GitLab

* 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

VaeImageProcessor.preprocess refactor

* refactored VaeImageProcessor 
   -  allow passing optional height and width argument to resize()
   - add convert_to_rgb
* refactored prepare_latents method for img2img pipelines so that if we pass latents directly as image input, it will not encode it again
* added a test in test_pipelines_common.py to test latents as image inputs
* refactored img2img pipelines that accept latents as image: 
   - controlnet img2img, stable diffusion img2img , instruct_pix2pix

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

* part 2 of api fixes

* move randn_tensor

* add to toctree

* apply feedback

* more feedback

* fix: assertion.

* assertion fix.

* Update Compel documentation for textual inversions

* Fix typo

Correct multi gpu

* load a1111 lora

* fix

* apply feedback

* fix

Expose num_cycles kwarg of get_schedule() through args.lr_num_cycles.

So that schedule_func() calls get_piecewise_constant_schedule() with correctly named kwarg.

* dreambooth if docs - stage II, more info

* Update docs/source/en/training/dreambooth.mdx
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* Update docs/source/en/training/dreambooth.mdx
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

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

* download instructions for downsized images

* update source README to match docs

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

* set config from original module but set compiled module on class

* add test

* add tensorrt inpaint pipeline
Signed-off-by: Asfiya Baig <asfiyab@nvidia.com>

* run make style
Signed-off-by: Asfiya Baig <asfiyab@nvidia.com>

---------
Signed-off-by: Asfiya Baig <asfiyab@nvidia.com>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* Updated the filename and readme file.

* reformatter

* reformetter

* fix latents

* fix copies

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

fixed typo

* iterate over unique tokens to avoid duplicate replacements

* added test for multiple references to multi embedding

* adhere to black formatting

* reorder test post-rebase

* add _convert_kohya_lora_to_diffusers

* make style

* add scaffold

* match result: unet attention only

* fix monkey-patch for text_encoder

* with CLIPAttention

While the terrible images are no longer produced,
the results do not match those from the hook ver.
This may be due to not setting the network_alpha value.

* add to support network_alpha

* generate diff image

* fix monkey-patch for text_encoder

* add test_text_encoder_lora_monkey_patch()

* verify that it's okay to release the attn_procs

* fix closure version

* add comment

* Revert "fix monkey-patch for text_encoder"

This reverts commit bb9c61e6faecc1935c9c4319c77065837655d616.

* Fix to reuse utility functions

* make LoRAAttnProcessor targets to self_attn

* fix LoRAAttnProcessor target

* make style

* fix split key

* Update src/diffusers/loaders.py

* remove TEXT_ENCODER_TARGET_MODULES loop

* add print memory usage

* remove test_kohya_loras_scaffold.py

* add: doc on LoRA civitai

* remove print statement and refactor in the doc.

* fix state_dict test for kohya-ss style lora

* Apply suggestions from code review
Co-authored-by: Takuma Mori <takuma104@gmail.com>

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

* Improve docs

* up

* Update docs/source/en/api/pipelines/kandinsky.mdx

* up

* up

* correct more

* further improve

* Update docs/source/en/api/pipelines/kandinsky.mdx
Co-authored-by: YiYi Xu <yixu310@gmail.com>

---------
Co-authored-by: YiYi Xu <yixu310@gmail.com>

include the instruction-tuning blog link.

* 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.