GitLab

Bring flax attention naming in sync with PyTorch.

* is_safetensors_compatible refactor

* files list comma

* Sequential cpu offload: require accelerate 0.14.0.

* Import is_accelerate_version

* Missing copy.

* Use "hub" directory for cache instead of "diffusers"

* Import cache locations from huggingface_hub

I verified that the constants are available in huggingface_hub version
0.10.0, which is the minimum we require.
Co-authored-by: Lucain Pouget <lucainp@gmail.com>

* make style

* Move cached directories to new location.

* make style

* Apply suggestions by @Wauplin
Co-authored-by: Lucain <lucainp@gmail.com>

* Fix is_file

* Ignore symlinks.

Especially important if we want to ensure that the user may want to invoke the
process again later, if they are keeping multiple envs with different
versions.

* Style

---------
Co-authored-by: Lucain Pouget <lucainp@gmail.com>

* attend and excite batch test causing timeouts

* pix2pix tests, no write to fs

* [Safetensors] Make sure metadata is saved

* make style

small bugfix at StableDiffusionDepth2ImgPipeline call to check_inputs and batch size calculation (#2423)

small bugfix in call to check_inputs and batch size calculation
Co-authored-by: mishka <gartsocial@gmail.com>

Co-authored-by: yiyixuxu <yixu310@gmail,com>

Deprecation warning should only hit at version 0.15

Fix typo in AttnProcessor2_0 symbol.

This reverts commit 024c4376.

Signed-off-by: daquexian <daquexian566@gmail.com>

* add MultiDiffusionPanorama pipeline

* fix docs naming

* update pipeline name, remove redundant tests

* apply styling.

* debugging information.

* fix: assertion values.

* fix-copies.

* update docs

* update docs

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

* add

* finish

* add tests

* add tests

* up

* up

* pull from main

* uP

* Apply suggestions from code review

* finish

* Update docs/source/en/_toctree.yml
Co-authored-by: Suraj Patil <surajp815@gmail.com>

* finish

* clean docs

* next

* next

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

* up

* up

---------
Co-authored-by: Suraj Patil <surajp815@gmail.com>
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

* Add semantic guidance pipeline

* Fix style

* Refactor Pipeline

* Pipeline documentation

* Add documentation

* Fix style and quality

* Fix doctree

* Add tests for SEGA

* Update src/diffusers/pipelines/semantic_stable_diffusion/pipeline_semantic_stable_diffusion.py
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* Update src/diffusers/pipelines/semantic_stable_diffusion/pipeline_semantic_stable_diffusion.py
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* Update src/diffusers/pipelines/semantic_stable_diffusion/pipeline_semantic_stable_diffusion.py
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* Make compatible with half precision

* Change deprecation warning to throw an exception

* update

---------
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* 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>

* [Pix2Pix] Add utility function

* improve

* update

* Apply suggestions from code review

* uP

* Update src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_pix2pix_zero.py

* fix typos in the doc

* restyle the code

fix safety_checker for batch_size > 1

Revert "[Pix2Pix0] Add utility function to get edit vector (#2383)"

This reverts commit 857c04cf.

uP

* attend and excite pipeline

* update

update docstring example

remove visualization

remove the base class attention control

remove dependency on stable diffusion pipeline

always apply gaussian filter with default setting

remove run_standard_sd argument

hardcode attention_res and scale_range (related to step size)

Update docs/source/en/api/pipelines/stable_diffusion/attend_and_excite.mdx
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

Update src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_attend_and_excite.py
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

Update src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_attend_and_excite.py
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

Update src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_attend_and_excite.py
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

Update src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_attend_and_excite.py
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

Update src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_attend_and_excite.py
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

Update src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_attend_and_excite.py
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

Update tests/pipelines/stable_diffusion_2/test_stable_diffusion_attend_and_excite.py
Co-authored-by: Will Berman <wlbberman@gmail.com>

Update src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_attend_and_excite.py
Co-authored-by: Will Berman <wlbberman@gmail.com>

Update src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_attend_and_excite.py
Co-authored-by: Will Berman <wlbberman@gmail.com>

revert test_float16_inference

revert change to the batch related tests

fix test_float16_inference

handle batch

remove the deprecation message

remove None check, step_size

remove debugging logging

add slow test

indices_to_alter -> indices

add check_input

* skip mps

* style

* Apply suggestions from code review
Co-authored-by: Suraj Patil <surajp815@gmail.com>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* indices -> token_indices
---------
Co-authored-by: evin <evinpinarornek@gmail.com>
Co-authored-by: yiyixuxu <yixu310@gmail,com>
Co-authored-by: Suraj Patil <surajp815@gmail.com>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* [Dummy imports] Add missing if else statements for SD]

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

---------
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

replace torch.concat by torch.cat

* add UniPC scheduler

* add the return type to the functions

* code quality check

* add tests

* finish docs

---------
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* 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

* add store and restore() methods to EMAModel.

* Update src/diffusers/training_utils.py
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* make style with doc builder

* remove explicit listing.

* Apply suggestions from code review
Co-authored-by: Will Berman <wlbberman@gmail.com>

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

* chore: better variable naming.

* better treatment of temp_stored_params
Co-authored-by: patil-suraj <surajp815@gmail.com>

* make style

* remove temporary params from earth 🌎



* make fix-copies.

---------
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: Will Berman <wlbberman@gmail.com>
Co-authored-by: patil-suraj <surajp815@gmail.com>

reset cur_model_output

* Add Stable Diffusion Sw/ elf-Attention Guidance

* Modify __init__.py

* Register attention storing processor

* Update pipeline_stable_diffusion_sag.py

* Editing default value

* Update pipeline_stable_diffusion_sag.py

* Update pipeline_stable_diffusion_sag.py

* Update pipeline_stable_diffusion_sag.py

* Update dummy_torch_and_transformers_objects.py

* Update pipeline_stable_diffusion_sag.py

* Update pipeline_stable_diffusion_sag.py

* Update pipeline_stable_diffusion_sag.py

* Update src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_sag.py
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* Update pipeline_stable_diffusion_sag.py

* Update src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_sag.py
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* Update src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_sag.py
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* Update src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_sag.py
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* Update src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_sag.py
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* Update src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_sag.py
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* Update src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_sag.py
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* Update src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_sag.py
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* Update src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_sag.py
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* Update src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_sag.py
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* Update src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_sag.py
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* Update pipeline_stable_diffusion_sag.py

* Update pipeline_stable_diffusion_sag.py

* Update pipeline_stable_diffusion_sag.py

* Update pipeline_stable_diffusion_sag.py

* Create test_stable_diffusion_sag.py

* Create self_attention_guidance.py

* Update pipeline_stable_diffusion_sag.py

* Update test_stable_diffusion_sag.py

* Update pipeline_stable_diffusion_sag.py

* Rename self_attention_guidance.py to self_attention_guidance.mdx

* Update self_attention_guidance.mdx

* Update self_attention_guidance.mdx

* Update _toctree.yml

* Update pipeline_stable_diffusion_sag.py

* Update pipeline_stable_diffusion_sag.py

* Update pipeline_stable_diffusion_sag.py

* Update pipeline_stable_diffusion_sag.py

* Fixing order

* Update pipeline_stable_diffusion_sag.py

* fixing import order

* fix order

* Update pipeline_stable_diffusion_sag.py

* Update pipeline_stable_diffusion_sag.py

* Naming change

* Noting pred_x0

* Adding some fast tests

* Update pipeline_stable_diffusion_sag.py

* Update test_stable_diffusion_sag.py

* Update test_stable_diffusion_sag.py

* Update test_stable_diffusion_sag.py

* Update docs/source/en/api/pipelines/stable_diffusion/self_attention_guidance.mdx

* implement gaussian_blur

* Update pipeline_stable_diffusion_sag.py

* Update pipeline_stable_diffusion_sag.py

* fix tests

* Update pipeline_stable_diffusion_sag.py

* Update pipeline_stable_diffusion_sag.py

---------
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: Will Berman <wlbberman@gmail.com>

* add: support for BLIP generation.

* add: support for editing synthetic images.

* remove unnecessary comments.

* add inits and run make fix-copies.

* version change of diffusers.

* fix: condition for loading the captioner.

* default conditions_input_image to False.

* guidance_amount -> cross_attention_guidance_amount

* fix inputs to check_inputs()

* fix: attribute.

* fix: prepare_attention_mask() call.

* debugging.

* better placement of references.

* remove torch.no_grad() decorations.

* put torch.no_grad() context before the first denoising loop.

* detach() latents before decoding them.

* put deocding in a torch.no_grad() context.

* add reconstructed image for debugging.

* no_grad(0

* apply formatting.

* address one-off suggestions from the draft PR.

* back to torch.no_grad() and add more elaborate comments.

* refactor prepare_unet() per Patrick's suggestions.

* more elaborate description for .

* formatting.

* add docstrings to the methods specific to pix2pix zero.

* suspecting a redundant noise prediction.

* needed for gradient computation chain.

* less hacks.

* fix: attention mask handling within the processor.

* remove attention reference map computation.

* fix: cross attn args.

* fix: prcoessor.

* store attention maps.

* fix: attention processor.

* update docs and better treatment to xa args.

* update the final noise computation call.

* change xa args call.

* remove xa args option from the pipeline.

* add: docs.

* first test.

* fix: url call.

* fix: argument call.

* remove image conditioning for now.

* 🚨 add: fast tests.

* explicit placement of the xa attn weights.

* add: slow tests 🐢

* fix: tests.

* edited direction embedding should be on the same device as prompt_embeds.

* debugging message.

* debugging.

* add pix2pix zero pipeline for a non-deterministic test.

* debugging/

* remove debugging message.

* make caption generation _

* address comments (part I).

* address PR comments (part II)

* fix: DDPM test assertion.

* refactor doc.

* address PR comments (part III).

* fix: type annotation for the scheduler.

* apply styling.

* skip_mps and add note on embeddings in the docs.