GitLab

* EDICT pipeline initial commit

- Starting point taking from https://github.com/Joqsan/edict-diffusion



* refactor __init__() method

* minor refactoring

* refactor scheduler code

- remove scheduler and move its methods to the EDICTPipeline class

* make CFG optional
- refactor encode_prompt().
- include optional generator for sampling with vae.
- minor variable renaming

* add EDICT pipeline description to README.md

* replace preprocess() with VaeImageProcessor

* run make style and make quality commands

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

* 👽

 qol improvements for LoRA.

* better function name?

* fix: LoRA weight loading with the new format.

* address Patrick's comments.

* Apply suggestions from code review
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* change wording around encouraging the use of load_lora_weights().

* fix: function name.

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

* [docs] add notes for stateful model changes

* Update docs/source/en/optimization/fp16.mdx
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

* link to accelerate docs for discarding hooks

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

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

Revert "Revert "[Community Pipelines] Update lpw_stable_diffusion pipeline" (#3201)"

This reverts commit 91a2a80e.

* config fixes

* deprecate get_input_dims

The pipeline is built as `pipe` but then used as `pipeline`.

Co-authored-by: multimodalart <joaopaulo.passos+multimodal@gmail.com>

Update repaint.mdx

accomodate to #1701

* removed unnecessary parameters from get_up_block and get_down_block functions

* adding resnet_skip_time_act, resnet_out_scale_factor and cross_attention_norm to get_up_block and get_down_block functions

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

Remove required from tracker_project_name.

As observed by https://github.com/off99555 in https://github.com/huggingface/diffusers/issues/2695#issuecomment-1470755050, it already has a default value.

[Slow Test]: Cuda test fixes
Co-authored-by: njindal <njindal@adobe.com>

* [2064]: Add stochastic sampler

* [2064]: Add stochastic sampler

* [2064]: Add stochastic sampler

* [2064]: Add stochastic sampler

* [2064]: Add stochastic sampler

* [2064]: Add stochastic sampler

* [2064]: Add stochastic sampler

* Review comments

* [Review comment]: Add is_torchsde_available()

* [Review comment]: Test and docs

* [Review comment]

* [Review comment]

* [Review comment]

* [Review comment]

* [Review comment]

---------
Co-authored-by: njindal <njindal@adobe.com>

Write model card in controlnet training script.

* [docs] only mention one stage

* add blurb on auto accepting

---------
Co-authored-by: William Berman <WLBberman@gmail.com>

* Post release

* fix more

* [AudioLDM] Update docs to use updated ckpt

* make style

* add document on token merging.

* fix headline.

* fix: headline.

* add some samples for comparison.

* Add all files

* update

* Make sure vae is memory efficient for PT 1

* make style

* Add all files

* update

* add

* clean

* up

* clean up more

* fix more tests

* Improve docs further

* improve

* more fixes docs

* Improve docs more

* Update src/diffusers/models/unet_2d_condition.py

* fix

* up

* update doc links

* make fix-copies

* add safety checker and watermarker to stage 3 doc page code snippets

* speed optimizations docs

* memory optimization docs

* make style

* add watermarking snippets to doc string examples

* make style

* use pt_to_pil helper functions in doc strings

* skip mps tests

* Improve safety

* make style

* new logic

* fix

* fix bad onnx design

* make new stable diffusion upscale pipeline model arguments optional

* define has_nsfw_concept when non-pil output type

* lowercase linked to notebook name

---------
Co-authored-by: William Berman <WLBberman@gmail.com>

* Fix docs text inversion

* Apply suggestions from code review

sync cache version check from transformers

When the token used for textual inversion does not have any special symbols (e.g. it is not surrounded by <>), the tokenizer does not properly split the replacement tokens.  Adding a space for the padding tokens fixes this.

Add v1.1 docs

adding enable_vae_tiling and disable_val_tiling functions

cast to weight dtype

Revert "[Community Pipelines] Update lpw_stable_diffusion pipeline (#3197)"

This reverts commit 9965cb50.

* Make sure attention works with Torch 2_0

* make style

* Fix more

* Update lpw_stable_diffusion.py

* fix cpu offload

* Update train_dreambooth_lora.py

fix bug

* Update train_dreambooth_lora.py

* Add karras pattern to discrete heun scheduler

* Add integration test

* Fix failing CI on pytorch test on M1 (mps)

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

* Multi Vector

* Improve

* fix multi token

* improve test

* make style

* Update examples/test_examples.py

* Apply suggestions from code review
Co-authored-by: Suraj Patil <surajp815@gmail.com>

* update

* Finish

* Apply suggestions from code review

---------
Co-authored-by: Suraj Patil <surajp815@gmail.com>

* clarify training arg

* apply feedback