* add accelerate to load models with smaller memory footprint
* remove low_cpu_mem_usage as it is reduntant
* move accelerate init weights context to modelling utils
* add test to ensure results are the same when loading with accelerate
* add tests to ensure ram usage gets lower when using accelerate
* move accelerate logic to single snippet under modelling utils and remove it from configuration utils
* format code using to pass quality check
* fix imports with isor
* add accelerate to test extra deps
* only import accelerate if device_map is set to auto
* move accelerate availability check to diffusers import utils
* format code
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
* Add callback parameters for Stable Diffusion pipelines
Signed-off-by: James R T <jamestiotio@gmail.com>
* Lint code with `black --preview`
Signed-off-by: James R T <jamestiotio@gmail.com>
* Refactor callback implementation for Stable Diffusion pipelines
* Fix missing imports
Signed-off-by: James R T <jamestiotio@gmail.com>
* Fix documentation format
Signed-off-by: James R T <jamestiotio@gmail.com>
* Add kwargs parameter to standardize with other pipelines
Signed-off-by: James R T <jamestiotio@gmail.com>
* Modify Stable Diffusion pipeline callback parameters
Signed-off-by: James R T <jamestiotio@gmail.com>
* Remove useless imports
Signed-off-by: James R T <jamestiotio@gmail.com>
* Change types for timestep and onnx latents
* Fix docstring style
* Return decode_latents and run_safety_checker back into __call__
* Remove unused imports
* Add intermediate state tests for Stable Diffusion pipelines
Signed-off-by: James R T <jamestiotio@gmail.com>
* Fix intermediate state tests for Stable Diffusion pipelines
Signed-off-by: James R T <jamestiotio@gmail.com>
Signed-off-by: James R T <jamestiotio@gmail.com>
* Allow resolutions that are not multiples of 64
* ran black
* fix bug
* add test
* more explanation
* more comments
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
* pytorch only schedulers
* fix style
* remove match_shape
* pytorch only ddpm
* remove SchedulerMixin
* remove numpy from karras_ve
* fix types
* remove numpy from lms_discrete
* remove numpy from pndm
* fix typo
* remove mixin and numpy from sde_vp and ve
* remove remaining tensor_format
* fix style
* sigmas has to be torch tensor
* removed set_format in readme
* remove set format from docs
* remove set_format from pipelines
* update tests
* fix typo
* continue to use mixin
* fix imports
* removed unsed imports
* match shape instead of assuming image shapes
* remove import typo
* update call to add_noise
* use math instead of numpy
* fix t_index
* removed commented out numpy tests
* timesteps needs to be discrete
* cast timesteps to int in flax scheduler too
* fix device mismatch issue
* small fix
* Update src/diffusers/schedulers/scheduling_pndm.py
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
* add grad ckpt to downsample blocks
* make it work
* don't pass gradient_checkpointing to upsample block
* add tests for UNet2DConditionModel
* add test_gradient_checkpointing
* add gradient_checkpointing for up and down blocks
* add functions to enable and disable grad ckpt
* remove the forward argument
* better naming
* make supports_gradient_checkpointing private
* Unify offset configuration in DDIM and PNDM schedulers
* Format
Add missing variables
* Fix pipeline test
* Update src/diffusers/schedulers/scheduling_ddim.py
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
* Default set_alpha_to_one to false
* Format
* Add tests
* Format
* add deprecation warning
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
* Fix typos
* Add a typo check action
* Fix a bug
* Changed to manual typo check currently
Ref: https://github.com/huggingface/diffusers/pull/483#pullrequestreview-1104468010
Co-authored-by: Anton Lozhkov <aglozhkov@gmail.com>
* Removed a confusing message
* Renamed "nin_shortcut" to "in_shortcut"
* Add memo about NIN
Co-authored-by: Anton Lozhkov <aglozhkov@gmail.com>
* beta never changes removed from state
* fix typos in docs
* removed unused var
* initial ddim flax scheduler
* import
* added dummy objects
* fix style
* fix typo
* docs
* fix typo in comment
* set return type
* added flax ddom
* fix style
* remake
* pass PRNG key as argument and split before use
* fix doc string
* use config
* added flax Karras VE scheduler
* make style
* fix dummy
* fix ndarray type annotation
* replace returns a new state
* added lms_discrete scheduler
* use self.config
* add_noise needs state
* use config
* use config
* docstring
* added flax score sde ve
* fix imports
* fix typos
* initial attempt at solving
* fix pndm power of 3 inference_step
* add power of 3 test
* fix index in pndm test, remove ddim test
* add comments, change to round()
* update expected results of slow tests
* relax sum and mean tests
* Print shapes when reporting exception
* formatting
* fix sentence
* relax test_stable_diffusion_fast_ddim for gpu fp16
* relax flakey tests on GPU
* added comment on large tolerences
* black
* format
* set scheduler seed
* added generator
* use np.isclose
* set num_inference_steps to 50
* fix dep. warning
* update expected_slice
* preprocess if image
* updated expected results
* updated expected from CI
* pass generator to VAE
* undo change back to orig
* use orignal
* revert back the expected on cpu
* revert back values for CPU
* more undo
* update result after using gen
* update mean
* set generator for mps
* update expected on CI server
* undo
* use new seed every time
* cpu manual seed
* reduce num_inference_steps
* style
* use generator for randn
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
* 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
* clean ddpm api to match ddim
* correct ve sde class
* update pipeline API for ve sde
* make style
* Apply suggestions from code review
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
* improve comments for sde_ve scheduler, init tests
* more comments, tweaking pipelines
* timesteps --> num_training_timesteps, some comments
* merge cpu test, add m1 data
* fix scheduler tests with num_train_timesteps
* make np compatible, add tests for sde ve
* minor default variable fixes
* make style and fix-copies
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
Kashif Rasul