GitLab

fake context parallel cache, vae encode tiling

(cherry picked from commit bf890bca0e8aed875d6a207f9b826ce894901522)

update to a place holder

* add a note on torchao/quanto benchmarks and memory-efficient inference

* apply suggestions from review

* update

* Update docs/source/en/api/pipelines/cogvideox.md
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* Update docs/source/en/api/pipelines/cogvideox.md
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* add note on enable sequential cpu offload

---------
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

update

change get_1d_rotary to accept pos as torch tensors

fix notes and dtype

[train_custom_diffusion.py] Fix the LR schedulers when `num_train_epochs` is passed in a distributed training env (#9308)

* Update train_custom_diffusion.py to fix the LR schedulers for `num_train_epochs`

* Fix saving text embeddings during safe serialization

* Fixed formatting

* support kohya lora in flux.

* format

* support xlabs

* diffusion_model prefix.

* Apply suggestions from code review
Co-authored-by: apolinário <joaopaulo.passos@gmail.com>

* empty commit.
Co-authored-by: Leommm-byte <leom20031@gmail.com>

---------
Co-authored-by: apolinário <joaopaulo.passos@gmail.com>
Co-authored-by: Leommm-byte <leom20031@gmail.com>

To match the original code, 7.0 is too high

* update

* implement prompt interpolation

* make style

* resnet memory optimizations

* more memory optimizations; todo: refactor

* update

* update animatediff controlnet with latest changes

* refactor chunked inference changes

* remove print statements

* undo memory optimization changes

* update docstrings

* fix tests

* fix pia tests

* apply suggestions from review

* add tests

* update comment

update

* update

* update

update

to avoid "FutureWarning: transformers.deepspeed module is deprecated and will be removed in a future version. Please import deepspeed modules directly from transformers.integrations"
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

update pipelines

initial fix

* fix shape

* fix prompt encoding

* style

* fix device

* add comment

* refactor 3d rope

* repeat -> expand

* refactor
---------
Co-authored-by: haofanwang <haofanwang.ai@gmail.com>

Update pipeline_kandinsky2_2_combined.py

Bugfix on image type check mismatch

* update

* update

update

update

* start fusing flux.

* test

* finish fusion

* fix-copues

* draft of embedding

---------
Co-authored-by: Aryan <aryan@huggingface.co>

merge now, will add/fix test next 

* fix PHILOSOPHY.md

* fix CONTRIBUTING.md

* fix tutorial_overview.md

* fix stable_diffusion.md

* Update tutorial_overview.md

* fix xformers tests

* remove unnecessary modifications to cogvideox tests

* update

* support parsing alpha from a flux lora state dict.

* conditional import.

* fix breaking changes.

* safeguard alpha.

* fix

* break from_pretrained part i.

* part ii.

* init_kwargs

* remove _fetch_init_kwargs

* type annotation

* dtyle

* switch to _check_and_update_init_kwargs_for_missing_modules.

* remove _check_and_update_init_kwargs_for_missing_modules.

* use pipeline_loading_kwargs.

* remove _determine_current_device_map.

* remove _filter_null_components.

* device_map fix.

* fix _update_init_kwargs_with_connected_pipeline.

* better handle custom pipeline.

* explain _maybe_raise_warning_for_inpainting.

* add example for model variant.

* fix

fix docstring
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* refactor rotary embeds

* adding jsmidt as co-author of this PR for https://github.com/huggingface/diffusers/pull/9133



---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: Joseph Smidt <josephsmidt@gmail.com>

* Added pad controlnet sdxl img2img pipeline

---------
Co-authored-by: YiYi Xu <yixu310@gmail.com>

update

fix

* make latent upscaler accept prompt embeds

---------
Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: YiYi Xu <yixu310@gmail.com>

Custom sampler support Stable Cascade Decoder