GitLab

* Support K-LMS in img2img

* Apply review suggestions

* Fixed add_noise in LMSDiscreteScheduler

* Linting

* Update src/diffusers/schedulers/scheduling_lms_discrete.py
Co-authored-by: Anton Lozhkov <aglozhkov@gmail.com>
Co-authored-by: Anton Lozhkov <aglozhkov@gmail.com>

* [Tests] Make sure tests are on GPU

* move more models

* speed up tests

adds missing torch import to example

* expand latents before the check, style

* update readme

* Init CI

* clarify cpu

* style

* Check scripts quality too

* Drop smi for cpu tests

* Run PR tests on cpu docker envs

* Update .github/workflows/push_tests.yml
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* Try minimal python container

* Print env, install stable GPU torch

* Manual torch install

* remove deprecated platform.dist()
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* add inpainting

* added proper noising of init_latent as reccommened by jackloomen (https://github.com/huggingface/diffusers/pull/241#issuecomment-1226283542)

* move image preprocessing inside pipeline and allow non 512x512 mask

* Update README.md

* Update README.md
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

* Update README.md
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

* Accept latents as input for StableDiffusionPipeline.

* Notebook to demonstrate reusable seeds (latents).

* More accurate type annotation
Co-authored-by: Suraj Patil <surajp815@gmail.com>

* Review comments: move to device, raise instead of assert.

* Actually commit the test notebook.

I had mistakenly pushed an empty file instead.

* Adapt notebook to Colab.

* Update examples readme.

* Move notebook to personal repo.
Co-authored-by: Suraj Patil <surajp815@gmail.com>

Style scripts

Pin black==22.3

* CleanResNet

* refactor more

* correct

* added test workflow and fixed failing test

* 4 decimal places

* split tests_modeling_utils

* Fix SD tests .to(device)

* fix merge

* Fix style
Co-authored-by: anton-l <anton@huggingface.co>

raise error if strength is not in desired range

* boom boom

* reorganise examples

* add image2image in example inference

* add readme

* fix example

* update colab url

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

* fix init_timestep

* update colab url

* update main readme

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

remove dead code in resnet.py
Co-authored-by: ydshieh <ydshieh@users.noreply.github.com>

add add_noise method in more schedulers

Restore `is_modelcards_available` in `.utils`.

Otherwise attempting to import `hub_utils` (in training scripts, for
example), fails.

This was removed during the refactor in df90f0ce.

* Update README for 0.2.3 release:

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

* Implement `pipeline.to(device)`

* DiffusionPipeline.to() decides best device on None.

* Breaking change: torch_device removed from __call__

`pipeline.to()` now has PyTorch semantics.

* Use kwargs and deprecation notice
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* Apply torch_device compatibility to all pipelines.

* style
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: anton-l <anton@huggingface.co>

* add SafetyChecker

* better name, fix checker

* add checker in main init

* remove from main init

* update logic to detect pipeline module

* style

* handle all safety logic in safety checker

* draw text

* can't draw

* small fixes

* treat special care as nsfw

* remove commented lines

* update safety checker

* Support one-string prompts in LDM

* Add other features from SD too

* Add is_<framework>_available, refactor import utils

* deps

* quality

* Revive Make utils

* Add datasets for training too

use default params in __call__