GitLab

* 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__

init pipeline once

https://github.com/CompVis/stable-diffusion

* Allow passing non-default modules to pipeline.

Override modules are recognized and replaced in the pipeline. However,
no check is performed about mismatched classes yet. This is because the
override module is already instantiated and we have no library or class
name to compare against.

* up

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

* test LMS with LDM

* test LMS with LDM

* Interchangeable sigma and timestep. Added dummy objects

* Debug

* cuda generator

* Fix derivatives

* Update tests

* Rename Lms->LMS

* [PNDM] Stable diffusino

* finish

* [Half precision] Make sure half-precision is correct

* Update src/diffusers/models/unet_2d.py

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

* correct some tests

* Apply suggestions from code review
Co-authored-by: Suraj Patil <surajp815@gmail.com>

* finalize

* finish
Co-authored-by: Suraj Patil <surajp815@gmail.com>

* allow custom height width

* raise if height width are not mul of 8

add tests for sd pipeline

* add stable diffusion pipeline

* get rid of multiple if/else

* batch_size is unused

* add type hints

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

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

fix typo in condirion

use inspect instead of unused kwargs

* karras + VE, not flexible yet

* Fix inputs incompatibility with the original unet

* Roll back sigma scaling

* Apply suggestions from code review

* Old comment

* Fix doc

make text model generic

Fix arg key for `dataset_name`

The example training script was changed in #152, but not
`create_model_card`.

* pass downsample_padding in encoder

* update tests

add cross_attention_dim as an argument

add instruction to install with conda
Co-authored-by: Anton Lozhkov <anton@huggingface.co>

* Add issue template for feature requests and bug reports

* Update .github/ISSUE_TEMPLATE/config.yml
Co-authored-by: Anton Lozhkov <anton@huggingface.co>

* Support training with an image folder

* style