GitLab

* initial commit

* move modules to import struct

* add dummy objects and _LazyModule

* add lazy import to schedulers

* clean up unused imports

* lazy import on models module

* lazy import for schedulers module

* add lazy import to pipelines module

* lazy import altdiffusion

* lazy import audio diffusion

* lazy import audioldm

* lazy import consistency model

* lazy import controlnet

* lazy import dance diffusion ddim ddpm

* lazy import deepfloyd

* lazy import kandinksy

* lazy imports

* lazy import semantic diffusion

* lazy imports

* lazy import stable diffusion

* move sd output to its own module

* clean up

* lazy import t2iadapter

* lazy import unclip

* lazy import versatile and vq diffsuion

* lazy import vq diffusion

* helper to fetch objects from modules

* lazy import sdxl

* lazy import txt2vid

* lazy import stochastic karras

* fix model imports

* fix bug

* lazy import

* clean up

* clean up

* fixes for tests

* fixes for tests

* clean up

* remove import of torch_utils from utils module

* clean up

* clean up

* fix mistake import statement

* dedicated modules for exporting and loading

* remove testing utils from utils module

* fixes from  merge conflicts

* Update src/diffusers/pipelines/kandinsky2_2/__init__.py

* fix docs

* fix alt diffusion copied from

* fix check dummies

* fix more docs

* remove accelerate import from utils module

* add type checking

* make style

* fix check dummies

* remove torch import from xformers check

* clean up error message

* fixes after upstream merges

* dummy objects fix

* fix tests

* remove unused module import

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

* Fix potential type conversion errors in SDXL pipelines

* make sure vae stays in fp16

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

* fix sdxl_lwp empty neg_prompt error issue

* fix sdxl_lwp empty neg_prompt error issue, update code format

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

* Add SDXL long weighted prompt pipeline

* Add SDXL long weighted prompt pipeline usage sample in the readme document

* Add SDXL long weighted prompt pipeline usage sample in the readme document, add result image

* make safetensors default

* set default save method as safetensors

* update tests

* update to support saving safetensors

* update test to account for safetensors default

* update example tests to use safetensors

* update example to support safetensors

* update unet tests for safetensors

* fix failing loader tests

* fix qc issues

* fix pipeline tests

* fix example test

---------
Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>

fix guidance scale value

* Clean up duplicate line

* Clean up duplicate lines

* Clean up duplicate line

* sdxl lora changes.

* better name replacement.

* better replacement.

* debugging

* debugging

* debugging

* debugging

* debugging

* remove print.

* print state dict keys.

* print

* distingisuih better

* debuggable.

* fxi: tyests

* fix: arg from training script.

* access from class.

* run style

* debug

* save intermediate

* some simplifications for SDXL LoRA

* styling

* unet config is not needed in diffusers format.

* fix: dynamic SGM block mapping for SDXL kohya loras (#4322)

* Use lora compatible layers for linear proj_in/proj_out (#4323)

* improve condition for using the sgm_diffusers mapping

* informative comment.

* load compatible keys and embedding layer maaping.

* Get SDXL 1.0 example lora to load

* simplify

* specif ranks and hidden sizes.

* better handling of k rank and hidden

* debug

* debug

* debug

* debug

* debug

* fix: alpha keys

* add check for handling LoRAAttnAddedKVProcessor

* sanity comment

* modifications for text encoder SDXL

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* denugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* up

* up

* up

* up

* up

* up

* unneeded comments.

* unneeded comments.

* kwargs for the other attention processors.

* kwargs for the other attention processors.

* debugging

* debugging

* debugging

* debugging

* improve

* debugging

* debugging

* more print

* Fix alphas

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* clean up

* clean up.

* debugging

* fix: text

---------
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: Batuhan Taskaya <batuhan@python.org>

[SDXL] Make watermarker optional under certain circumstances to improve usability of SDXL 1.0 (#4346)

* improve sdxl

* more fixes

* improve sdxl

* improve sdxl

* improve sdxl

* finish

* 0.20.0dev0

* make style

* up

* Apply suggestions from code review

* Apply suggestions from code review

* up

* Improve docs

* Correct docs

* Add better example inpaint

* make style

* Apply suggestions from code review
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* fix

---------
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* Allow low precision sd xl

* finish

* finish

* feat: initial draft for supporting text encoder lora finetuning for SDXL DreamBooth

* fix: variable assignments.

* add: autocast block.

* add debugging

* vae dtype hell

* fix: vae dtype hell.

* fix: vae dtype hell 3.

* clean up

* lora text encoder loader.

* fix: unwrapping models.

* add: tests.

* docs.

* handle unexpected keys.

* fix vae dtype in the final inference.

* fix scope problem.

* fix: save_model_card args.

* initialize: prefix to None.

* fix: dtype issues.

* apply gixes.

* debgging.

* debugging

* debugging

* debugging

* debugging

* debugging

* add: fast tests.

* pre-tokenize.

* address: will's comments.

* fix: loader and tests.

* fix: dataloader.

* simplify dataloader.

* length.

* simplification.

* make style && make quality

* simplify state_dict munging

* fix: tests.

* fix: state_dict packing.

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

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

Allow specifying denoising_start and denoising_end as integers representing the discrete timesteps, fixing the XL ensemble not working for many schedulers (#4115)

* Fix the XL ensemble not working for any kerras scheduler sigmas and having an off by one bug

* Update src/diffusers/pipelines/stable_diffusion_xl/pipeline_stable_diffusion_xl.py

* make sytle

---------

Co-authored-by: Jimmy <39@🇺🇸

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

* [SDXL] Fix sd xl encode prompt

* add tests

* fix bug in sdxl

* Update pipeline_stable_diffusion_xl_img2img.py

* Update pipeline_stable_diffusion_xl.py

* Update pipeline_stable_diffusion_xl_img2img.py

* Update pipeline_stable_diffusion_xl_inpaint.py

* Update pipeline_stable_diffusion_xl.py

* Update pipeline_stable_diffusion_xl_img2img.py

* Update pipeline_stable_diffusion_xl_inpaint.py

* Update pipeline_stable_diffusion_xl_img2img.py

* Update pipeline_controlnet_sd_xl.py

* Update pipeline_controlnet_sd_xl.py

* Update pipeline_stable_diffusion_xl.py

* Update pipeline_stable_diffusion_xl_img2img.py

* Update pipeline_stable_diffusion_xl_inpaint.py

* Update test_stable_diffusion_xl.py

* Update test_stable_diffusion_xl.py

* Update test_stable_diffusion_xl.py

add test on prompt_embeds

* add test on prompt_embeds

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

* fix bug when no cfg

* style

* fix no cfg for shap-e and cycle

* style

* fix no cfg for sdxl

* fix copies

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

* start with stable diffusion

* fix

* finish stable diffusion pipelines

* fix path to pipeline output

* fix flax paths

* fix copies

* add up to score sde ve

* finish first pass of pipelines

* fix copies

* second review

* align doc titles

* more review fixes

* final review

* sdxl prompt2

* Improve checks

* doc linting

* whoops

* remove cat

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

* Add other pipelines and tests

* Add multi-prompting to docs

* doc and copies check

* Fix copied froms

* Apply suggestions from code review
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* Bring back the original code for unrelated files

* Fix tests

* Fix img2img

* Fix all

* fix

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

* create general cpu offload & execution device

* Remove boiler plate

* finish

* kp

* Correct offload more pipelines

* up

* Update src/diffusers/pipelines/pipeline_utils.py

* make style

* up

* Add more

* more

* up

* Get ensemble of expert denoisers working

* Fix code

* add tests

* up

* Allow low precision sd xl

* finish

* finish

* make style

* diffusers#4003 - initial implementation of max_inference_steps

* diffusers#4003 - initial implementation of max_inference_steps and first_inference_step for img2img

* diffusers#4003 - use first_inference_step as an input arg for get_timestamps in img2img

* diffusers#4003 Do not add noise during img2img when we have a defined first timestep

* diffusers#4003 Mild updates after revert

* diffusers#4003 Missing change

* Show implementation with denoising_start and end

* Apply suggestions from code review

* Update src/diffusers/pipelines/stable_diffusion_xl/pipeline_stable_diffusion_xl.py
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

* move to 0.19.0dev

* Apply suggestions from code review

* add exhaustive tests

* add docs

* finish

* Apply suggestions from code review
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* make style

---------
Co-authored-by: bghira <bghira@users.github.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>

* add dreambooth lora script for SDXL incorporating latest changes.

* remove use_auth_token=True.

* add: documentation

* remove unneeded cli.

* increase the number of training steps in the readme.

* add LoraLoaderMixin to the subclassing mix.

* add sdxl lora dreambooth test.

* add: inference code sample.

* add: refiner output.

* add LoraLoaderMixin to the mix of classes of StableDiffusionXLImg2ImgPipeline.

* change default resolution of DreamBoothDataset.

* better sdxl report path.

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

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

* Update pipeline_stable_diffusion_xl.py

fix a bug

* Update pipeline_stable_diffusion_xl_img2img.py

* Update pipeline_stable_diffusion_xl_img2img.py

* Update pipeline_stable_diffusion_upscale.py

* style

---------
Co-authored-by: Hu Ye <xiaohuzc@gmail.com>

* Add sdxl prompt embeddings

* Fix more

* fix some slow tests

fix some slow tests

* improve sd xl

* correct more

* finish

* make style

* fix more

* Add new text encoder

* add transformers depth

* More

* Correct conversion script

* Fix more

* Fix more

* Correct more

* correct text encoder

* Finish all

* proof that in works in run local xl

* clean up

* Get refiner to work

* Add red castle

* Fix batch size

* Improve pipelines more

* Finish text2image tests

* Add img2img test

* Fix more

* fix import

* Fix embeddings for classic models (#3888)

Fix embeddings for classic SD models.

* Allow multiple prompts to be passed to the refiner (#3895)

* finish more

* Apply suggestions from code review

* add watermarker

* Model offload (#3889)

* Model offload.

* Model offload for refiner / img2img

* Hardcode encoder offload on img2img vae encode

Saves some GPU RAM in img2img / refiner tasks so it remains below 8 GB.

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

* correct

* fix

* clean print

* Update install warning for `invisible-watermark`

* add: missing docstrings.

* fix and simplify the usage example in img2img.

* fix setup for watermarking.

* Revert "fix setup for watermarking."

This reverts commit 491bc9f5a640bbf46a97a8e52d6eff7e70eb8e4b.

* fix: watermarking setup.

* fix: op.

* run make fix-copies.

* make sure tests pass

* improve convert

* make tests pass

* make tests pass

* better error message

* fiinsh

* finish

* Fix final test

---------
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* 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>

* add text2img

* fix-copies

* add

* add all other pipelines

* add

* add

* add

* add

* add

* make style

* style + fix copies

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

* test: Added test case

* fix: fixed type checking issue on _encode_prompt

* fix: fixed copies consistency

* fix: one copy was not sufficient

* fix more

* Fix more

* fix more

* Apply suggestions from code review

* fix

* make style

* make fix-copies

* fix

* make sure torch compile

* Clean

* fix test

* add mixin class for pipeline from original sd ckpt

* Improve

* make style

* merge main into

* Improve more

* fix more

* up

* Apply suggestions from code review

* finish docs

* rename

* make style

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

* add: first draft for a better LoRA enabler.

* make fix-copies.

* feat: backward compatibility.

* add: entry to the docs.

* add: tests.

* fix: docs.

* fix: norm group test for UNet3D.

* feat: add support for flat dicts.

* add depcrcation message instead of warning.

* [Config] Fix config prints and save, load

* Only use potential nn.Modules for dtype and device

* Correct vae image processor

* make sure in_channels is not accessed directly

* make sure in channels is only accessed via config

* Make sure schedulers only access config attributes

* Make sure to access config in SAG

* Fix vae processor and make style

* add tests

* uP

* make style

* Fix more naming issues

* Final fix with vae config

* change more