GitLab

upgrade version

* [SD] Make sure batched input works correctly

* uP

* uP

* up

* up

* uP

* up

* fix mask stuff

* up

* uP

* more up

* up

* uP

* up

* finish

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

* Fix type checking remainders

* Remove IS_V20_MODEL flag always being True
Co-authored-by: apolinario <joaopaulo.passos+multimodal@gmail.com>

* Added Community pipeline for comparing Stable Diffusion v1.1-4
Signed-off-by: Suvaditya Mukherjee <suvadityamuk@gmail.com>

* Made changes to provide support for current iteration of from_pretrained and added example
Signed-off-by: Suvaditya Mukherjee <suvadityamuk@gmail.com>

* updated a small spelling error
Signed-off-by: Suvaditya Mukherjee <suvadityamuk@gmail.com>

* added pipeline entry to table
Signed-off-by: Suvaditya Mukherjee <suvadityamuk@gmail.com>
Signed-off-by: Suvaditya Mukherjee <suvadityamuk@gmail.com>

handle missing global_step key and don't download config if it already exists

* fix bug if we don't do_classifier_free_guidance

* update for copied diffusers.pipelines..alt_diffusion..pipeline_alt_diffusion.AltDiffusionPipeline

Deprecate init image correctl

bug fix
Co-authored-by: Prathik Rao <prathikrao@microsoft.com>
Co-authored-by: anton- <anton@huggingface.co>

* fix versatile diffusion input

* merge main

* `make fix-copies`
Co-authored-by: anton- <anton@huggingface.co>

* Initial code for attempt at improving SD <--> diffusers conversions for v2.0

* Updates to support round-trip between orig. SD 2.0 and diffusers models

* Corrected formatting to Black standard

* Correcting import formatting

* Fixed imports (properly this time)

* add some corrections

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

Since no deprecate() call was done, the typos were silently ignored.

remove unnecessary offset in img2img

Allow k pipeline to generate > 1 images.

dreambooth: fix #1566: maintain fp32 wrapper when saving a checkpoint to avoid crash when running fp16 (#1618)

* dreambooth: fix #1566: maintain fp32 wrapper when saving a checkpoint to avoid crash when running fp16

* dreambooth: guard against passing keep_fp32_wrapper arg to older versions of accelerate. part of fix for #1566

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

* Update examples/dreambooth/train_dreambooth.py
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

Remove spurious arg in training scripts.

* do not automatically enable xformers

* uP

* Adapt to forced transformers version in some dependent libraries

* style

* Update __init__.py

* update requires_backends

* Re-add xformers enable to UNet2DCondition (#1627)

* finish

* fix

* Update tests/models/test_models_unet_2d.py

* style
Co-authored-by: Anton Lozhkov <anton@huggingface.co>

* Release: v0.10.1
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* finish

* fix

* Update tests/models/test_models_unet_2d.py

* style
Co-authored-by: Anton Lozhkov <anton@huggingface.co>

Don't assume 512x512 in k-diffusion pipeline.

* Update requirements.txt

* Update requirements_flax.txt

* Update requirements.txt

* Update requirements_flax.txt

* Update requirements.txt

* Update requirements_flax.txt

* begin depth pipeline

* add depth estimation model

* fix prepare_depth_mask

* add a comment about autocast

* copied from, quality, cleanup

* begin tests

* handle tensors

* norm image tensor

* fix batch size

* fix tests

* fix enable_sequential_cpu_offload

* fix save load

* fix test_save_load_float16

* fix test_save_load_optional_components

* fix test_float16_inference

* fix test_cpu_offload_forward_pass

* fix test_dict_tuple_outputs_equivalent

* up

* fix fast tests

* fix test_stable_diffusion_img2img_multiple_init_images

* fix few more fast tests

* don't use device map for DPT

* fix test_stable_diffusion_pipeline_with_sequential_cpu_offloading

* accept external depth maps

* prepare_depth_mask -> prepare_depth_map

* fix file name

* fix file name

* quality

* check transformers version

* fix test names

* use skipif

* fix import

* add docs

* skip tests on mps

* correct version

* uP

* Update docs/source/api/pipelines/stable_diffusion_2.mdx

* fix fix-copies

* fix fix-copies
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: anton- <anton@huggingface.co>

* Fix PyCharm/VSCode static type checking for dummy objects

* Re-add dummies

* Fix AudioDiffusion imports

* fix import

* fix import

* Update utils/check_dummies.py
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

* Update src/diffusers/utils/import_utils.py

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

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

* fix double import
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

add upcast_attention arg

* uP

* uP

easy fix for undefined name in train_dreambooth.py

import_model_class_from_model_name_or_path loads a pretrained model
and refers to args.revision in a context where args is undefined. I modified
the function to take revision as an argument and modified the invocation
of the function to pass in the revision from args. Seems like this was caused
by a cut and paste.

* [ONNX] Fix flaky tests

* revert

* Make cross-attention check more robust.

* Fix copies.

* init docs update

* style

* fix bad colab formatting, add pipeline comment

* update todo

* Update scheduling_repaint.py

* update the expected image
Co-authored-by: anton- <anton@huggingface.co>

* fix upcast in slice attention

* fix dtype

* add test

* fix test

* add singlestep dpmsolver

* fix a style typo

* fix a style typo

* add docs

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

* Do not recompile when guidance_scale changes.

* Remove debug for simplicity.

* make style

* Make guidance_scale an array.

* Make DEBUG a constant to avoid passing it down.

* Add comments for clarification.

upcast attention