GitLab

* [Flax] Stateless schedulers, fixes and refactors

* Remove scheduling_common_flax and some renames

* Update src/diffusers/schedulers/scheduling_pndm_flax.py
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

* expose polynomial:power and cosine_with_restarts:num_cycles using get_scheduler func, add it to train_dreambooth.py

* fix formatting

* fix style

* Update src/diffusers/optimization.py
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

* reflect changes

* run make style
Co-authored-by: Prathik Rao <prathikrao@microsoft.com>
Co-authored-by: Prathik Rao <prathikrao@microsoft.com@orttrainingdev7.d32nl1ml4oruzj4qz3bqlggovf.px.internal.cloudapp.net>

* Fail if there are less images than the effective batch size.

* Remove lr-scheduler arg as it's currently ignored.

* Make guidance_scale work for batch_size > 1.

* update composable diffusion for an updated diffuser library

* fix style/quality for code

* Revert "fix style/quality for code"

This reverts commit 71f23497639fe69de00d93cf91edc31b08dcd7a4.

* update style

* reduce memory usage by computing score sequentially

Update train_unconditional.py

Add logger flag to choose between tensorboard and wandb

* 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

* 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>

* 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`.

Change the one-step dummy pipeline for testing

* 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>

* 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>

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

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

* Update requirements.txt

* Update requirements_flax.txt

* Update requirements.txt

* Update requirements_flax.txt

* Update requirements.txt

* Update requirements_flax.txt

* 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.

* init docs update

* style

* fix bad colab formatting, add pipeline comment

* update todo

* fix lpw_stable_diffusion

* rollback preprocess_mask resample

make collate_fn global

* add check_min_version for examples

* move __version__ to the top

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

* fix comment

* fix error_message

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

* Mega community pipeline

* fix

* Research folder

* Update examples/research_projects/README.md

* up

The mask and instance image were being cropped in different ways without --center_crop, causing the model to learn to ignore the mask in some cases. This PR fixes that and generate more consistent results.

us from_pretrained to load scheduler

[textual_inversion] Add an option to only save embeddings

Add an command line option --only_save_embeds to the example script, for
not saving the full model. Then only the learned embeddings are saved,
which can be added to the original model at runtime in a similar way as
they are created in the training script.
Saving the full model is forced when --push_to_hub is used. (Implements #759)

* Add checkpoint_merger pipeline

* Added missing docs for a parameter.

* Fomratting fixes.

* Fixed code quality issues.

* Bug fix: Off by 1 index

* Added docs for pipeline

* Create train_dreambooth_inpaint.py

train_dreambooth.py adapted to work with the inpaint model, generating random masks during the training

* Update train_dreambooth_inpaint.py

refactored train_dreambooth_inpaint with black

* Update train_dreambooth_inpaint.py

* Update train_dreambooth_inpaint.py

* Update train_dreambooth_inpaint.py

Fix prior preservation

* add instructions to readme, fix SD2 compatibility

* up

* up

* finish

* finish

* up

* up

* finish