GitLab

* update dreambooth lora to work with IF stage II

* Update dreambooth script for IF stage II upscaler

* update code to reflect latest changes as of May 30th

* update text to image example

* reflect changes to textual inversion

* make style

* fix typo

* Revert unnecessary readme changes

---------
Co-authored-by: root <root@orttrainingdev8.d32nl1ml4oruzj4qz3bqlggovf.px.internal.cloudapp.net>
Co-authored-by: Prathik Rao <prathikrao@microsoft.com@orttrainingdev8.d32nl1ml4oruzj4qz3bqlggovf.px.internal.cloudapp.net>

Make sure we also change the config when setting `encoder_hid_dim_type=="text_proj"` and allow xformers (#3615)

* fix if

* make style

* make style

* add tests for xformers

* make style

* update

* added clip_guided_images_mixing_stable_diffusion file and readme description

* apply pre-commit

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

* enable state dict for textual inversion loader

* Empty-Commit | restart CI

* Empty-Commit | restart CI

* Empty-Commit | restart CI

* Empty-Commit | restart CI

* add tests

* fix tests

* fix tests

* fix tests

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

add reference tricks

* added mixture pipeline

* added docstring

* update docstring

* Throw error if strength adjusted num_inference_steps < 1

* Added new fast test to check ValueError raised when num_inference_steps < 1

when strength adjusts the num_inference_steps then the inpainting pipeline should fail

* fix #3487 initial latents are now only scaled by init_noise_sigma when pure noise

updated this commit w.r.t the latest merge here: https://github.com/huggingface/diffusers/pull/3533



* fix

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

* fix: unidiffuser test failures.

* living room.

* Fix temb attention

* Apply suggestions from code review

* make style

* Add tests and fix docker

* Apply suggestions from code review

* add ckpt

* fix format

* apply feedback

* fix

* include pb

* rename file

update the broken links

update the broken links for training folder doc

* doc fixes

* fix latex

* parenthesis on inside

* [IF super res] correctl normalize PIL input

* 175 -> 127.5

Fix to apply LoRAXFormersAttnProcessor instead of LoRAAttnProcessor when xFormers is enabled (#3556)

* fix to use LoRAXFormersAttnProcessor

* add test

* using new LoraLoaderMixin.save_lora_weights

* add test_lora_save_load_with_xformers

* Fix a bug of pano when not doing CFG (#3030)

* Fix a bug of pano when not doing CFG

* enhance code quality

* apply formatting.

---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* Text2video zero refinements (#3070)

* fix progress bar issue in pipeline_text_to_video_zero.py. Copy scheduler after first backward

* fix tensor loading in test_text_to_video_zero.py

* make style && make quality

* Release: v0.15.0

* [Tests] Speed up panorama tests (#3067)

* fix: norm group test for UNet3D.

* chore: speed up the panorama tests (fast).

* set default value of _test_inference_batch_single_identical.

* fix: batch_sizes default value.

* [Post release] v0.16.0dev (#3072)

* Adds profiling flags, computes train metrics average. (#3053)

* WIP controlnet training

- bugfix --streaming
- bugfix running report_to!='wandb'
- adds memory profile before validation

* Adds final logging statement.

* Sets tr...

* add attnprocessor to docs

* fix path to class

* create separate page for attnprocessors

* fix path

* fix path for real

* fill in docstrings

* apply feedback

* apply feedback

* Fix guess mode controlnet for euler-like schedulers

* make style

* Co-authored-by: Chanchana Sornsoontorn <off.chanchana@gmail.com>

* Add co author Co-authored-by: Chanchana Sornsoontorn <off.chanchana@gmail.com>

* 2nd try
Co-authored-by: Chanchana Sornsoontorn <off.chanchana@gmail.com>

* renamed variable to input_ and output_

* changed input
_ to intputs and output_ to outputs

[Stable Diffusion Inpainting] Allow standard text-to-img checkpoints to be useable for SD inpainting (#3533)

* Add default to inpaint

* Make sure controlnet also works with normal sd for inpaint

* Add tests

* improve

* Correct encode images function

* Correct inpaint controlnet

* Improve text2img inpanit

* make style

* up

* up

* up

* up

* fix more

fix vq_model
Co-authored-by: yiyixuxu <yixu310@gmail,com>

add kandinsky2.1

---------
Co-authored-by: yiyixuxu <yixu310@gmail,com>
Co-authored-by: Ayush Mangal <43698245+ayushtues@users.noreply.github.com>
Co-authored-by: ayushmangal <ayushmangal@microsoft.com>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* Add open parti prompts

* More changes

* refactor blocks init

* refactor blocks loop

* remove unused function and warnings

* fix scheduler update location

* reformat code

* reformat code again

* fix PNDM test case

* reformat pndm test case

refactor save_model_card utility in dreambooth examples.

* Run ControlNet compile test in a separate subprocess

`torch.compile()` spawns several subprocesses and the GPU memory used
was not reclaimed after the test ran. This approach was taken from
`transformers`.

* Style

* Prepare a couple more compile tests to run in subprocess.

* Use require_torch_2 decorator.

* Test inpaint_compile in subprocess.

* Run img2img compile test in subprocess.

* Run stable diffusion compile test in subprocess.

* style

* Temporarily trigger on pr to test.

* Revert "Temporarily trigger on pr to test."

This reverts commit 82d76868ddf9cc634a9f14b2b0aef1d5433cd750.