GitLab

correct qk norm list.

update

Fix fp16 bug
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

* flux group-offload

* feedback

* sd_embed

* feedback

Co-authored-by: puhuk <wetr235@gmail.com>

* restruct certain keys to be checked for peft config update.

* updates

* finish./

* finish 2.

* updates

* Fix `torch_dtype` in Kolors text encoder with `transformers` v4.49

* Default torch_dtype and warning

* More robust from_pretrained init_kwargs type checking

* Corrected for Python 3.10

* Type checks subclasses and fixed type warnings

* More type corrections and skip tokenizer type checking

* make style && make quality

* Updated docs and types for Lumina pipelines

* Fixed check for empty signature

* changed location of helper functions

* make style

---------
Co-authored-by: hlky <hlky@hlky.ac>

* lora

* update

* update

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

remove check

Fix docs

* `device_map` in `load_model_dict_into_meta`

* _LOW_CPU_MEM_USAGE_DEFAULT

* fix is_peft_version is_bitsandbytes_version

* update

* update

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

update

fix

template for remote vae.

* fix: run tests from a pr workflow.

* correct

* update

* checking.

* update

* make fix-copies

* update

* tests

* update

* update

* add co-author
Co-Authored-By: Langdx <82783347+Langdx@users.noreply.github.com>

* add co-author
Co-Authored-By: howe <howezhang2018@gmail.com>

* update

---------
Co-authored-by: Langdx <82783347+Langdx@users.noreply.github.com>
Co-authored-by: howe <howezhang2018@gmail.com>

* update

* update

* Added runtime checkpoint conversion

* Updated docs

* Fix for quantized model

* run fast gpu tests conditionally on pull requests.

* revert unneeded changes.

* simplify PR.

install accelerate transformers from .

Add 5 Notebooks, improve their example
scripts and update the missing links for the
example README.

* store cls instead of an obj

* style

* poc encode_prompt() tests

* fix

* updates.

* fixes

* fixes

* updates

* updates

* updates

* revert

* updates

* updates

* updates

* updates

* remove SDXLOptionalComponentsTesterMixin.

* remove tests that directly leveraged encode_prompt() in some way or the other.

* fix imports.

* remove _save_load

* fixes

* fixes

* fixes

* fixes

* add; utility to check if attn_procs,norms,acts are properly documented.

* add support listing to the workflows.

* change to 2024.

* small fixes.

* does adding detailed docstrings help?

* uncomment image processor check

* quality

* fix, thanks to @mishig.

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

* style

* JointAttnProcessor2_0

* fixes

* fixes

* fixes

* fixes

* fixes

* fixes

* Update docs/source/en/api/normalization.md
Co-authored-by: hlky <hlky@hlky.ac>

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

* feat: lora support for Lumina2.

* fix-copies.

* updates

* updates

* docs.

* fix

* add: training script.

* tests

* updates

* updates

* major updates.

* updates

* fixes

* docs.

* updates

* updates

use proper gemma class and config in lumina2 tests.

remove prints

* feat: introduce a style bot.

* updates

* Apply suggestions from code review
Co-authored-by: Guillaume LEGENDRE <glegendre01@gmail.com>

* apply suggestion

* fixes

* updates

---------
Co-authored-by: Guillaume LEGENDRE <glegendre01@gmail.com>

* first draft model loading refactor

* revert name change

* fix bnb

* revert name

* fix dduf

* fix huanyan

* style

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

* suggestions from reviews

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

* remove safetensors check

* fix default value

* more fix from suggestions

* revert logic for single file

* style

* typing + fix couple of issues

* improve speed

* Update src/diffusers/models/modeling_utils.py
Co-authored-by: Aryan <aryan@huggingface.co>

* fp8 dtype

* add tests

* rename resolved_archive_file to resolved_model_file

* format

* map_location default cpu

* add utility function

* switch to smaller model + test inference

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

* rm comment

* add log

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

* add decorator

* cosine sim instead

* fix use_keep_in_fp32_modules

* comm

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

* make set_adapters() robust on silent failures.

* fixes to tests

* flaky decorator.

* fix

* flaky to sd3.

* remove warning.

* sort

* quality

* skip test_simple_inference_with_text_denoiser_multi_adapter_block_lora

* skip testing unsupported features.

* raise warning instead of error.

DiffusionPipeline mixin `to`+FromOriginalModelMixin/FromSingleFileMixin `from_single_file` type hint (#10811)

* DiffusionPipeline mixin `to` type hint

* FromOriginalModelMixin from_single_file

* FromSingleFileMixin from_single_file

add missing entries to the lora docs.

This PR updates the max_shift value in flux to 1.15 for consistency across the codebase. In addition to modifying max_shift in flux, all related functions that copy and use this logic, such as calculate_shift in `src/diffusers/pipelines/stable_diffusion_3/pipeline_stable_diffusion_3_img2img.py`, have also been updated to ensure uniform behavior.

update lora support for flux.

fix