GitLab

`encoder_hid_dim` provides an additional projection for the input `encoder_hidden_states` from `encoder_hidden_dim` to `cross_attention_dim`

dynamic threshold sampling bug fix and docs

Co-authored-by: wangguan <dizhipeng.dzp@alibaba-inc.com>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

Update the K-Diffusion SD pipeline, to allow calling it with only prompt_embeds (instead of always requiring a prompt) (#2962)

* [2905]: Add Karras pattern to discrete euler

* [2905]: Add Karras pattern to discrete euler

* Review comments

* Review comments

* Review comments

* Review comments

---------
Co-authored-by: njindal <njindal@adobe.com>

* [Pipeline download] Improve pipeline download for index and passed components

* correct

* add more tests

* up

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

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

* [2884]: Fix cross_attention_kwargs in StableDiffusionImg2ImgPipeline

* [Build Fix]

* [Build Fix]

---------
Co-authored-by: njindal <njindal@adobe.com>

* Remove suggestion to use cuDNN benchmark in docs

* removing the wrong line

* add support for embeds

* fix line length

* add use_karras_sigmas option

thanks @Stax124

* fix sigma_min/max from scheduler.sigmas

* add docstring

* revert to use k_diffusion_model.sigma, to(device)

* add integration test

* make style

* add load textual inversion embeddings draft

* fix quality

* fix typo

* make fix copies

* move to textual inversion mixin

* make it accept from sd-concept library

* accept list of paths to embeddings

* fix styling of stable diffusion pipeline

* add dummy TextualInversionMixin

* add docstring to textualinversionmixin

* add load textual inversion embeddings draft

* fix quality

* fix typo

* make fix copies

* move to textual inversion mixin

* make it accept from sd-concept library

* accept list of paths to embeddings

* fix styling of stable diffusion pipeline

* add dummy TextualInversionMixin

* add docstring to textualinversionmixin

* add case for parsing embedding from auto1111 UI format
Co-authored-by: Evan Jones <evan.a.jones3@gmail.com>
Co-authored-by: Ana Tamais <aninhamoraestamais@gmail.com>

* fix style after rebase

* move textual inversion mixin to loaders

* move mixin inheritance to DiffusionPipeline from StableDiffusionPipeline)

* update dummy class name

* addressed allo comments

* fix old dangling import

* fix style

* proposal

* remove bogus

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

* finish

* make style

* up

* fix code quality

* fix code quality - again

* fix code quality - 3

* fix alt diffusion code quality

* fix model editing pipeline

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

* Finish

---------
Co-authored-by: Evan Jones <evan.a.jones3@gmail.com>
Co-authored-by: Ana Tamais <aninhamoraestamais@gmail.com>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: Will Berman <wlbberman@gmail.com>
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

Co-authored-by: njindal <njindal@adobe.com>

Add warning in __init__ if user loads a checkpoint with pipeline.unet.config.in_channels other than 9.

Add last_epoch arg to optimization.get_scheduler.

Allows the specification of the index of the last epoch when
resuming training.

Update the legacy inpainting SD pipeline, to allow calling it with only prompt_embeds (instead of always requiring a prompt) (#2842)

Fix error 'required positional argument: prompt' when Legacy Inpaint is called only with prompt_embeds

* Remove duplicate sentence

* format

* Allow user to disable SafetyChecker and enable dtypes if loading models from .ckpt or .safetensors

* Fix Import sorting (Ruff error)

* Get rid of the dtype convert method as it was implemented all along

* Fix the docstring

* Fix ruff formatting

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

Improve init

* Workaround for saving dynamo-wrapped models.

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

* Apply workaround when overriding pipeline components.

* Ensure the correct config.json is saved to disk.

Instead of the dynamo class.

* Save correct module (not compiled one)

* Add test

* style

* fix docstrings

* Go back to using string comparisons.

PyTorch CPU does not have _dynamo.

* Simple test for save_pretrained of compiled models.

* Helper function to test whether module is compiled.

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

* add: better warning messages when handling multiple conditioning.

* fix: handling of controlnet_conditioning_scale

* Helper function to disable custom attention processors.

* Restore code deleted by mistake.

* Format

* Fix modeling_text_unet copy.

* Apply same ruff settings as in transformers

See https://github.com/huggingface/transformers/blob/main/pyproject.toml

Co-authored-by: Aaron Gokaslan <aaronGokaslan@gmail.com>

* Apply new style rules

* Style
Co-authored-by: Aaron Gokaslan <aaronGokaslan@gmail.com>

* style

* remove list, ruff wouldn't auto fix.

---------
Co-authored-by: Aaron Gokaslan <aaronGokaslan@gmail.com>