GitLab

SDXL microconditioning documentation should indicate the correct default order of parameters, so that developers know (#5155)

* SDXL microconditioning documentation should indicate the correct default order of parameters, so that developers know

* SDXL microconditioning documentation should indicate the correct default order of parameters, so that developers know

* empty

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

* Fix type annotation on Scheduler.from_pretrained

* Fix type annotation on PIL.Image

* [Doc builder] Ensure slow import for doc builder

* Apply suggestions from code review

* env for doc builder

* fix more

* [Diffusers] Set import to slow as env variable

* fix docs

* fix docs

* Apply suggestions from code review

* Apply suggestions from code review

* fix docs

* fix docs

* fix cpu offload

* fix

* fix

* Update src/diffusers/pipelines/pipeline_utils.py

* make style

* Apply suggestions from code review
Co-authored-by: YiYi Xu <yixu310@gmail.com>
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

* fix more

* fix more

---------
Co-authored-by: YiYi Xu <yixu310@gmail.com>
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

cpu offload fix for blip diffusion

* support transformer_layers_per block in flax UNet

* add support for text_time additional embeddings to Flax UNet

* rename attention layers for VAE

* add shape asserts when renaming attention layers

* transpose VAE attention layers

* add pipeline flax SDXL code [WIP]

* continue add pipeline flax SDXL code [WIP]

* cleanup

* Working on JIT support

Fixed prompt embedding shapes so they work in parallel mode. Assuming we
always have both text encoders for now, for simplicity.

* Fixing embeddings (untested)

* Remove spurious line

* Shard guidance_scale when jitting.

* Decode images

* Fix sharding

* style

* Refiner UNet can be loaded.

* Refiner / img2img pipeline

* Allow latent outputs from base and latent inputs in refiner

This makes it possible to chain base + refiner without having to use the
vae decoder in the base model, the vae encoder in the refiner, skipping
conversions to/from PIL, and avoiding TPU <-> CPU memory copies.

* Adapt to FlaxCLIPTextModelOutput

* Update Flax XL pipeline to FlaxCLIPTextModelOutput

* make fix-copies

* make style

* add euler scheduler

* Fix import

* Fix copies, comment unused code.

* Fix SDXL Flax imports

* Fix euler discrete begin

* improve init import

* finish

* put discrete euler in init

* fix flax euler

* Fix more

* make style

* correct init

* correct init

* Temporarily remove FlaxStableDiffusionXLImg2ImgPipeline

* correct pipelines

* finish

---------
Co-authored-by: Martin Müller <martin.muller.me@gmail.com>
Co-authored-by: patil-suraj <surajp815@gmail.com>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* SDXL: update links to refine docs

* make style

* more fixes

* up

* up

* style

* add in setup

* oops

* more changes

* v1 rzfactor CI

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

* few todos

* protect torch import

* style

* fix fuse text encoder

* Update src/diffusers/loaders.py
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* replace with `recurse_replace_peft_layers`

* keep old modules for BC

* adjustments on `adjust_lora_scale_text_encoder`

* nit

* move tests

* add conversion utils

* remove unneeded methods

* use class method instead

* oops

* use `base_version`

* fix examples

* fix CI

* fix weird error with python 3.8

* fix

* better fix

* style

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

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

* add comment

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

* conv2d support for recurse remove

* added docstrings

* more docstring

* add deprecate

* revert

* try to fix merge conflicts

* v1 tests

* add new decorator

* add saving utilities test

* adapt tests a bit

* add save / from_pretrained tests

* add saving tests

* add scale tests

* fix deps tests

* fix lora CI

* fix tests

* add comment

* fix

* style

* add slow tests

* slow tests pass

* style

* Update src/diffusers/utils/import_utils.py
Co-authored-by: Benjamin Bossan <BenjaminBossan@users.noreply.github.com>

* Apply suggestions from code review
Co-authored-by: Benjamin Bossan <BenjaminBossan@users.noreply.github.com>

* circumvents pattern finding issue

* left a todo

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

* update hub path

* add lora workflow

* fix

---------
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: Benjamin Bossan <BenjaminBossan@users.noreply.github.com>

Add missing parenthesis in the sample code of BLIP Diffusion

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

fix and add tests
Co-authored-by: yiyixuxu <yixu310@gmail,com>

* Add BLIP Diffusion skeleton

* Add other model components

* Add BLIP2, need to change it for now

* Fix pipeline imports

* Load pretrained ViT

* Make qformer fwd pass same

* Replicate fwd passes

* Fix device bug

* Add accelerate functions

* Remove extra functions from Blip2

* Minor bug

* Integrate initial review changes

* Refactoring

* Refactoring

* Refactor

* Add controlnet

* Refactor

* Update conversion script

* Add image processor

* Shift postprocessing to ImageProcessor

* Refactor

* Fix device

* Add fast tests

* Update conversion script

* Fix checkpoint conversion script

* Integrate review changes

* Integrate reivew changes

* Remove unused functions from test

* Reuse HF image processor in Cond image

* Create new BlipImageProcessor based on transfomers

* Fix image preprocessor

* Minor

* Minor

* Add canny preprocessing

* Fix controlnet preprocessing

* Fix blip diffusion test

* Add controlnet test

* Add initial doc strings

* Integrate review changes

* Refactor

* Update examples

* Remove DDIM comments

* Add copied from for prepare_latents

* Add type anotations

* Add docstrings

* Do black formatting

* Add batch support

* Make tests pass

* Make controlnet tests pass

* Black formatting

* Fix progress bar

* Fix some licensing comments

* Fix imports

* Refactor controlnet

* Make tests faster

* Edit examples

* Black formatting/Ruff

* Add doc

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

* Move controlnet pipeline

* Make tests faster

* Fix imports

* Fix formatting

* Fix make errors

* Fix make errors

* Minor

* Add suggested doc changes
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* Edit docs

* Fix 16 bit loading

* Update examples

* Edit toctree

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

* Minor

* Add tips

* Edit examples

* Update model paths

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

* core: add support for clip ckip to SDXL

* add clip_skip support to the rest of the pipeline.

* Empty-Commit

* [SDXL] Make sure multi batch prompt embeds works

* [SDXL] Make sure multi batch prompt embeds works

* improve more

* improve more

* Apply suggestions from code review

* add support for clip skip

* fix condition

* fix

* add clip_output_layer_to_default

* expose

* remove the previous functions.

* correct condition.

* apply final layer norm

* address feedback

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

* refactor clip_skip.

* port to the other pipelines.

* fix copies one more time

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

remove adapter weights in MultiAdapter constructor

* convert tensorrt controlnet

* Fix code quality

* Fix code quality

* Fix code quality

* Fix code quality

* Fix code quality

* Fix code quality

* Fix number controlnet condition

* Add convert SD XL to onnx

* Add convert SD XL to tensorrt

* Add convert SD XL to tensorrt

* Add examples in comments

* Add examples in comments

* Add test onnx controlnet

* Add tensorrt test

* Remove copied

* Move file test to examples/community

* Remove script

* Remove script

* Remove text

* Fix import

* Fix T2I MultiAdapter

* fix tests

---------
Co-authored-by: dotieuthien <thien.do@mservice.com.vn>
Co-authored-by: dotieuthien <dotieuthien9997@gmail.com>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: dotieuthien <hades@cinnamon.is>

* fix

* fix num_images_per_prompt >1

* other pipelines

* add fast tests for inpaint pipelines

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

* [LoRA] fix typo in attention_processor.py

fixes #5062

* make style

* make fix-copies, logger comented for torch compile

* fix typos in docs

* fix for issue  #5023

* [Release 0.21] Bump version

* fix & remove

* fix more

* fix all, upload

* [Import] Add missing settings

* up

* up

* up

finish config_files implementation

* fix model offload bug when key isn't present

* make style

* fix compel usage

* minor changes in documentation

* fix tests

* fix more

* fix more

* typos

* fix tests

* formatting

---------
Co-authored-by: Dominic Rampas <d6582533@gmail.com>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* check out dtypes.

* check out dtypes.

* check out dtypes.

* check out dtypes.

* check out dtypes.

* check out dtypes.

* check out dtypes.

* potential fix

* check out dtypes.

* check out dtypes.

* working?

fix flaky flax class name

* fix gligen clip import issue

* fix dtype issue with gligen text to image pipeline

* make fix copies

* [SDXL] Add LoRA to all pipelines

* fix all

* fix all

* fix all

* fix more docs

* make style

* fix safety checker

* fix safety checker

* fix safety checker

* Fix an unmatched backtick and make description more general for DiffusionPipeline.enable_sequential_cpu_offload.

* make style

* _exclude_from_cpu_offload -> self._exclude_from_cpu_offload

* make style

* apply suggestions from review

* make style

* fix encode_prompt

* added prompt_embeds and negative_prompt_embeds

* prompt_embeds for the prior only

* [Utils] Correct custom init sort

* [Utils] Correct custom init sort

* [Utils] Correct custom init sort

* add type checking

* fix custom init sort

* fix test

* fix tests

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

* [Draft] Refactor model offload

* [Draft] Refactor model offload

* Apply suggestions from code review

* cpu offlaod updates

* remove model cpu offload from individual pipelines

* add hook to offload models to cpu

* clean up

* model offload

* add model cpu offload string

* make style

* clean up

* fixes for offload issues

* fix tests issues

* resolve merge conflicts

* update src/diffusers/pipelines/pipeline_utils.py
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* make style

* Update src/diffusers/pipelines/latent_diffusion/pipeline_latent_diffusion.py

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