Clean up code formatting and documentation
This commit focuses on code cleanup in the CogView4 pipeline implementation, removing unnecessary commented code and improving readability without changing functionality.
* [cogview4][scheduler] Implement CogView4 scheduler and pipeline
* now It work
* add timestep
* batch
* change convert scipt
* refactor pt. 1; make style
* refactor pt. 2
* refactor pt. 3
* add tests
* make fix-copies
* update toctree.yml
* use flow match scheduler instead of custom
* remove scheduling_cogview.py
* add tiktoken to test dependencies
* Update src/diffusers/models/embeddings.py
Co-authored-by: YiYi Xu <yixu310@gmail.com>
* apply suggestions from review
* use diffusers apply_rotary_emb
* update flow match scheduler to accept timesteps
* fix comment
* apply review sugestions
* Update src/diffusers/schedulers/scheduling_flow_match_euler_discrete.py
Co-authored-by: YiYi Xu <yixu310@gmail.com>
---------
Co-authored-by: 三洋三洋 <1258009915@qq.com>
Co-authored-by: OleehyO <leehy0357@gmail.com>
Co-authored-by: Aryan <aryan@huggingface.co>
Co-authored-by: YiYi Xu <yixu310@gmail.com>
* copy transformer
* copy vae
* copy pipeline
* make fix-copies
* refactor; make original code work with diffusers; test latents for comparison generated with this commit
* move rope into pipeline; remove flash attention; refactor
* begin conversion script
* make style
* refactor attention
* refactor
* refactor final layer
* their mlp -> our feedforward
* make style
* add docs
* refactor layer names
* refactor modulation
* cleanup
* refactor norms
* refactor activations
* refactor single blocks attention
* refactor attention processor
* make style
* cleanup a bit
* refactor double transformer block attention
* update mochi attn proc
* use diffusers attention implementation in all modules; checkpoint for all values matching original
* remove helper functions in vae
* refactor upsample
* refactor causal conv
* refactor resnet
* refactor
* refactor
* refactor
* grad checkpointing
* autoencoder test
* fix scaling factor
* refactor clip
* refactor llama text encoding
* add coauthor
Co-Authored-By: "Gregory D. Hunkins" <greg@ollano.com>
* refactor rope; diff: 0.14990234375; reason and fix: create rope grid on cpu and move to device
Note: The following line diverges from original behaviour. We create the grid on the device, whereas
original implementation creates it on CPU and then moves it to device. This results in numerical
differences in layerwise debugging outputs, but visually it is the same.
* use diffusers timesteps embedding; diff: 0.10205078125
* rename
* convert
* update
* add tests for transformer
* add pipeline tests; text encoder 2 is not optional
* fix attention implementation for torch
* add example
* update docs
* update docs
* apply suggestions from review
* refactor vae
* update
* Apply suggestions from code review
Co-authored-by: hlky <hlky@hlky.ac>
* Update src/diffusers/pipelines/hunyuan_video/pipeline_hunyuan_video.py
Co-authored-by: hlky <hlky@hlky.ac>
* Update src/diffusers/pipelines/hunyuan_video/pipeline_hunyuan_video.py
Co-authored-by: hlky <hlky@hlky.ac>
* make fix-copies
* update
---------
Co-authored-by: "Gregory D. Hunkins" <greg@ollano.com>
Co-authored-by: hlky <hlky@hlky.ac>
* first add a script for DC-AE;
* DC-AE init
* replace triton with custom implementation
* 1. rename file and remove un-used codes;
* no longer rely on omegaconf and dataclass
* replace custom activation with diffuers activation
* remove dc_ae attention in attention_processor.py
* iinherit from ModelMixin
* inherit from ConfigMixin
* dc-ae reduce to one file
* update downsample and upsample
* clean code
* support DecoderOutput
* remove get_same_padding and val2tuple
* remove autocast and some assert
* update ResBlock
* remove contents within super().__init__
* Update src/diffusers/models/autoencoders/dc_ae.py
Co-authored-by: YiYi Xu <yixu310@gmail.com>
* remove opsequential
* update other blocks to support the removal of build_norm
* remove build encoder/decoder project in/out
* remove inheritance of RMSNorm2d from LayerNorm
* remove reset_parameters for RMSNorm2d
Co-authored-by: YiYi Xu <yixu310@gmail.com>
* remove device and dtype in RMSNorm2d __init__
Co-authored-by: YiYi Xu <yixu310@gmail.com>
* Update src/diffusers/models/autoencoders/dc_ae.py
Co-authored-by: YiYi Xu <yixu310@gmail.com>
* Update src/diffusers/models/autoencoders/dc_ae.py
Co-authored-by: YiYi Xu <yixu310@gmail.com>
* Update src/diffusers/models/autoencoders/dc_ae.py
Co-authored-by: YiYi Xu <yixu310@gmail.com>
* remove op_list & build_block
* remove build_stage_main
* change file name to autoencoder_dc
* move LiteMLA to attention.py
* align with other vae decode output;
* add DC-AE into init files;
* update
* make quality && make style;
* quick push before dgx disappears again
* update
* make style
* update
* update
* fix
* refactor
* refactor
* refactor
* update
* possibly change to nn.Linear
* refactor
* make fix-copies
* replace vae with ae
* replace get_block_from_block_type to get_block
* replace downsample_block_type from Conv to conv for consistency
* add scaling factors
* incorporate changes for all checkpoints
* make style
* move mla to attention processor file; split qkv conv to linears
* refactor
* add tests
* from original file loader
* add docs
* add standard autoencoder methods
* combine attention processor
* fix tests
* update
* minor fix
* minor fix
* minor fix & in/out shortcut rename
* minor fix
* make style
* fix paper link
* update docs
* update single file loading
* make style
* remove single file loading support; todo for DN6
* Apply suggestions from code review
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
* add abstract
* 1. add DCAE into diffusers;
2. make style and make quality;
* add DCAE_HF into diffusers;
* bug fixed;
* add SanaPipeline, SanaTransformer2D into diffusers;
* add sanaLinearAttnProcessor2_0;
* first update for SanaTransformer;
* first update for SanaPipeline;
* first success run SanaPipeline;
* model output finally match with original model with the same intput;
* code update;
* code update;
* add a flow dpm-solver scripts
* 🎉[important update]
1. Integrate flow-dpm-sovler into diffusers;
2. finally run successfully on both `FlowMatchEulerDiscreteScheduler` and `FlowDPMSolverMultistepScheduler`;
* 🎉🔧[important update & fix huge bugs!!]
1. add SanaPAGPipeline & several related Sana linear attention operators;
2. `SanaTransformer2DModel` not supports multi-resolution input;
2. fix the multi-scale HW bugs in SanaPipeline and SanaPAGPipeline;
3. fix the flow-dpm-solver set_timestep() init `model_output` and `lower_order_nums` bugs;
* remove prints;
* add convert sana official checkpoint to diffusers format Safetensor.
* Update src/diffusers/models/transformers/sana_transformer_2d.py
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
* Update src/diffusers/models/transformers/sana_transformer_2d.py
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
* Update src/diffusers/models/transformers/sana_transformer_2d.py
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
* Update src/diffusers/pipelines/pag/pipeline_pag_sana.py
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
* Update src/diffusers/models/transformers/sana_transformer_2d.py
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
* Update src/diffusers/models/transformers/sana_transformer_2d.py
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
* Update src/diffusers/pipelines/sana/pipeline_sana.py
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
* Update src/diffusers/pipelines/sana/pipeline_sana.py
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
* update Sana for DC-AE's recent commit;
* make style && make quality
* Add StableDiffusion3PAGImg2Img Pipeline + Fix SD3 Unconditional PAG (#9932)
* fix progress bar updates in SD 1.5 PAG Img2Img pipeline
---------
Co-authored-by: Vinh H. Pham <phamvinh257@gmail.com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
* make the vae can be None in `__init__` of `SanaPipeline`
* Update src/diffusers/models/transformers/sana_transformer_2d.py
Co-authored-by: hlky <hlky@hlky.ac>
* change the ae related code due to the latest update of DCAE branch;
* change the ae related code due to the latest update of DCAE branch;
* 1. change code based on AutoencoderDC;
2. fix the bug of new GLUMBConv;
3. run success;
* update for solving conversation.
* 1. fix bugs and run convert script success;
2. Downloading ckpt from hub automatically;
* make style && make quality;
* 1. remove un-unsed parameters in init;
2. code update;
* remove test file
* refactor; add docs; add tests; update conversion script
* make style
* make fix-copies
* refactor
* udpate pipelines
* pag tests and refactor
* remove sana pag conversion script
* handle weight casting in conversion script
* update conversion script
* add a processor
* 1. add bf16 pth file path;
2. add complex human instruct in pipeline;
* fix fast \tests
* change gemma-2-2b-it ckpt to a non-gated repo;
* fix the pth path bug in conversion script;
* change grad ckpt to original; make style
* fix the complex_human_instruct bug and typo;
* remove dpmsolver flow scheduler
* apply review suggestions
* change the `FlowMatchEulerDiscreteScheduler` to default `DPMSolverMultistepScheduler` with flow matching scheduler.
* fix the tokenizer.padding_side='right' bug;
* update docs
* make fix-copies
* fix imports
* fix docs
* add integration test
* update docs
* update examples
* fix convert_model_output in schedulers
* fix failing tests
---------
Co-authored-by: Junyu Chen <chenjydl2003@gmail.com>
Co-authored-by: YiYi Xu <yixu310@gmail.com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: chenjy2003 <70215701+chenjy2003@users.noreply.github.com>
Co-authored-by: Aryan <aryan@huggingface.co>
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
Co-authored-by: hlky <hlky@hlky.ac>
* add skip_layers argument to SD3 transformer model class
* add unit test for skip_layers in stable diffusion 3
* sd3: pipeline should support skip layer guidance
* up
---------
Co-authored-by: bghira <bghira@users.github.com>
Co-authored-by: yiyixuxu <yixu310@gmail.com>
