GitLab

* [Onnx] support half-precision and fix bugs for onnx pipelines

* Update convert_stable_diffusion_checkpoint_to_onnx.py

* style

* fix has_nsfw_concept

* Update convert_stable_diffusion_checkpoint_to_onnx.py

* fix style

* Docs: refer to pre-RC version of PyTorch 1.13.0.

* Remove temporary workaround for unavailable op.

* Update comment to make it less ambiguous.

* Remove use of contiguous in mps.

It appears to not longer be necessary.

* Special case: use einsum for much better performance in mps

* Update mps docs.

* Minor doc update.

* Accept suggestion
Co-authored-by: Anton Lozhkov <anton@huggingface.co>
Co-authored-by: Anton Lozhkov <anton@huggingface.co>

* [WIP] Debugging mps DDIM tests

* revert num_steps

* check warmup with a generator

* more warmup!

* remove xdist

* just use a single process

* added broadcast_to_shape_from_left helper

* initial tests

* fixed pndm tests

* shape required for pndm

* added require_flax

* fix style

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

* Initial composable diffusion pipeline

* add composable stable diffusion to readme table

* Update examples/community/README.md

* Apply suggestions from code review

* Update examples/community/README.md

* Update examples/community/README.md

* Update examples/community/README.md

* up

* Update examples/community/README.md
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

Fix typo: torch_type -> torch_dtype

* add community pipeline docs

* fix style in code snippets (lol)

* clean up loading docs

* add license to doc files

* fix some weird links

* Update README.md

Additionally add FLAX so the model card can be slimmer and point to this page

* Find and replace all

* v-1-5 -> v1-5

* revert test changes

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

* Update docs/source/quicktour.mdx
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

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

* Update docs/source/quicktour.mdx
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

* Update README.md
Co-authored-by: Suraj Patil <surajp815@gmail.com>

* Revert certain references to v1-5

* Docs changes

* Apply suggestions from code review
Co-authored-by: apolinario <joaopaulo.passos+multimodal@gmail.com>
Co-authored-by: anton-l <anton@huggingface.co>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>
Co-authored-by: Suraj Patil <surajp815@gmail.com>

* Reorganize pipeline tests

* fix vq

one small typo in pipeline_ddpm.py

just a small typo in one comment

fix mps failing tests

* Initial Wildcard Stable Diffusion Pipeline

* Added some additional example usage

* style

* Added links in README and additional documentation

* Initial Wildcard Stable Diffusion Pipeline

* Added some additional example usage

* style

* Added links in README and additional documentation

* cleanup readme again

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

* Support LMSDiscreteScheduler in LDMPipeline

This is a small change to support all schedulers such as LMSDiscreteScheduler in LDMPipeline.

What's changed
-------
* Add the `scale_model_input` function before `step` to ensure correct denoising (L77)

* Add "scale the initial noise by the standard deviation required by the scheduler"

* run `make style`
Co-authored-by: Anton Lozhkov <anton@huggingface.co>

dont warn for bf16 weights

* [Tests] Move stable diffusion into their own files

* up

* Introduce the copy mechanism

* init tests

* fix dummy tests

* with

* update copies tests

* Bump the version to 0.7.0.dev0

* deprecate offsets

* deprecate LMS timesteps

* LMS 0.7.0->0.8.0

[Community Pipelines] fix pad_tokens_and_weights in lpw_stable_diffusion

Check if MPS backend is registered before calling is_available()

* Add an underscore to filename if it already exists

* Use sha1sum hash instead of adding underscores

dont' use safety check when generating prior images

* First draft

* created the SpeechToImagePipeline class

* Corrected speech_to_image_diffusion.py style

* Added safety checker

* Corrected style

* Adding examples to README

Add --sample_batch_size=1 to the 8 GB dreambooth script

[DiffusionPipeline.from_pretrained] add warning when passing unused kwargs

* [Stable Diffusion] Add components function

* uP

* [Community Pipelines] Long Prompt Weighting

* Update README.md

* fix

* style

* fix style

* Update examples/community/README.md
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

Docs update for new in-painting pipeline.
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* ONNX supervised inpainting

* sync with the torch pipeline

* fix concat

* update ref values

* back to 8 steps

* type fix

* make fix-copies

* begin pipe

* add new pipeline

* add tests

* correct fast test

* up

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

* Update tests/test_pipelines.py

* up

* up

* make style

* add fp16 test

* doc, comments

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

* finish

* up

* Apply suggestions from code review
Co-authored-by: Anton Lozhkov <anton@huggingface.co>

* Update src/diffusers/pipeline_utils.py

* Finish
Co-authored-by: Anton Lozhkov <anton@huggingface.co>

* [WIP] Onnx img2img determinism

* more numpy + seed

* numpy inpainting, tolerance

* revert test workflow

* * Stabe Diffusion img2img using onnx.

* * Stabe Diffusion inpaint using onnx.

* Export vae_encoder, upgrade img2img, add test

* updated inpainting pipeline + test

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

* allow fine-tuning text encoder

* fix a few things

* update readme