GitLab

Support ColossalAi for Dreamblooth

* added first version of the tiled upscaling pipeline

* reformatted to pass code quality tests

* Various Fixes for Flax Dreambooth

- Correctly update the progress bar every epoch
- Allow specifying a pretrained VAE
- Allow specifying a revision to pretrained models
- Cache compiled models between invocations (speeds up TPU execution a lot!)
- Save intermediate checkpoints by specifying `save_steps`

* Don't die when save_steps is not set.

* Address CR

* Address comments

* Apply suggestions from code review
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>
Co-authored-by: Suraj Patil <surajp815@gmail.com>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

Fix default lr-scaling cli argument

* Support training SD V2 with Flax

Mostly involves supporting a v_prediction scheduler.

The implementation in #1777 doesn't take into account a recent refactor of `scheduling_utils_flax`, so this should be used instead.

* Add to other top-level files.

fix resume step in train_text_to_image example

* [Deterministic torch randn] Allow tensors to be generated on CPU

* fix more

* up

* fix more

* up

* Update src/diffusers/utils/torch_utils.py
Co-authored-by: Anton Lozhkov <anton@huggingface.co>

* Apply suggestions from code review

* up

* up

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

Fixes to the help for report_to in training scripts.

* misc fixes

* more comments

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

* set transformers verbosity to warning
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

Fix typo in train_dreambooth_inpaint.

* allow using non-ema weights for training

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

* address more review comment

* reorganise a few lines

* always pad text to max_length to match original training

* ifx collate_fn

* remove unused code

* don't prepare ema_unet, don't register lr scheduler

* style

* assert => ValueError

* add allow_tf32

* set log level

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

update loss computation

* Fix ema decay and clarify nomenclature.

* Rename var.

* move files a bit

* more refactors

* fix more

* more fixes

* fix more onnx

* make style

* upload

* fix

* up

* fix more

* up again

* up

* small fix

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

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

Co-authored-by: Henrik Forstén <henrik.forsten@gmail.com>

* update TI script

* make flake happy

* fix typo

* initial

* type hints

* update scheduler type hint

* add to README

* add example generation to README

* v -> mix_factor

* load scheduler from pretrained

* allow selecting precision to make DB class images

addresses #1831

* add prior_generation_precision argument

* correct prior_generation_precision's description
Co-authored-by: Suraj Patil <surajp815@gmail.com>
Co-authored-by: Suraj Patil <surajp815@gmail.com>

* Make xformers optional even if it is available

* Raise exception if xformers is used but not available

* Rename use_xformers to enable_xformers_memory_efficient_attention

* Add a note about xformers in README

* Reformat code style

* unwrap_model text encoder before accessing weights

* fix another call

* fix the right call

* Remove hardcoded names from PT scripts

* Apply suggestions from code review
Co-authored-by: Suraj Patil <surajp815@gmail.com>

* reorder model wrap

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

* Section header for in-painting, inference from checkpoint.

* Inference: link to section to perform inference from checkpoint.

* Move Dreambooth in-painting instructions to the proper place.

* [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