* 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>
* Fix tqdm and OOM
* tqdm auto
* tqdm is still spamming try to disable it altogether
* rather just set the pipe config, to keep the global tqdm clean
* style
* 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>
* 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>
* 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>
* 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>
* 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
* [Vae and AutoencoderKL clean]
* save intermediate finished work
* more progress
* more progress
* finish modeling code
* save intermediate
* finish
* Correct tests
* work in progress, fixing tests for numpy and make deterministic
* make tests pass via pytorch
* make pytorch == numpy test cleaner
* change default tensor format pndm --> pt
* up
* change model name
* renaming
* more changes
* up
* up
* up
* save checkpoint
* finish api / naming
* finish config renaming
* rename all weights
* finish really
