GitLab

* 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>

Use warnings instead of logger in parse_args()

logger requires an `Accelerator`.

* 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>

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

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.

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>

us from_pretrained to load scheduler

* [Dreambooth] Make compatible with alt diffusion

* make style

* add example

* add get_velocity

* add v prediction for training

* fix saving

* add revision arg

* fix saving

* save checkpoints dreambooth

* fix saving embeds

* add instruction in readme

* quality

* noise_pred -> model_pred

* use accelerator to check mixed_precision

* default `mixed_precision` to `None`

* pass mixed_precision to accelerate launch

* [Examples] Correct path

* uP

* Make errors for invalid options without "--with_prior_preservation"

* Make --instance_prompt required

* Removed needless check because --instance_data_dir is marked with required

* Updated messages

* Use logger.warning instead of raise errors
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* [Better scheduler docs] Improve usage examples of schedulers

* finish

* fix warnings and add test

* finish

* more replacements

* adapt fast tests hf token

* correct more

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

* Integrate compatibility with euler
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

Set train mode for text encoder

make input_args optional

* Make training code usable by external scripts

Add parameter inputs to training and argument parsing function to allow this script to be used by an external call.

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

* Add --pretrained_model_name_revision option to train_dreambooth.py

* Renamed --pretrained_model_name_revision to --revision

* Add an underscore to filename if it already exists

* Use sha1sum hash instead of adding underscores

dont' use safety check when generating prior images

* allow fine-tuning text encoder

* fix a few things

* update readme

Fix dreambooth loss type with prior preservation

* Support deepspeed

* Dreambooth DeepSpeed documentation

* Remove unnecessary casts, documentation

Due to recent commits some casts to half precision are not necessary
anymore.

Mention that DeepSpeed's version of Adam is about 2x faster.

* Review comments

* Fix push_to_hub for dreambooth and textual_inversion

* Use repo.push_to_hub instead of push_to_hub

up

remove use_auth_token

using already created `Path` in dataset

* Fix typos

* Update examples/dreambooth/train_dreambooth.py
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

fix applying clip grad norm

don't pass tensor_format

* Add training example for DreamBooth.

* Fix bugs.

* Update readme and default hyperparameters.

* Reformatting code with black.

* Update for multi-gpu trianing.

* Apply suggestions from code review

* improgve sampling

* fix autocast

* improve sampling more

* fix saving

* actuallu fix saving

* fix saving

* improve dataset

* fix collate fun

* fix collate_fn

* fix collate fn

* fix key name

* fix dataset

* fix collate fn

* concat batch in collate fn

* add grad ckpt

* add option for 8bit adam

* do two forward passes for prior preservation

* Revert "do two forward passes for prior preservation"

This reverts commit 661ca4677e6dccc4ad596c2ee6ca4baad4159e95.

* add option for prior_loss_weight

* add option for clip grad norm

* add more comments

* update readme

* update readme

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

* add docstr for dataset

* update the saving logic

* Update examples/dreambooth/README.md

* remove unused imports
Co-authored-by: Suraj Patil <surajp815@gmail.com>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* Fix typos

* Add a typo check action

* Fix a bug

* Changed to manual typo check currently

Ref: https://github.com/huggingface/diffusers/pull/483#pullrequestreview-1104468010

Co-authored-by: Anton Lozhkov <aglozhkov@gmail.com>

* Removed a confusing message

* Renamed "nin_shortcut" to "in_shortcut"

* Add memo about NIN
Co-authored-by: Anton Lozhkov <aglozhkov@gmail.com>

* beta never changes removed from state

* fix typos in docs

* removed unused var

* initial ddim flax scheduler

* import

* added dummy objects

* fix style

* fix typo

* docs

* fix typo in comment

* set return type

* added flax ddom

* fix style

* remake

* pass PRNG key as argument and split before use

* fix doc string

* use config

* added flax Karras VE scheduler

* make style

* fix dummy

* fix ndarray type annotation

* replace returns a new state

* added lms_discrete scheduler

* use self.config

* add_noise needs state

* use config

* use config

* docstring

* added flax score sde ve

* fix imports

* fix typos