* format timesteps attrs to np arrays in pndm scheduler
because lists don't get formatted to tensors in `self.set_format`
* convert to long type to use timesteps as indices for tensors
* add scheduler set_format test
* fix `_timesteps` type
* make style with black 22.3.0 and isort 5.10.1
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
* [Type hint] Karras VE pipeline
* Apply suggestions from code review
Co-authored-by: Anton Lozhkov <anton@huggingface.co>
Co-authored-by: Anton Lozhkov <anton@huggingface.co>
* Helpful exception if inference steps not set in schedulers (#263)
* Apply suggestions from codereview by patrickvonplaten
* Apply suggestions from code review
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: Suraj Patil <surajp815@gmail.com>
* Refactor progress bar of pipeline __call__
* Make any tqdm configs available
* remove init
* add some tests
* remove file
* finish
* make style
* improve progress bar test
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
* 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>
* 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>
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 df90f0c.
* 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
Anton Lozhkov