GitLab

* 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.

* fix bug in micro-conditioning of class images

* fix bug in micro-conditioning of class images

* style

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

* 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 using_peft_for_inference.md

* add more explanation

* update

* update

* update

update

update

[DPMSolverSinglestepScheduler] correct `get_order_list` for `solver_order=2`and `lower_order_final=True`  (#6953)

* add

* change default

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

* update

* Updated lora inference instructions

* Update examples/dreambooth/README.md
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* Update README.md

* Update README.md

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

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

fix

* 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.

standardize model card template t21-adapter-sdxl

* update

* update

* update

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

* standardize model card template t2i-lora-sdxl

* type annotations

update

standardize model card template t2i-sdxl

standardize model card t2i-lora

* standardize model card

* fix base_model

---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: YiYi Xu <yixu310@gmail.com>
Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>

* fix

* add tests

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

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

* post release

* style

* Empty-Commit

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

* deprecate certain lora methods from the old backend.

* uncomment necessary things.

* safe remove old lora backend 👋

[FIX] IMPORTANT: rgb normalization

update

* controlnet

* style

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

* refactor decode latents in video pipelines

* make fix-copies

controlnet-sdxl

* controlnet-flax

* style

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

* Fix Compatibility Issues in stable_diffusion_xl_reference.py

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

Co-authored-by: wangshaoxiao <wangshaoxiao@xiaomi.com>

* Add vae tiling in img2img and inpaint

* Add vae tiling not slicing

Remove <cat-toy> validation prompt from examples/textual_inversion/textual_inversion_sdxl.py (#6877)

Remove <cat-toy> validation prompt from textual_inversion_sdxl.py

The `<cat-toy>` validation prompt is a default choice for the example task in the README. But no other part of `textual_inversion_sdxl.py` references the cat toy and `textual_inversion.py` has a default validation prompt of `None` as well.

So bring `textual_inversion_sdxl.py` in line with `textual_inversion.py` and change default validation prompt to `None`