GitLab

* make sure fp16 runs well

* add fp16 test for superes

* Update src/diffusers/models/unet_2d.py
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

* gen on cuda

* always run fast inferecne test on cpu

* run on cpu
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

* fix non square images with UNet2DModel and DDIM/DDPM pipelines

* fix unet_2d `sample_size` docstring

* update pipeline tests for unet uncond
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* use memory_efficient_attention by default

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

* Add pipeline_stable_diffusion_safe.py to pipelines

* Fix repository consistency

Ran make fix-copies after adding new pipline

* Add Paper/Equation reference for parameters to doc string

* Ensure code style and quality

* Perform code refactoring

* Fix copies inherited from merge with huggingface/main

* Add docs

* Fix code style

* Fix errors in documentation

* Fix refactoring error

* remove debugging print statement

* added Safe Latent Diffusion tests

* Fix style

* Fix style

* Add pre-defined safety configurations

* Fix line-break

* fix some tests

* finish

* Change safety checker

* Add missing safety_checker.py file

* Remove unused imports
Co-authored-by: PatrickSchrML <patrick_schramowski@hotmail.de>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

perf: prefer batched matmuls for attention. added fast-path to Decoder when num_heads=1

Handle batches and Tensors in `pipeline_stable_diffusion_inpaint.py:prepare_mask_and_masked_image` (#1003)

* Handle batches and Tensors in `prepare_mask_and_masked_image`

* `blackfy`
upgrade `black`

* handle mask as `np.array`

* add docstring

* revert `black` changes with smaller line length

* missing ValueError in docstring

* raise `TypeError` for image as tensor but not mask

* typo in mask shape selection

* check for batch dim

* fix: wrong indentation

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

* support negative prompts in sd jax pipeline

* pass batched neg_prompt

* only encode when negative prompt is None
Co-authored-by: Juan Acevedo <jfacevedo@google.com>

* Add legacy inpainting pipeline compatibility for onnx

* remove commented out line

* Add onnx legacy inpainting test

* Fix slow decorators

* pep8 styling

* isort styling

* dummy object

* ordering consistency

* style

* docstring styles

* Refactor common prompt encoding pattern

* Update tests to permanent repository home

* support all available schedulers until ONNX IO binding is available
Co-authored-by: Anton Lozhkov <aglozhkov@gmail.com>

* updated styling from PR suggested feedback
Co-authored-by: Anton Lozhkov <aglozhkov@gmail.com>

Casting `self.sigmas` into a different dtype (the one of original_samples) is not advisable. In my img2img pipeline this leads to a long running time in the  `integrate.quad` call later on- by long I mean more than 10x slower.
Co-authored-by: Anton Lozhkov <anton@huggingface.co>

* Avoid nested `# Copied from` statements during `make fix-copies`

* style

* inpaint fix k lms

* onnox as well

* up

[FLAX] Fix loading scheduler from subfolder

* make fix copies again

* Fix typo

* [Custom pipeline] Easier loading of local pipelines

* upgrade black

* integrate ort

* use return_dict=False

* revert unet return value change

* revert unet return value change

* add note to readme

* adjust readme

* add contact

* `make style`
Co-authored-by: Prathik Rao <prathikrao@microsoft.com>
Co-authored-by: Anton Lozhkov <anton@huggingface.co>

* doc string args shape fix

* fix styling

* vq diffusion classifier free sampling

* correct

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

mutli GPU support

* Better error message for transformers dummy

* [PIL] Better deprecation functionality

* up

* being tests

* fix model ids

* don't use safety checker in tests

* add im2img2 tests

* fix integration tests

* integration tests

* style

* add sentencepiece in test dep

* quality

* 4 decimalk points

* fix im2img test

* increase the tok slightly

* add conversion script for vae

* up

* up

* some fixes

* add text model

* use the correct config

* add docs

* move model in it's own file

* move model in its own file

* pass attenion mask to text encoder

* pass attn mask to uncond inputs

* quality

* fix image2image

* add imag2image in init

* fix import

* fix one more import

* fix import, dummy objetcs

* fix copied from

* up

* finish
Co-authored-by: patil-suraj <surajp815@gmail.com>

* add conversion script for vae

* uP

* uP

* more changes

* push

* up

* finish again

* up

* up

* up

* up

* finish

* up

* uP

* up

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

* up

* up
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>
Co-authored-by: Anton Lozhkov <anton@huggingface.co>
Co-authored-by: Suraj Patil <surajp815@gmail.com>

Update README.md

* Fix documentation typo

* Fix other typo

* re-add RL model code

* match model forward api

* add register_to_config, pass training tests

* fix tests, update forward outputs

* remove unused code, some comments

* add to docs

* remove extra embedding code

* unify time embedding

* remove conv1d output sequential

* remove sequential from conv1dblock

* style and deleting duplicated code

* clean files

* remove unused variables

* clean variables

* add 1d resnet block structure for downsample

* rename as unet1d

* fix renaming

* rename files

* add get_block(...) api

* unify args for model1d like model2d

* minor cleaning

* fix docs

* improve 1d resnet blocks

* fix tests, remove permuts

* fix style

* add output activation

* rename flax blocks file

* Add Value Function and corresponding example script to Diffuser implementation (#884)

* valuefunction code

* start example scripts

* missing imports

* bug fixes and placeholder example script

* add value function scheduler

* load value function from hub and get best actions in example

* very close to working example

* larger batch size for planning

* more tests

* merge unet1d changes

* wandb for debugging, use newer models

* success!

* turns out we just need more diffusion steps

* run on modal

* merge and code cleanup

* use same api for rl model

* fix variance type

* wrong normalization function

* add tests

* style

* style and quality

* edits based on comments

* style and quality

* remove unused var

* hack unet1d into a value function

* add pipeline

* fix arg order

* add pipeline to core library

* community pipeline

* fix couple shape bugs

* style

* Apply suggestions from code review
Co-authored-by: Nathan Lambert <nathan@huggingface.co>

* update post merge of scripts

* add mdiblock / outblock architecture

* Pipeline cleanup (#947)

* valuefunction code

* start example scripts

* missing imports

* bug fixes and placeholder example script

* add value function scheduler

* load value function from hub and get best actions in example

* very close to working example

* larger batch size for planning

* more tests

* merge unet1d changes

* wandb for debugging, use newer models

* success!

* turns out we just need more diffusion steps

* run on modal

* merge and code cleanup

* use same api for rl model

* fix variance type

* wrong normalization function

* add tests

* style

* style and quality

* edits based on comments

* style and quality

* remove unused var

* hack unet1d into a value function

* add pipeline

* fix arg order

* add pipeline to core library

* community pipeline

* fix couple shape bugs

* style

* Apply suggestions from code review

* clean up comments

* convert older script to using pipeline and add readme

* rename scripts

* style, update tests

* delete unet rl model file

* remove imports in src
Co-authored-by: Nathan Lambert <nathan@huggingface.co>

* Update src/diffusers/models/unet_1d_blocks.py

* Update tests/test_models_unet.py

* RL Cleanup v2 (#965)

* valuefunction code

* start example scripts

* missing imports

* bug fixes and placeholder example script

* add value function scheduler

* load value function from hub and get best actions in example

* very close to working example

* larger batch size for planning

* more tests

* merge unet1d changes

* wandb for debugging, use newer models

* success!

* turns out we just need more diffusion steps

* run on modal

* merge and code cleanup

* use same api for rl model

* fix variance type

* wrong normalization function

* add tests

* style

* style and quality

* edits based on comments

* style and quality

* remove unused var

* hack unet1d into a value function

* add pipeline

* fix arg order

* add pipeline to core library

* community pipeline

* fix couple shape bugs

* style

* Apply suggestions from code review

* clean up comments

* convert older script to using pipeline and add readme

* rename scripts

* style, update tests

* delete unet rl model file

* remove imports in src

* add specific vf block and update tests

* style

* Update tests/test_models_unet.py
Co-authored-by: Nathan Lambert <nathan@huggingface.co>

* fix quality in tests

* fix quality style, split test file

* fix checks / tests

* make timesteps closer to main

* unify block API

* unify forward api

* delete lines in examples

* style

* examples style

* all tests pass

* make style

* make dance_diff test pass

* Refactoring RL PR (#1200)

* init file changes

* add import utils

* finish cleaning files, imports

* remove import flags

* clean examples

* fix imports, tests for merge

* update readmes

* hotfix for tests

* quality

* fix some tests

* change defaults

* more mps test fixes

* unet1d defaults

* do not default import experimental

* defaults for tests

* fix tests

* fix-copies

* fix

* changes per Patrik's comments (#1285)

* changes per Patrik's comments

* update conversion script

* fix renaming

* skip more mps tests

* last test fix

* Update examples/rl/README.md
Co-authored-by: Ben Glickenhaus <benglickenhaus@gmail.com>

fix bs for mask and masked latents

Older versions of xformers require query, key, value to be contiguous, this calls .contiguous() on q/k/v before passing to xformers.

* finish

* cleaner

* more fixes

* refactor

* make fix copies

* refactor cycle diffusion

* finish

* finish2

* Apply suggestions from code review

* [Stable Diffusion] Fix padding / truncation

* finish

* Fix Flax usage comments (they didn't work).

* Spell out dtype

* make style

* [Tests] Fix mps+generator fast tests

* mps for Euler

* retry

* warmup issue again?

* fix reproducible initial noise

* Revert "fix reproducible initial noise"

This reverts commit f300d05cb9782ed320064a0c58577a32d4139e6d.

* fix reproducible initial noise

* fix device