GitLab

* Run ControlNet compile test in a separate subprocess

`torch.compile()` spawns several subprocesses and the GPU memory used
was not reclaimed after the test ran. This approach was taken from
`transformers`.

* Style

* Prepare a couple more compile tests to run in subprocess.

* Use require_torch_2 decorator.

* Test inpaint_compile in subprocess.

* Run img2img compile test in subprocess.

* Run stable diffusion compile test in subprocess.

* style

* Temporarily trigger on pr to test.

* Revert "Temporarily trigger on pr to test."

This reverts commit 82d76868ddf9cc634a9f14b2b0aef1d5433cd750.

* up

* fix more

* Apply suggestions from code review

* fix more

* fix more

* Check it

* Remove 16:8

* fix more

* fix more

* fix more

* up

* up

* Test only stable diffusion

* Test only two files

* up

* Try out spinning up processes that can be killed

* up

* Apply suggestions from code review

* up

* up

* [2064]: Add stochastic sampler

* [2064]: Add stochastic sampler

* [2064]: Add stochastic sampler

* [2064]: Add stochastic sampler

* [2064]: Add stochastic sampler

* [2064]: Add stochastic sampler

* [2064]: Add stochastic sampler

* Review comments

* [Review comment]: Add is_torchsde_available()

* [Review comment]: Test and docs

* [Review comment]

* [Review comment]

* [Review comment]

* [Review comment]

* [Review comment]

---------
Co-authored-by: njindal <njindal@adobe.com>

* Update pipeline_stable_diffusion_inpaint_legacy.py

* fix preprocessing of Pil images with adequate batch size

* revert map

* add tests

* reformat

* Update test_stable_diffusion_inpaint_legacy.py

* Update test_stable_diffusion_inpaint_legacy.py

* Update test_stable_diffusion_inpaint_legacy.py

* Update test_stable_diffusion_inpaint_legacy.py

* next try to fix the style

* wth is this

* Update testing_utils.py

* Update testing_utils.py

* Update test_stable_diffusion_inpaint_legacy.py

* Update test_stable_diffusion_inpaint_legacy.py

* Update test_stable_diffusion_inpaint_legacy.py

* Update test_stable_diffusion_inpaint_legacy.py

* Update test_stable_diffusion_inpaint_legacy.py

* Update test_stable_diffusion_inpaint_legacy.py

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

* Workaround for saving dynamo-wrapped models.

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

* Apply workaround when overriding pipeline components.

* Ensure the correct config.json is saved to disk.

Instead of the dynamo class.

* Save correct module (not compiled one)

* Add test

* style

* fix docstrings

* Go back to using string comparisons.

PyTorch CPU does not have _dynamo.

* Simple test for save_pretrained of compiled models.

* Helper function to test whether module is compiled.

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

* initial TokenEncoder and ContinuousEncoder

* initial modules

* added ContinuousContextTransformer

* fix copy paste error

* use numpy for get_sequence_length

* initial terminal relative positional encodings

* fix weights keys

* fix assert

* cross attend style: concat encodings

* make style

* concat once

* fix formatting

* Initial SpectrogramPipeline

* fix input_tokens

* make style

* added mel output

* ignore weights for config

* move mel to numpy

* import pipeline

* fix class names and import

* moved models to models folder

* import ContinuousContextTransformer and SpectrogramDiffusionPipeline

* initial spec diffusion converstion script

* renamed config to t5config

* added weight loading

* use arguments instead of t5config

* broadcast noise time to batch dim

* fix call

* added scale_to_features

* fix weights

* transpose laynorm weight

* scale is a vector

* scale the query outputs

* added comment

* undo scaling

* undo depth_scaling

* inital get_extended_attention_mask

* attention_mask is none in self-attention

* cleanup

* manually invert attention

* nn.linear need bias=False

* added T5LayerFFCond

* remove to fix conflict

* make style and dummy

* remove unsed variables

* remove predict_epsilon

* Move accelerate to a soft-dependency (#1134)

* finish

* finish

* Update src/diffusers/modeling_utils.py

* Update src/diffusers/pipeline_utils.py
Co-authored-by: Anton Lozhkov <anton@huggingface.co>

* more fixes

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

* fix order

* added initial midi to note token data pipeline

* added int to int tokenizer

* remove duplicate

* added logic for segments

* add melgan to pipeline

* move autoregressive gen into pipeline

* added note_representation_processor_chain

* fix dtypes

* remove immutabledict req

* initial doc

* use np.where

* require note_seq

* fix typo

* update dependency

* added note-seq to test

* added is_note_seq_available

* fix import

* added toc

* added example usage

* undo for now

* moved docs

* fix merge

* fix imports

* predict first segment

* avoid un-needed copy to and from cpu

* make style

* Copyright

* fix style

* add test and fix inference steps

* remove bogus files

* reorder models

* up

* remove transformers dependency

* make work with diffusers cross attention

* clean more

* remove @

* improve further

* up

* uP

* Apply suggestions from code review

* Update tests/pipelines/spectrogram_diffusion/test_spectrogram_diffusion.py

* loop over all tokens

* make style

* Added a section on the model

* fix formatting

* grammer

* formatting

* make fix-copies

* Update src/diffusers/pipelines/__init__.py
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* Update src/diffusers/pipelines/spectrogram_diffusion/pipeline_spectrogram_diffusion.py
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* added callback ad optional ionnx

* do not squeeze batch dim

* clean up more

* upload

* convert jax to nnumpy

* make style

* fix warning

* make fix-copies

* fix warning

* add initial fast tests

* add initial pipeline_params

* eval mode due to dropout

* skip batch tests as pipeline runs on a single file

* make style

* fix relative path

* fix doc tests

* Update src/diffusers/models/t5_film_transformer.py
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* Update src/diffusers/models/t5_film_transformer.py
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* Update docs/source/en/api/pipelines/spectrogram_diffusion.mdx
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* Update tests/pipelines/spectrogram_diffusion/test_spectrogram_diffusion.py
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* Update tests/pipelines/spectrogram_diffusion/test_spectrogram_diffusion.py
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* Update tests/pipelines/spectrogram_diffusion/test_spectrogram_diffusion.py
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* Update tests/pipelines/spectrogram_diffusion/test_spectrogram_diffusion.py
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* add MidiProcessor

* format

* fix org

* Apply suggestions from code review

* Update tests/pipelines/spectrogram_diffusion/test_spectrogram_diffusion.py

* make style

* pin protobuf to <4

* fix formatting

* white space

* tensorboard needs protobuf

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

* [MS Text To Video} Add first text to video

* upload

* make first model example

* match unet3d params

* make sure weights are correcctly converted

* improve

* forward pass works, but diff result

* make forward work

* fix more

* finish

* refactor video output class.

* feat: add support for a video export utility.

* fix: opencv availability check.

* run make fix-copies.

* add: docs for the model components.

* add: standalone pipeline doc.

* edit docstring of the pipeline.

* add: right path to TransformerTempModel

* add: first set of tests.

* complete fast tests for text to video.

* fix bug

* up

* three fast tests failing.

* add: note on slow tests

* make work with all schedulers

* apply styling.

* add slow tests

* change file name

* update

* more correction

* more fixes

* finish

* up

* Apply suggestions from code review

* up

* finish

* make copies

* fix pipeline tests

* fix more tests

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

* apply suggestions

* up

* revert

---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

* add docs

* correct

* finish

* Apply suggestions from code review
Co-authored-by: Will Berman <wlbberman@gmail.com>
Co-authored-by: YiYi Xu <yixu310@gmail.com>

* update deps table

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

---------
Co-authored-by: Will Berman <wlbberman@gmail.com>
Co-authored-by: YiYi Xu <yixu310@gmail.com>
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

* attend and excite batch test causing timeouts

* pix2pix tests, no write to fs

* finish

* Apply suggestions from code review

* fix indent and import error in test_stable_diffusion_depth

---------
Co-authored-by: William Berman <WLBberman@gmail.com>

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

* before running make style

* remove left overs from flake8

* finish

* make fix-copies

* final fix

* more fixes

* make tests deterministic

* run slow tests

* prepare for testing

* finish

* refactor

* add print statements

* finish more

* correct some test failures

* more fixes

* set up to correct tests

* more corrections

* up

* fix more

* more prints

* add

* up

* up

* up

* uP

* uP

* more fixes

* uP

* up

* up

* up

* up

* fix more

* up

* up

* clean tests

* up

* up

* up

* more fixes

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

* make

* correct

* finish

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

* [WIP] Nightly integration tests

* initial SD tests

* update SD slow tests

* style

* repaint

* ImageVariations

* style

* finish imgvar

* img2img tests

* debug

* inpaint 1.5

* inpaint legacy

* torch isn't happy about deterministic ops

* allclose -> max diff for shorter logs

* add SD2

* debug

* Update tests/pipelines/stable_diffusion_2/test_stable_diffusion.py
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* Update tests/pipelines/stable_diffusion/test_stable_diffusion.py
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* fix refs

* Update src/diffusers/utils/testing_utils.py
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

* fix refs

* remove debug
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

* improve test precision

get tests passing with greater precision using lewington images

* make old numpy load function a wrapper around a more flexible numpy loading function

* adhere to black formatting

* add more black formatting

* adhere to isort

* loosen precision and replace path
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* Reorganize pipeline tests

* fix vq

Check if MPS backend is registered before calling is_available()

[DiffusionPipeline.from_pretrained] add warning when passing unused kwargs

* pass norm_num_groups param and add tests

* set resnet_groups for FlaxUNetMidBlock2D

* fixed docstrings

* fixed typo

* using is_flax_available util and created require_flax decorator

* [Custom Pipelines]

* uP

* make style

* finish

* finish

* remove ipdb

* upload

* fix

* finish docs

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

* finish

* final uploads

* remove unnecessary test
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>
Co-authored-by: apolinario <joaopaulo.passos@gmail.com>

* [Utils] Add deprecate function

* up

* up

* uP

* up

* up

* up

* up

* uP

* up

* fix

* up

* move to deprecation utils file

* fix

* fix

* fix more

* make_reports

* add test utils

* style

* style

* Finally fix the image-based SD tests

* Remove autocast

* Remove autocast in image tests

* [MPS] Make sure it doesn't break torch < 1.12

* up

* Initial support for mps in Stable Diffusion pipeline.

* Initial "warmup" implementation when using mps.

* Make some deterministic tests pass with mps.

* Disable training tests when using mps.

* SD: generate latents in CPU then move to device.

This is especially important when using the mps device, because
generators are not supported there. See for example
https://github.com/pytorch/pytorch/issues/84288.

In addition, the other pipelines seem to use the same approach: generate
the random samples then move to the appropriate device.

After this change, generating an image in MPS produces the same result
as when using the CPU, if the same seed is used.

* Remove prints.

* Pass AutoencoderKL test_output_pretrained with mps.

Sampling from `posterior` must be done in CPU.

* Style

* Do not use torch.long for log op in mps device.

* Perform incompatible padding ops in CPU.

UNet tests now pass.
See https://github.com/pytorch/pytorch/issues/84535



* Style: fix import order.

* Remove unused symbols.

* Remove MPSWarmupMixin, do not apply automatically.

We do apply warmup in the tests, but not during normal use.
This adopts some PR suggestions by @patrickvonplaten.

* Add comment for mps fallback to CPU step.

* Add README_mps.md for mps installation and use.

* Apply `black` to modified files.

* Restrict README_mps to SD, show measures in table.

* Make PNDM indexing compatible with mps.

Addresses #239.

* Do not use float64 when using LDMScheduler.

Fixes #358.

* Fix typo identified by @patil-suraj
Co-authored-by: Suraj Patil <surajp815@gmail.com>

* Adapt example to new output style.

* Restore 1:1 results reproducibility with CompVis.

However, mps latents need to be generated in CPU because generators
don't work in the mps device.

* Move PyTorch nightly to requirements.

* Adapt `test_scheduler_outputs_equivalence` ton MPS.

* mps: skip training tests instead of ignoring silently.

* Make VQModel tests pass on mps.

* mps ddim tests: warmup, increase tolerance.

* ScoreSdeVeScheduler indexing made mps compatible.

* Make ldm pipeline tests pass using warmup.

* Style

* Simplify casting as suggested in PR.

* Add Known Issues to readme.

* `isort` import order.

* Remove _mps_warmup helpers from ModelMixin.

And just make changes to the tests.

* Skip tests using unittest decorator for consistency.

* Remove temporary var.

* Remove spurious blank space.

* Remove unused symbol.

* Remove README_mps.
Co-authored-by: Suraj Patil <surajp815@gmail.com>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>