GitLab

* Tiled VAE for high-res text2img and img2img

* vae tiling, fix formatting

* enable_vae_tiling API and tests

* tiled vae docs, disable tiling for images that would have only one tile

* tiled vae tests, use channels_last memory format

* tiled vae tests, use smaller test image

* tiled vae tests, remove tiling test from fast tests

* up

* up

* make style

* Apply suggestions from code review

* Apply suggestions from code review

* Apply suggestions from code review

* make style

* improve naming

* finish

* apply suggestions

* Apply suggestions from code review
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

* up

---------
Co-authored-by: Ilmari Heikkinen <ilmari@fhtr.org>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

* Add 4090 benchmark (PyTorch 2.0)

* Small changes in nomenclature.

Fix typo in AttnProcessor2_0 symbol.

* add sdpa processor

* don't use it by default

* add some checks and style

* typo

* support torch sdpa in dreambooth example

* use torch attn proc by default when available

* typo

* add attn mask

* fix naming

* being doc

* doc

* Apply suggestions from code review

* polish

* torctree

* Apply suggestions from code review
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* better name

* style

* add benchamrk table

* Update docs/source/en/optimization/torch2.0.mdx

* up

* fix example

* check if processor is None

* Apply suggestions from code review
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

* add fp32 benchmakr

* Apply suggestions from code review
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

* enable_model_offload PoC

It's surprisingly more involved than expected, see comments in the PR.

* Rename final_offload_hook

* Invoke the vae forward hook manually.

* Completely remove decoder.

* Style

* apply_forward_hook decorator

* Rename method.

* Style

* Copy enable_model_cpu_offload

* Fix copies.

* Remove comment.

* Fix copies

* Missing import

* Fix doc-builder style.

* Merge main and fix again.

* Add docs

* Fix docs.

* Add a couple of tests.

* style

* before running make style

* remove left overs from flake8

* finish

* make fix-copies

* final fix

* more fixes

Update xFormers docs.

no more autocast

* [CPU offload] correct cpu offload

* [CPU offload] correct cpu offload

* finish

* finish

* Update docs/source/en/optimization/fp16.mdx
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

* Update src/diffusers/pipelines/alt_diffusion/pipeline_alt_diffusion.py
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

* init for korean docs

* edit build yml file for multi language docs

* edit one more build yml file for multi language docs

* add title for get_frontmatter error