GitLab

* only check for xformers when xformers are enabled

* only test for xformers when enabling them

* Fail if there are less images than the effective batch size.

* Remove lr-scheduler arg as it's currently ignored.

* Make guidance_scale work for batch_size > 1.

* Transformers version req for UnCLIP

* add to the list

* Add CPU offloading to UnCLIP

* use fp32 for testing the offload

duplicate maks for num_images_per_prompt

* Remove bogus file

* [Unclip] Add efficient attention

* [Unclip] Add efficient attention

* [unCLIP docs] markdown

* [unCLIP docs] UnCLIPPipeline

* [fix] pipeline_unclip generator

pass generator to all schedulers

* fix fast tests test data

* [wip] attention block updates

* [wip] unCLIP unet decoder and super res

* [wip] unCLIP prior transformer

* [wip] scheduler changes

* [wip] text proj utility class

* [wip] UnCLIPPipeline

* [wip] kakaobrain unCLIP convert script

* [unCLIP pipeline] fixes re: @patrickvonplaten

remove callbacks

move denoising loops into call function

* UNCLIPScheduler re: @patrickvonplaten

Revert changes to DDPMScheduler. Make UNCLIPScheduler, a modified
DDPM scheduler with changes to support karlo

* mask -> attention_mask re: @patrickvonplaten

* [DDPMScheduler] remove leftover change

* [docs] PriorTransformer

* [docs] UNet2DConditionModel and UNet2DModel

* [nit] UNCLIPScheduler -> UnCLIPScheduler

matches existing unclip naming better

* [docs] SchedulingUnCLIP

* [docs] UnCLIPTextProjModel

* refactor

* finish licenses

* rename all to attention_mask and prep in models

* more renaming

* don't expose unused configs

* final renaming fixes

* remove x attn mask when not necessary

* configure kakao script to use new class embedding config

* fix copies

* [tests] UnCLIPScheduler

* finish x attn

* finish

* remove more

* rename condition blocks

* clean more

* Apply suggestions from code review

* up

* fix

* [tests] UnCLIPPipelineFastTests

* remove unused imports

* [tests] UnCLIPPipelineIntegrationTests

* correct

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

* Fix/update LDM tests

* batched generators

Co-authored-by: Peter <peterto@users.noreply.github.com>

[Batched Generators] This PR adds generators that are useful to make batched generation fully reproducible  (#1718)

* [Batched Generators] all batched generators

* up

* up

* up

* up

* up

* up

* up

* up

* up

* up

* up

* up

* up

* up

* up

* up

* hey

* up again

* fix tests

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

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

* [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>

* Fix ONNX img2img preprocessing and add fast tests coverage

* revert

* disable progressbars

* Latent Diffusion pipeline accept latents

* make style

* check for mps

randn does not work reproducibly on mps

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

* update inpaint_legacy to allow the use of predicted noise to construct intermediate diffused images

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

* add fast tests

* better tests and fp16

* batch fixes

* Reuse preprocessing

* quickfix

* [Community pipeline] Add github mechanism

* better

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

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

fixed #1685 - disables telemetry when DISABLE_TELEMETRY and HF_HUB_OFFLINE is set

upgrade version

* [SD] Make sure batched input works correctly

* uP

* uP

* up

* up

* uP

* up

* fix mask stuff

* up

* uP

* more up

* up

* uP

* up

* finish

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

* fix bug if we don't do_classifier_free_guidance

* update for copied diffusers.pipelines..alt_diffusion..pipeline_alt_diffusion.AltDiffusionPipeline

Deprecate init image correctl

* fix versatile diffusion input

* merge main

* `make fix-copies`
Co-authored-by: anton- <anton@huggingface.co>

Since no deprecate() call was done, the typos were silently ignored.

remove unnecessary offset in img2img

Allow k pipeline to generate > 1 images.

* do not automatically enable xformers

* uP