GitLab

* Latent Diffusion pipeline accept latents

* make style

* check for mps

randn does not work reproducibly on mps

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

* Add examples with Intel optimizations (BF16 fine-tuning and inference)

* Remove unused package

* Add README for intel_opts and refine the description for research projects

* Add notes of intel opts for diffusers

* add conf.yaml

* enable bf16

enable amp bf16 for unet forward

fix style

fix readme

remove useless file

* change amp to full bf16

* align

* make stype

* fix format

* update inpaint_legacy to allow the use of predicted noise to construct intermediate diffused images

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

* Add state checkpointing to other training scripts

* Fix first_epoch

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

* Update Dreambooth checkpoint help message.

* Dreambooth docs: checkpoints, inference from a checkpoint.

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

* add fast tests

* better tests and fp16

* batch fixes

* Reuse preprocessing

* quickfix

Specify that we don't actively monitor the conda scripts

* Remove bogus file

* [Docs] Remove mentioning of gated access since no longer exsits

* add docs to index

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

* manually update train_unconditional_ort

* formatting
Co-authored-by: Prathik Rao <prathikrao@microsoft.com>

Use warnings instead of logger in parse_args()

logger requires an `Accelerator`.

* [Community pipeline] Add github mechanism

* better

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

* adapt
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

Change the one-step dummy pipeline for testing

fixed #1685 - disables telemetry when DISABLE_TELEMETRY and HF_HUB_OFFLINE is set

* Dreambooth: save / restore training state.

* make style

* Rename vars for clarity.
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

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

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