GitLab

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

* updated black format

* update black format

* make style format

* updated line endings

* update code formatting

* Update examples/research_projects/onnxruntime/text_to_image/train_text_to_image.py
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

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

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

* added vae gradient checkpointing test

* make style

---------
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: Will Berman <wlbberman@gmail.com>

Improve error message

* Adding `use_safetensors` argument to give more control to users

about which weights they use.

* Doc style.

* Rebased (not functional).

* Rebased and functional with tests.

* Style.

* Apply suggestions from code review

* Style.

* Addressing comments.

* Update tests/test_pipelines.py
Co-authored-by: Will Berman <wlbberman@gmail.com>

* Black ???

---------
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: Will Berman <wlbberman@gmail.com>

* rename file

* rename attention

* fix more

* rename more

* up

* more deprecation imports

* fixes

* add image_processor

---------
Co-authored-by: yiyixuxu <yixu310@gmail,com>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

* fix AttnProcessor2_0

Fix use of AttnProcessor2_0 for cross attention with mask

* added scale_qk and out_bias flags

* fixed for xformers

* check if it has scale argument

* Update cross_attention.py

* check torch version

* fix sliced attn

* style

* set scale

* fix test

* fixed addedKV processor

* revert back AttnProcessor2_0

* if missing if

* fix inner_dim

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

* Controlnet training code initial commit

Works with circle dataset: https://github.com/lllyasviel/ControlNet/blob/main/docs/train.md



* Script for adding a controlnet to existing model

* Fix control image transform

Control image should be in 0..1 range.

* Add license header and remove more unused configs

* controlnet training readme

* Allow nonlocal model in add_controlnet.py

* Formatting

* Remove unused code

* Code quality

* Initialize controlnet in training script

* Formatting

* Address review comments

* doc style

* explicit constructor args and submodule names

* hub dataset

NOTE -  not tested

* empty prompts

* add conditioning image

* rename

* remove instance data dir

* image_transforms -> -1,1 . conditioning_image_transformers -> 0, 1

* nits

* remove local rank config

I think this isn't necessary in any of our training scripts

* validation images

* proportion_empty_prompts typo

* weight copying to controlnet bug

* call log validation fix

* fix

* gitignore wandb

* fix progress bar and resume from checkpoint iteration

* initial step fix

* log multiple images

* fix

* fixes

* tracker project name configurable

* misc

* add controlnet requirements.txt

* update docs

* image labels

* small fixes

* log validation using existing models for pipeline

* fix for deepspeed saving

* memory usage docs

* Update examples/controlnet/train_controlnet.py
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* Update examples/controlnet/train_controlnet.py
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* Update examples/controlnet/README.md
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* Update examples/controlnet/README.md
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* Update examples/controlnet/README.md
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* Update examples/controlnet/README.md
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* Update examples/controlnet/README.md
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* Update examples/controlnet/README.md
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* Update examples/controlnet/README.md
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* Update examples/controlnet/README.md
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* remove extra is main process check

* link to dataset in intro paragraph

* remove unnecessary paragraph

* note on deepspeed

* Update examples/controlnet/README.md
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* assert -> value error

* weights and biases note

* move images out of git

* remove .gitignore

---------
Co-authored-by: William Berman <WLBberman@gmail.com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* Add support for different model prediction types in DDIMInverseScheduler
Resolve alpha_prod_t_prev index issue for final step of inversion

* Fix old bug introduced when prediction type is "sample"

* Add support for sample clipping for numerical stability and deprecate old kwarg

* Detach sample, alphas, betas

Derive predicted noise from model output before dist. regularization

Style cleanup

* Log loss for debugging

* Revert "Log loss for debugging"

This reverts commit 76ea9c856f99f4c8eca45a0b1801593bb982584b.

* Add comments

* Add inversion equivalence test

* Add expected data for Pix2PixZero pipeline tests with SD 2

* Update tests/pipelines/stable_diffusion/test_stable_diffusion_pix2pix_zero.py

* Remove cruft and add more explanatory comments

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

* [Lora] correct lora saving & loading

* fix final

* Apply suggestions from code review

* fix the in-place modification in unet condition when using controlnet, which will cause backprop errors when training

* add clone to mid block

* fix-copies

---------
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: William Berman <WLBberman@gmail.com>

* support for List[ControlNetModel] on init()

* Add to support for multiple ControlNetCondition

* rename conditioning_scale to scale

* scaling bugfix

* Manually merge `MultiControlNet` #2621
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

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

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

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

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

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

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

* cleanups
- don't expose ControlNetCondition
- move scaling to ControlNetModel

* make style error correct

* remove ControlNetCondition to reduce code diff

* refactoring image/cond_scale

* add explain for `images`

* Add docstrings

* all fast-test passed

* Add a slow test

* nit

* Apply suggestions from code review

* small precision fix

* nits

MultiControlNet -> MultiControlNetModel - Matches existing naming a bit
closer

MultiControlNetModel inherit from model utils class - Don't have to
re-write fp16 test

Skip tests that save multi controlnet pipeline - Clearer than changing
test body

Don't auto-batch the number of input images to the number of controlnets.
We generally like to require the user to pass the expected number of
inputs. This simplifies the processing code a bit more

Use existing image pre-processing code a bit more. We can rely on the
existing image pre-processing code and keep the inference loop a bit
simpler.

---------
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: William Berman <WLBberman@gmail.com>

* [attention] Fix attention

* fix

* correct

* Support non square image generation for StableDiffusionSAGPipeline

* Fix style

* [Pipeline loading]

* up

* controlnet sd 2.1 checkpoint conversions

* remove global_step -> make config file mandatory

* [From pretrained] Speed-up loading from cache

* up

* Fix more

* fix one more bug

* make style

* bigger refactor

* factor out function

* Improve more

* better

* deprecate return cache folder

* clean up

* improve tests

* up

* upload

* add nice tests

* simplify

* finish

* correct

* fix version

* rename

* Apply suggestions from code review
Co-authored-by: Lucain <lucainp@gmail.com>

* rename

* correct doc string

* correct more

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

* apply code suggestions

* finish

---------
Co-authored-by: Lucain <lucainp@gmail.com>
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

Improve ddim scheduler
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* improve error message

* upload

* [Schedulers] Correct config changing

* uP

* add tests

Improve docs

* add api doc for flax pipeline + doc string examples

* make style

---------
Co-authored-by: yiyixuxu <yixu@yis-macbook-pro.lan>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

Fixed incorrect width/height assignment in StableDiffusionDepth2ImgPipeline when passing in tensor

* Improve dynamic threshold

* Update code

* Add dynamic threshold to ddim and ddpm

* Encapsulate and leverage code copy mechanism

Update style

* Clean up DDPM/DDIM constructor arguments

* add test

* also add to unipc

---------
Co-authored-by: Peter Lin <peterlin9863@gmail.com>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* add docs

* correct

* finish

* Apply suggestions from code review
Co-authored-by: Will Berman <wlbberman@gmail.com>
Co-authored-by: YiYi Xu <yixu310@gmail.com>

* update deps table

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

---------
Co-authored-by: Will Berman <wlbberman@gmail.com>
Co-authored-by: YiYi Xu <yixu310@gmail.com>
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

add attn_res variable
Co-authored-by: yiyixuxu <yixu310@gmail,com>

* [Onnx] add Stable Diffusion Upscale pipeline

* add a test for the OnnxStableDiffusionUpscalePipeline

* check for VAE config before adjusting scaling factor

* update test assertions, lint fixes

* run fix-copies target

* switch test checkpoint to one hosted on huggingface

* partially restore attention mask

* reshape embeddings after running text encoder

* add longer nightly test for ONNX upscale pipeline

* use package import to fix tests

* fix scheduler compatibility and class labels dtype

* use more precise type

* remove LMS from fast tests

* lookup latent and timestamp types

* add docs for ONNX upscaling, rename lookup table

* replace deprecated pipeline names in ONNX docs

Fix for InstructPix2PixPipeline to allow for prompt embeds to be passed in without prompts.  (#2456)

* fix check inputs to allow prompt embeds in instruct pix2pix

* linting

* add reference comment to check inputs

* remove comment

* style changes

---------
Co-authored-by: Will Berman <wlbberman@gmail.com>

* Fix regression introduced in #2448

* Style.

* attend and excite batch test causing timeouts

* move test num_images_per_prompt to pipeline mixin

* style

* prompt_key -> self.batch_params

Update pipeline_stable_diffusion_inpaint_legacy.py resize to integer multiple of 8 instead of 32 for init image and mask (#2350)

Update pipeline_stable_diffusion_inpaint_legacy.py

Change resize to integer multiple of 8 instead of 32

Remove explicit message argument