GitLab

switch to logger.warning

* update the signature of from_single_file

* Update src/diffusers/loaders/single_file.py
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* Update src/diffusers/loaders/single_file.py
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* Update src/diffusers/loaders/single_file.py
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* Update src/diffusers/loaders/single_file.py
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

---------
Co-authored-by: yiyixuxu <yixu310@gmail,com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* update

* fix parameter name

* feedback

* add no mask version

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

* debig

* cast tuples to lists.

* debug

* handle upcast attention

* handle downblock types for vae.

* remove print.

* address Dhruv's comments.

* fix: upblock types.

* upcast attention

* debug

* debug

* debug

* better guarding.

* style

* fix: support for loading playground v2.5 single file checkpoint.

* remove is_playground_model.

* fix: edm key

* apply Dhruv's comments but errors.

* fix: things.

* delegate model_type inference to a function.

* address Dhruv's comment.

* address rest of the comments.

* fix: kwargs

* fix

* update

---------
Co-authored-by: DN6 <dhruv.nair@gmail.com>

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

---------
Co-authored-by: yiyixuxu <yixu310@gmail,com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* copy the state dict in load lora weights

* fixup

* allow passing tokenizer & text_encoder to unload_textual_inversion


---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: YiYi Xu <yixu310@gmail.com>
Co-authored-by: Fabio Rigano <fabio2rigano@gmail.com>
Co-authored-by: Linoy Tsaban <57615435+linoytsaban@users.noreply.github.com>

* fix doc

* remove use_safetensors from signature

* more

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

update

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

* feat: allow low_cpu_mem_usage in ip adapter loading

* reduce the number of device placements.

* documentation.

* throw low_cpu_mem_usage warning only once from the main entry point.

* use cases

* first draft

* fix image links

* lcm-lora

* feedback

* review

* feedback

* feedback

* use load_model_into_meta in single file utils

* propagate to autoencoder and controlnet.

* correct class name access behaviour.

* remove torch_dtype from load_model_into_meta; seems unncessary

* remove incorrect kwarg

* style to avoid extra unnecessary line breaks

* update

* update

* update

* update

* fix: bias loading bug

* fixes for SDXL

* apply changes to the conversion script to match single_file_utils.py

* do transpose to match the single file loading logic.

* fix

* add tests

---------
Co-authored-by: yiyixuxu <yixu310@gmail,com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* deprecate certain lora methods from the old backend.

* uncomment necessary things.

* safe remove old lora backend 👋

change to 2024

* add: support for passing ip adapter image embeddings

* debugging

* make feature_extractor unloading conditioned on safety_checker

* better condition

* type annotation

* index to look into value slices

* more debugging

* debugging

* serialize embeddings dict

* better conditioning

* remove unnecessary prints.

* Update src/diffusers/loaders/ip_adapter.py
Co-authored-by: YiYi Xu <yixu310@gmail.com>

* make fix-copies and styling.

* styling and further copy fixing.

* fix: check_inputs call in controlnet sdxl img2img pipeline

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

[ip-adapter] make sure length of `scale` is same as number of ip-adapters when using  `set_ip_adapter_scale` (#6884)

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

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

fix

* Add unload_textual_inversion

* Fix dicts in tokenizer

* Fix quality

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

* Fix variable name after last update

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

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

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update'

* update

* update

* update

* update

* update

* update

* up

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* up

* update

* update

* update

* update

* update'

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* clean

* update

* update

* clean up

* clean up

* update

* clean

* clean

* update

* updaet

* clean up

* fix docs

* update

* update

* Revert "update"

This reverts commit dbfb8f1ea9c61a2b4e02f926245be2b3d387e577.

* update

* update

* update

* update

* fix controlnet

* fix scheduler

* fix controlnet tests

* posix lora

* changes and style fix

* Fix path generation on Windows

* Update set_default_attn_processors

* Use pathlib

* Fix quality

* Fix copy

* Revert changes in set_default_attn_processors

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

* remove omegaconf from convert_from_ckpt.

* remove from single_file.

* change to string based ubscription.

* style

* okay

* fix: vae_param

* no . indexing.

* style

* style

* turn getattrs into explicit if/else

* style

* propagate changes to ldm_uncond.

* propagate to gligen

* propagate to if.

* fix: quotes.

* propagate to audioldm.

* propagate to audioldm2

* propagate to musicldm.

* propagate to vq_diffusion

* propagate to zero123.

* remove omegaconf from diffusers codebase.

* fix: training resume from fp16.

* add: comment

* remove residue from another branch.

* remove more residues.

* thanks to Younes; no hacks.

* style.

* clean things a bit and modularize _set_state_dict_into_text_encoder

* add comment about the fix detailed.

follow up

* introduce integrations module.

* remove duplicate methods.

* better imports.

* move to loaders.py

* remove peftadaptermixin from modelmixin.

* add: peftadaptermixin selectively.

* add: entry to _toctree

* Empty-Commit

* handle rest of the stuff related to deprecated lora stuff.

* fix: copies

* don't modify the uNet in-place.

* fix: temporal autoencoder.

* manually remove lora layers.

* don't copy unet.

* alright

* remove lora attn processors from unet3d

* fix: unet3d.

* styl

* Empty-Commit

* Add unload_ip_adapter method

* Update attn_processors with original layers

* Add test

* Use set_default_attn_processor

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

* refactor ip-adapter-imageproj, gligen

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

* add adapter_name in fuse

* add tesrt

* up

* fix CI

* adapt from suggestion

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

* change to `require_peft_version_greater`

* change variable names in test

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

* break into 2 lines

* final comments

---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: Benjamin Bossan <BenjaminBossan@users.noreply.github.com>

* [Peft] fix saving / loading when unet is not "unet"

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

* undo stablediffusion-xl changes

* use unet_name to get unet for lora helpers

* use unet_name

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