GitLab

* add method to enable cuda with minimal gpu usage to stable diffusion

* add test to minimal cuda memory usage

* ensure all models but unet are onn torch.float32

* move to cpu_offload along with minor internal changes to make it work

* make it test against accelerate master branch

* coming back, its official: I don't know how to make it test againt the master branch from accelerate

* make it install accelerate from master on tests

* go back to accelerate>=0.11

* undo prettier formatting on yml files

* undo prettier formatting on yml files againn

remove tensor_format in the new version

CompVis -> diffusers script - allow converting from merged checkpoint to either EMA or non-EMA (#991)

* improve script

* up

* Add failing test for #940.

* Do not use torch.float64 in mps.

* style

* Temporarily skip add_noise for IPNDMScheduler.

Until #990 is addressed.

* Add --pretrained_model_name_revision option to train_dreambooth.py

* Renamed --pretrained_model_name_revision to --revision

uP

* add in fp16

* up

* start

* add more logic

* Update src/diffusers/models/unet_2d_condition_flax.py

* match weights

* up

* make model work

* making class more general, fixing missed file rename

* small fix

* make new conversion work

* up

* finalize conversion

* up

* first batch of variable renamings

* remove c and c_prev var names

* add mid and out block structure

* add pipeline

* up

* finish conversion

* finish

* upload

* more fixes

* Apply suggestions from code review

* add attr

* up

* uP

* up

* finish tests

* finish

* uP

* finish

* fix test

* up

* naming consistency in tests

* Apply suggestions from code review
Co-authored-by: Suraj Patil <surajp815@gmail.com>
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>
Co-authored-by: Nathan Lambert <nathan@huggingface.co>
Co-authored-by: Anton Lozhkov <anton@huggingface.co>

* remove hardcoded 16

* Remove bogus

* fix some stuff

* finish

* improve logging

* docs

* upload
Co-authored-by: Nathan Lambert <nol@berkeley.edu>
Co-authored-by: Suraj Patil <surajp815@gmail.com>
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>
Co-authored-by: Nathan Lambert <nathan@huggingface.co>
Co-authored-by: Anton Lozhkov <anton@huggingface.co>

* [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>