GitLab

* fix tests

* Fix more

* more

* [Scheduler] Move predict epsilon to init

* up

* uP

* uP

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

* up
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

* Schedulers: don't use float64 on mps

* Test set_timesteps() on device (float schedulers).

* SD pipeline: use device in set_timesteps.

* SD in-painting pipeline: use device in set_timesteps.

* Tests: fix mps crashes.

* Skip test_load_pipeline_from_git on mps.

Not compatible with float16.

* Use device.type instead of str in Euler schedulers.

* fix noise device in ddim sched

* fix typo

* self.device -> device

* remove duplicated if

* use str device

* don't use str for device

* add dpmsolver discrete pytorch scheduler

* fix some typos in dpm-solver pytorch

* add dpm-solver pytorch in stable-diffusion pipeline

* add jax/flax version dpm-solver

* change code style

* change code style

* add docs

* add `add_noise` method for dpmsolver

* add pytorch unit test for dpmsolver

* add dummy object for pytorch dpmsolver

* Update src/diffusers/schedulers/scheduling_dpmsolver_discrete.py
Co-authored-by: Suraj Patil <surajp815@gmail.com>

* Update tests/test_config.py
Co-authored-by: Suraj Patil <surajp815@gmail.com>

* Update tests/test_config.py
Co-authored-by: Suraj Patil <surajp815@gmail.com>

* resolve the code comments

* rename the file

* change class name

* fix code style

* add auto docs for dpmsolver multistep

* add more explanations for the stabilizing trick (for steps < 15)

* delete the dummy file

* change the API name of predict_epsilon, algorithm_type and solver_type

* add compatible lists
Co-authored-by: Suraj Patil <surajp815@gmail.com>

* Add CycleDiffusion pipeline for Stable Diffusion

* Add the option of passing noise to DDIMScheduler

Add the option of providing the noise itself to DDIMScheduler, instead of the random seed generator.

* Update README.md

* Update README.md

* Update pipeline_stable_diffusion_cycle_diffusion.py

* Update pipeline_stable_diffusion_cycle_diffusion.py

* Update pipeline_stable_diffusion_cycle_diffusion.py

* Update pipeline_stable_diffusion_cycle_diffusion.py

* Update scheduling_ddim.py

* Update import format

* Update pipeline_stable_diffusion_cycle_diffusion.py

* Update scheduling_ddim.py

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

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

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

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

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

* Update scheduling_ddim.py

* Update scheduling_ddim.py

* Update scheduling_ddim.py

* add two tests

* Update pipeline_stable_diffusion_cycle_diffusion.py

* Update pipeline_stable_diffusion_cycle_diffusion.py

* Update README.md

* Rename pipeline name as suggested in the latest reviewer comment

* Update test_pipelines.py

* Update test_pipelines.py

* Update test_pipelines.py

* Update pipeline_stable_diffusion_cycle_diffusion.py

* Remove the generator

This generator does not control all randomness during sampling, which can be misleading.

* Update optimal hyperparameters

* Update src/diffusers/pipelines/stable_diffusion/README.md
Co-authored-by: Suraj Patil <surajp815@gmail.com>

* Update src/diffusers/pipelines/stable_diffusion/README.md
Co-authored-by: Suraj Patil <surajp815@gmail.com>

* Update src/diffusers/pipelines/stable_diffusion/README.md
Co-authored-by: Suraj Patil <surajp815@gmail.com>

* Apply suggestions from code review

* uP

* Update src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_cycle_diffusion.py
Co-authored-by: Suraj Patil <surajp815@gmail.com>

* up

* up

* Replace assert with ValueError

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

* Bump to 0.8.0.dev0

* deprecate int timesteps

* style

* handle device for randn in euler step

* convert device to str

* Changes for VQ-diffusion VQVAE

Add specify dimension of embeddings to VQModel:
`VQModel` will by default set the dimension of embeddings to the number
of latent channels. The VQ-diffusion VQVAE has a smaller
embedding dimension, 128, than number of latent channels, 256.

Add AttnDownEncoderBlock2D and AttnUpDecoderBlock2D to the up and down
unet block helpers. VQ-diffusion's VQVAE uses those two block types.

* Changes for VQ-diffusion transformer

Modify attention.py so SpatialTransformer can be used for
VQ-diffusion's transformer.

SpatialTransformer:
- Can now operate over discrete inputs (classes of vector embeddings) as well as continuous.
- `in_channels` was made optional in the constructor so two locations where it was passed as a positional arg were moved to kwargs
- modified forward pass to take optional timestep embeddings

ImagePositionalEmbeddings:
- added to provide positional embeddings to discrete inputs for latent pixels

BasicTransformerBlock:
- norm layers were made configurable so that the VQ-diffusion could use AdaLayerNorm with timestep embeddings
- modified forward pass to take optional timestep embeddings

CrossAttention:
- now may optionally take a bias parameter for its query, key, and value linear layers

FeedForward:
- Internal layers are now configurable

ApproximateGELU:
- Activation function in VQ-diffusion's feedforward layer

AdaLayerNorm:
- Norm layer modified to incorporate timestep embeddings

* Add VQ-diffusion scheduler

* Add VQ-diffusion pipeline

* Add VQ-diffusion convert script to diffusers

* Add VQ-diffusion dummy objects

* Add VQ-diffusion markdown docs

* Add VQ-diffusion tests

* some renaming

* some fixes

* more renaming

* correct

* fix typo

* correct weights

* finalize

* fix tests

* Apply suggestions from code review
Co-authored-by: Anton Lozhkov <aglozhkov@gmail.com>

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

* finish

* finish

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

* feat: add repaint

* fix: fix quality check with `make fix-copies`

* fix: remove old unnecessary arg

* chore: change default to DDPM (looks better in experiments)

* ".to(device)" changed to "device="
Co-authored-by: Anton Lozhkov <aglozhkov@gmail.com>

* make generator device-specific
Co-authored-by: Anton Lozhkov <aglozhkov@gmail.com>

* make generator device-specific and change shape
Co-authored-by: Anton Lozhkov <aglozhkov@gmail.com>

* fix: add preprocessing for image and mask
Co-authored-by: Anton Lozhkov <aglozhkov@gmail.com>

* fix: update test
Co-authored-by: Anton Lozhkov <aglozhkov@gmail.com>

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

* Add docs and examples

* Fix toctree
Co-authored-by: fja <fja@zurich.ibm.com>
Co-authored-by: Anton Lozhkov <aglozhkov@gmail.com>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: Anton Lozhkov <anton@huggingface.co>

* Fix equality test for ddim and ddpm

* add docs for use_clipped_model_output in DDIM

* fix inline comment

* reorder imports in test_pipelines.py

* Ignore use_clipped_model_output if scheduler doesn't take it

* [Better scheduler docs] Improve usage examples of schedulers

* finish

* fix warnings and add test

* finish

* more replacements

* adapt fast tests hf token

* correct more

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

* Integrate compatibility with euler
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

* k-diffusion-euler

* make style make quality

* make fix-copies

* fix tests for euler a

* Update src/diffusers/schedulers/scheduling_euler_ancestral_discrete.py
Co-authored-by: Anton Lozhkov <aglozhkov@gmail.com>

* Update src/diffusers/schedulers/scheduling_euler_ancestral_discrete.py
Co-authored-by: Anton Lozhkov <aglozhkov@gmail.com>

* Update src/diffusers/schedulers/scheduling_euler_discrete.py
Co-authored-by: Anton Lozhkov <aglozhkov@gmail.com>

* Update src/diffusers/schedulers/scheduling_euler_discrete.py
Co-authored-by: Anton Lozhkov <aglozhkov@gmail.com>

* remove unused arg and method

* update doc

* quality

* make flake happy

* use logger instead of warn

* raise error instead of deprication

* don't require scipy

* pass generator in step

* fix tests

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

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

* remove unused generator

* pass generator as extra_step_kwargs

* update tests

* pass generator as kwarg

* pass generator as kwarg

* quality

* fix test for lms

* fix tests
Co-authored-by: patil-suraj <surajp815@gmail.com>
Co-authored-by: Anton Lozhkov <aglozhkov@gmail.com>
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* Add failing test for #940.

* Do not use torch.float64 in mps.

* style

* Temporarily skip add_noise for IPNDMScheduler.

Until #990 is addressed.

* Fix additional float64 error in mps.

* Improve add_noise test

* Slight edit – I think it's clearer this way.

* Add failing test for #940.

* Do not use torch.float64 in mps.

* style

* Temporarily skip add_noise for IPNDMScheduler.

Until #990 is addressed.

* 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>

* 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>

* 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

* Bump to 0.6.0.dev0

* Deprecate tensor_format and .samples

* style

* upd

* upd

* style

* sample -> images

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

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

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

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

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

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

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

* update flax scheduler API

* remoev set format

* fix call to scale_model_input

* update flax pndm

* use int32

* update docstr

* add sigmoid betas

* convert to torch

* add comment on source

* handle dtype in vae and image2image pipeline

* handle dtype in add noise

* don't modify vae and pipeline

* remove the if

Otherwise, it crashes when eta > 0 with float16.

This reverts commit 2e209c30.

Temporarily remove Flax modules from the public API

* Better steps deprecation for LMS

* upd

* Add back-compatibility to LMS timesteps

* style

* init

* improve add_noise

* [debug start] run slow test

* [debug end]

* quick revert

* Add docstrings and warnings + API tests

* Make the warning less spammy

* pytorch timesteps

* style

* get rid of if-else

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

* Update links in schedulers README.md

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

* [Utils] Add deprecate function

* up

* up

* uP

* up

* up

* up

* up

* uP

* up

* fix

* up

* move to deprecation utils file

* fix

* fix

* fix more

* Don't use `load_state_dict` if torch is not installed.

* Define `SchedulerOutput` to use torch or flax arrays.

* Don't import LMSDiscreteScheduler without torch.

* Create distinct FlaxSchedulerOutput.

* Additional changes required for FlaxSchedulerMixin

* Do not import torch pipelines in Flax.

* Revert "Define `SchedulerOutput` to use torch or flax arrays."

This reverts commit f653140134b74d9ffec46d970eb46925fe3a409d.

* Prefix Flax scheduler outputs for consistency.

* make style

* FlaxSchedulerOutput is now a dataclass.

* Don't use f-string without placeholders.

* Add blank line.

* Style (docstrings)

* Flax: add shape argument to set_timesteps

* style

* initial commit

* make UNet stream capturable

* try to fix noise_pred value

* remove cuda graph and keep NB

* non blocking unet with PNDMScheduler

* make timesteps np arrays for pndm scheduler
because lists don't get formatted to tensors in `self.set_format`

* make max async in pndm

* use channel last format in unet

* avoid moving timesteps device in each unet call

* avoid memcpy op in `get_timestep_embedding`

* add `channels_last` kwarg to `DiffusionPipeline.from_pretrained`

* update TODO

* replace `channels_last` kwarg with `memory_format` for more generality

* revert the channels_last changes to leave it for another PR

* remove non_blocking when moving input ids to device

* remove blocking from all .to() operations at beginning of pipeline

* fix merging

* fix merging

* model can run in other precisions without autocast

* attn refactoring

* Revert "attn refactoring"

This reverts commit 0c70c0e189cd2c4d8768274c9fcf5b940ee310fb.

* remove restriction to run conv_norm in fp32

* use `baddbmm` instead of `matmul`for better in attention for better perf

* removing all reshapes to test perf

* Revert "removing all reshapes to test perf"

This reverts commit 006ccb8a8c6bc7eb7e512392e692a29d9b1553cd.

* add shapes comments

* hardcore whats needed for jitting

* Revert "hardcore whats needed for jitting"

This reverts commit 2fa9c698eae2890ac5f8e367ca80532ecf94df9a.

* Revert "remove restriction to run conv_norm in fp32"

This reverts commit cec592890c32da3d1b78d38b49e4307aedf459b9.

* revert using baddmm in attention's forward

* cleanup comment

* remove restriction to run conv_norm in fp32. no quality loss was noticed

This reverts commit cc9bc1339c998ebe9e7d733f910c6d72d9792213.

* add more optimizations techniques to docs

* Revert "add shapes comments"

This reverts commit 31c58eadb8892f95478cdf05229adf678678c5f4.

* apply suggestions

* make quality

* apply suggestions

* styling

* `scheduler.timesteps` are now arrays so we dont need .to()

* remove useless .type()

* use mean instead of max in `test_stable_diffusion_inpaint_pipeline_k_lms`

* move scheduler timestamps to correct device if tensors

* add device to `set_timesteps` in LMSD scheduler

* `self.scheduler.set_timesteps` now uses device arg for schedulers that accept it

* quick fix

* styling

* remove kwargs from schedulers `set_timesteps`

* revert to using max in K-LMS inpaint pipeline test

* Revert "`self.scheduler.set_timesteps` now uses device arg for schedulers that accept it"

This reverts commit 00d5a51e5c20d8d445c8664407ef29608106d899.

* move timesteps to correct device before loop in SD pipeline

* apply previous fix to other SD pipelines

* UNet now accepts tensor timesteps even on wrong device, to avoid errors
- it shouldnt affect performance if timesteps are alrdy on correct device
- it does slow down performance if they're on the wrong device

* fix pipeline when timesteps are arrays with strides

* correcting the beta value assignment

* updating DDIM and LMSDiscreteFlax schedulers

* bringing back the changes that were lost as part of main branch merge