GitLab

* update reference pipeline

* update reference pipeline

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

* modify the issue template to include core maintainers.

* add: entry for audio.

* Update .github/ISSUE_TEMPLATE/bug-report.yml
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

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

fix colab notebook cells

* update kandinsky conversion script

* style

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

Update pipeline_flax_controlnet.py

Change type of images array from jax.numpy.array to numpy.ndarray to permit in-place modification of the array when the safety checker detects a NSFW image.

* [MultiControlNet] Allow save and load

* Correct more

* [MultiControlNet] Allow save and load

* make style

* Apply suggestions from code review

relax tolerance slightly

* fix docs typos. add frame_ids argument to text2video-zero pipeline call

* make style && make quality

* add support of pytorch 2.0 scaled_dot_product_attention for CrossFrameAttnProcessor

* add chunk-by-chunk processing to text2video-zero docs

* make style && make quality

* Update docs/source/en/api/pipelines/text_to_video_zero.mdx
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

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

Update installation.mdx

Replace dead link to Flax documentation

Replace the dead link to the Flax installation guide by a working one: https://flax.readthedocs.io/en/latest/#installation

* Correct timestep inpaint

* make style

* Fix

* Apply suggestions from code review

* make style

clean up more

clean up more

* remove seed

* style

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

* Post release

* Post release

* Fix loading

* make style

Apply deprecations

add image processor
Co-authored-by: yiyixuxu <yixu@yis-macbook-pro.lan>

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

* added StableDiffusionCanvasPipeline pipeline

* Added utils codes to pipe_utils file.

* make style

* delete mixture.py and Text2ImageRegion class

* make style

* Added the codes to the readme.md file.

* Moved functions from pipeline_utils to mix_canvas

* Fix custom releases

* make style

[tests] Run slow matrix sequentially.

* Implement option for rescaling betas to zero terminal SNR

* Implement rescale classifier free guidance in pipeline_stable_diffusion.py

* focus on DDIM

* make style

* make style

* make style

* make style

* Apply suggestions from Peter Lin

* Apply suggestions from Peter Lin

* make style

* Apply suggestions from code review

* Apply suggestions from code review

* make style

* make style

---------
Co-authored-by: MaxWe00 <gitlab.9v1lq@slmail.me>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* Add draft for lora text encoder scale

* Improve naming

* fix: training dreambooth lora script.

* Apply suggestions from code review

* Update examples/dreambooth/train_dreambooth_lora.py

* Apply suggestions from code review

* Apply suggestions from code review

* add lora mixin when fit

* add lora mixin when fit

* add lora mixin when fit

* fix more

* fix more

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

* support views batch for panorama

* add entry for the new argument

* format entry for the new argument

* add view_batch_size test

* fix batch test and a boundary condition

* add more docstrings

* fix a typos

* fix typos

* add: entry to the doc about view_batch_size.

* Revert "add: entry to the doc about view_batch_size."

This reverts commit a36aeaa9edf9b662d09bbfd6e18cbc556ed38187.

* add a tip on .

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

- use the correct Prior hub model id
 - use the new names in KandinskyPriorPipelineOutput

* refactor x4 upscaler

* style

* copies

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

* feat: add lora attention processor for pt 2.0.

* explicit context manager for SDPA.

* switch to flash attention

* make shapes compatible to work optimally with SDPA.

* fix: circular import problem.

* explicitly specify the flash attention kernel in sdpa

* fall back to efficient attention context manager.

* remove explicit dispatch.

* fix: removed processor.

* fix: remove optional from type annotation.

* feat: make changes regarding LoRAAttnProcessor2_0.

* remove confusing warning.

* formatting.

* relax tolerance for PT 2.0

* fix: loading message.

* remove unnecessary logging.

* add: entry to the docs.

* add: network_alpha argument.

* relax tolerance.

* merge undoable-monkeypatch

* remove TEXT_ENCODER_TARGET_MODULES, refactoring

* move create_lora_weight_file

fix link to load_lora_weights

* move activation dispatches into helper function

* tests