GitLab

Revert "[Core] better support offloading when side loading is enabled. (#4855)"

This reverts commit e4b8e792.

* initial evident fixes.

* instructpix2pix fixes.

* add: entry to doc.

* address PR feedback.

* make fix-copies

* initial

* initial

* added initial convert script for paella vqmodel

* initial wuerstchen pipeline

* add LayerNorm2d

* added modules

* fix typo

* use model_v2

* embed clip caption amd negative_caption

* fixed name of var

* initial modules in one place

* WuerstchenPriorPipeline

* inital shape

* initial denoising prior loop

* fix output

* add WuerstchenPriorPipeline to __init__.py

* use the noise ratio in the Prior

* try to save pipeline

* save_pretrained working

* Few additions

* add _execution_device

* shape is int

* fix batch size

* fix shape of ratio

* fix shape of ratio

* fix output dataclass

* tests folder

* fix formatting

* fix float16 + started with generator

* Update pipeline_wuerstchen.py

* removed vqgan code

* add WuerstchenGeneratorPipeline

* fix WuerstchenGeneratorPipeline

* fix docstrings

* fix imports

* convert generator pipeline

* fix convert

* Work on Generator Pipeline. WIP

* Pipeline works with our diffuzz code

* apply scale factor

* removed vqgan.py

* use cosine schedule

* redo the denoising loop

* Update src/diffusers/models/resnet.py
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* use torch.lerp

* use warp-diffusion org

* clip_sample=False,

* some refactoring

* use model_v3_stage_c

* c_cond size

* use clip-bigG

* allow stage b clip to be None

* add dummy

* würstchen scheduler

* minor changes

* set clip=None in the pipeline

* fix attention mask

* add attention_masks to text_encoder

* make fix-copies

* add back clip

* add text_encoder

* gen_text_encoder and tokenizer

* fix import

* updated pipeline test

* undo changes to pipeline test

* nip

* fix typo

* fix output name

* set guidance_scale=0 and remove diffuze

* fix doc strings

* make style

* nip

* removed unused

* initial docs

* rename

* toc

* cleanup

* remvoe test script

* fix-copies

* fix multi images

* remove dup

* remove unused modules

* undo changes for debugging

* no  new line

* remove dup conversion script

* fix doc string

* cleanup

* pass default args

* dup permute

* fix some tests

* fix prepare_latents

* move Prior class to modules

* offload only the text encoder and vqgan

* fix resolution calculation for prior

* nip

* removed testing script

* fix shape

* fix argument to set_timesteps

* do not change .gitignore

* fix resolution calculations + readme

* resolution calculation fix + readme

* small fixes

* Add combined pipeline

* rename generator -> decoder

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

* removed efficient_net

* create combined WuerstchenPipeline

* make arguments consistent with VQ model

* fix var names

* no need to return text_encoder_hidden_states

* add latent_dim_scale to config

* split model into its own file

* add WuerschenPipeline to docs

* remove unused latent_size

* register latent_dim_scale

* update script

* update docstring

* use Attention preprocessor

* concat with normed input

* fix-copies

* add docs

* fix test

* fix style

* add to cpu_offloaded_model

* updated type

* remove 1-line func

* updated type

* initial decoder test

* formatting

* formatting

* fix autodoc link

* num_inference_steps is int

* remove comments

* fix example in docs

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

* rename layernorm to WuerstchenLayerNorm

* rename DiffNext to WuerstchenDiffNeXt

* added comment about MixingResidualBlock

* move paella vq-vae to pipelines' folder

* initial decoder test

* increased test_float16_inference expected diff

* self_attn is always true

* more passing decoder tests

* batch image_embeds

* fix failing tests

* set the correct dtype

* relax inference test

* update prior

* added combined pipeline test

* faster test

* faster test

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

* fix issues from review

* update wuerstchen.md + change generator name

* resolve issues

* fix copied from usage and add back batch_size

* fix API

* fix arguments

* fix combined test

* Added timesteps argument + fixes

* Update tests/pipelines/test_pipelines_common.py
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* Update tests/pipelines/wuerstchen/test_wuerstchen_prior.py
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

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

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

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

* Update src/diffusers/pipelines/wuerstchen/pipeline_wuerstchen_combined.py

* up

* Fix more

* failing tests

* up

* up

* correct naming

* correct docs

* correct docs

* fix test params

* correct docs

* fix classifier free guidance

* fix classifier free guidance

* fix more

* fix all

* make tests faster

---------
Co-authored-by: Dominic Rampas <d6582533@gmail.com>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: Dominic Rampas <61938694+dome272@users.noreply.github.com>

* remove latent input

* fix test

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

* [Test] Reduce CPU memory

* [Test] Reduce CPU memory

* better support offloading when side loading is enabled.

* load_textual_inversion

* better messaging for textual inversion.

* fixes

* address PR feedback.

* sdxl support.

* improve messaging

* recursive removal when cpu sequential offloading is enabled.

* add: lora tests

* recruse.

* add: offload tests for textual inversion.

* throw warning when more than one lora is attempted to be fused.

* introduce support of lora scale during fusion.

* change test name

* changes

* change to _lora_scale

* lora_scale to call whenever applicable.

* debugging

* lora_scale additional.

* cross_attention_kwargs

* lora_scale -> scale.

* lora_scale fix

* lora_scale in patched projection.

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* styling.

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* remove unneeded prints.

* remove unneeded prints.

* assign cross_attention_kwargs.

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* clean up.

* refactor scale retrieval logic a bit.

* fix nonetypw

* fix: tests

* add more tests

* more fixes.

* figure out a way to pass lora_scale.

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

* unify the retrieval logic of lora_scale.

* move adjust_lora_scale_text_encoder to lora.py.

* introduce dynamic adjustment lora scale support to sd

* fix up copies

* Empty-Commit

* add: test to check fusion equivalence on different scales.

* handle lora fusion warning.

* make lora smaller

* make lora smaller

* make lora smaller

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

* fix

* add test

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

* Change StableDiffusionInpaintPipelineFastTests.get_dummy_inputs to produce a random image and a white mask_image.

* Add dummy expected slices for the test_stable_diffusion_inpaint tests.

* Remove print statement

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

* [Tests] Add combined pipeline tests

* Update tests/pipelines/kandinsky_v22/test_kandinsky.py

* [ControlNet SDXL Inpainting] Support inpainting of ControlNet SDXL

Co-authored-by: Jiabin Bai 1355864570@qq.com


---------
Co-authored-by: Harutatsu Akiyama <kf.zy.qin@gmail.com>

* add

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

add 

* proposal for flaky tests

* more precision fixes

* move more tests to use cosine distance

* more test fixes

* clean up

* use default attn

* clean up

* update expected value

* make style

* make style

* Apply suggestions from code review

* Update src/diffusers/pipelines/stable_diffusion/pipeline_onnx_stable_diffusion_img2img.py

* make style

* fix failing tests

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

* Add GLIGEN Text Image implementation

* add style transfer from image

* fix check_repository_consistency

* add convert script GLIGEN model to Diffusers

* rename attention type

* fix style code

* remove PositionNetTextImage

* Revert "fix check_repository_consistency"

This reverts commit 15f098c96e00bb9e67b831161615b30a2d28d815.

* change attention type name

* update docs for GLIGEN

* change examples with hf-document-image

* fix style

* add CLIPImageProjection for GLIGEN

* Add new encode_prompt, load project matrix in pipe init

* move CLIPImageProjection to stable_diffusion

* add comment

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

* Fix Unfuse Lora

* add tests

* Fix more

* Fix more

* Fix all

* make style

* make style

* refactoring of encode_prompt()

* better handling of device.

* fix: device determination

* fix: device determination 2

* handle num_images_per_prompt

* revert changes in loaders.py and give birth to encode_prompt().

* minor refactoring for encode_prompt()/

* make backward compatible.

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

* fix: concatenation of the neg and pos embeddings.

* incorporate encode_prompt() in test_stable_diffusion.py

* turn it into big PR.

* make it bigger

* gligen fixes.

* more fixes to fligen

* _encode_prompt -> encode_prompt in tests

* first batch

* second batch

* fix blasphemous mistake

* fix

* fix: hopefully for the final time.

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

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

* adding save and load for MultiAdapter, adding test

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

* Adding changes from review test_stable_diffusion_adapter

* import sorting fix

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

* Fuse loras

* initial implementation.

* add slow test one.

* styling

* add: test for checking efficiency

* print

* position

* place model offload correctly

* style

* style.

* unfuse test.

* final checks

* remove warning test

* remove warnings altogether

* debugging

* tighten up tests.

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* denugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debuging

* debugging

* debugging

* debugging

* suit up the generator initialization a bit.

* remove print

* update assertion.

* debugging

* remove print.

* fix: assertions.

* style

* can generator be a problem?

* generator

* correct tests.

* support text encoder lora fusion.

* tighten up tests.

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

* T2I-Adapter-XL

* update

* update

* add pipeline

* modify pipeline

* modify pipeline

* modify pipeline

* modify pipeline

* modify pipeline

* modify modeling_text_unet

* fix styling.

* fix: copies.

* adapter settings

* new test case

* new test case

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* debugging

* revert prints.

* new test case

* remove print

* org test case

* add test_pipeline

* styling.

* fix copies.

* modify test parameter

* style.

* add adapter-xl doc

* double quotes in docs

* Fix potential type mismatch

* style.

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

---------
Co-authored-by: yiyixuxu <yixu310@gmail,com>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* fix

---------
Co-authored-by: yiyixuxu <yixu310@gmail,com>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* fix



---------
Co-authored-by: yiyixuxu <yixu310@gmail,com>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* initial commit to fix inheritance issue

* clean up sd onnx upscale

* clean up

* [LoRA Attn] Refactor LoRA attn

* correct for network alphas

* fix more

* fix more tests

* fix more tests

* Move below

* Finish

* better version

* correct serialization format

* fix

* fix more

* fix more

* fix more

* Apply suggestions from code review

* Update src/diffusers/pipelines/stable_diffusion/pipeline_onnx_stable_diffusion_img2img.py

* deprecation

* relax atol for slow test slighly

* Finish tests

* make style

* make style

* Fix last ben sdxl lora

* Correct typo

* make style

* add: support negative conditions.

* fix: key

* add: tests

* address PR feedback.

* add documentation

* add img2img support.

* add inpainting support.

* ad controlnet support

* Apply suggestions from code review

* modify wording in the doc.

* refactor image processor for mask
---------
Co-authored-by: yiyixuxu <yixu310@gmail,com>

* fix
---------
Co-authored-by: yiyixuxu <yixu310@gmail,com>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* proposal for flaky tests

* clean up

* from audioldm

* fix vae

* move to new pipeline

* copied from audioldm

* remove redundant control flow

* iterate

* fix docstring

* finish pipeline

* tests: from audioldm2

* iterate

* finish fast tests

* finish slow integration tests

* add docs

* remove dtype test

* update toctree

* "copied from" in conversion (where possible)

* Update docs/source/en/api/pipelines/musicldm.md
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* fix docstring

* make nightly

* style

* fix dtype test

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

* fix docs

* fix unet docs

* use image output for latents

* fix hub checkpoints

* fix pipeline example

* update example

* return_dict = False

* revert image pipeline output

* revert doc changes

* remove dtype test

* make style

* remove docstring updates

* remove unet docstring update

* Empty commit to re-trigger CI

* fix cpu offload

* fix dtype test

* add offload test

* [fix] multi t2i adapter set total_downscale_factor

* move image checks into check inputs

* remove copied from

use max diff to compare model outputs

add self.step_index

---------
Co-authored-by: yiyixuxu <yixu310@gmail,com>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* Fix AutoencoderTiny encoder scaling convention

  * Add [-1, 1] -> [0, 1] rescaling to EncoderTiny

  * Move [0, 1] -> [-1, 1] rescaling from AutoencoderTiny.decode to DecoderTiny
    (i.e. immediately after the final conv, as early as possible)

  * Fix missing [0, 255] -> [0, 1] rescaling in AutoencoderTiny.forward

  * Update AutoencoderTinyIntegrationTests to protect against scaling issues.
    The new test constructs a simple image, round-trips it through AutoencoderTiny,
    and confirms the decoded result is approximately equal to the source image.
    This test checks behavior with and without tiling enabled.
    This test will fail if new AutoencoderTiny scaling issues are introduced.

  * Context: Raw TAESD weights expect images in [0, 1], but diffusers'
    convention represents images with zero-centered values in [-1, 1],
    so AutoencoderTiny needs to scale / unscale images at the start of
    encoding and at the end of decoding in order to work with diffusers.

* Re-add existing AutoencoderTiny test, update golden values

* Add comments to AutoencoderTiny.forward

This reverts commit 7b07f981.

* enable lora for sdxl controlnets too.

* add: tests

* fix: assertion values.