* 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.
* 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 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>
* 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>
* 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>
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.
* 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>
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.
[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)
* 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
* Moving the mem efficiient attention activation to the top + recursive
* black, too bad there's no pre-commit ?
Co-authored-by: Benjamin Lefaudeux <benjamin@photoroom.com>
* feat: switch core pipelines to use image arg
* test: update tests for core pipelines
* feat: switch examples to use image arg
* docs: update docs to use image arg
* style: format code using black and doc-builder
* fix: deprecate use of init_image in all pipelines
* Adapt ddpm, ddpmsolver to prediction_type.
* Deprecate predict_epsilon in __init__.
* Bring FlaxDDIMScheduler up to date with DDIMScheduler.
* Set prediction_type as an ivar for consistency.
* Convert pipeline_ddpm
* Adapt tests.
* Adapt unconditional training script.
* Adapt BitDiffusion example.
* Add missing kwargs in dpmsolver_multistep
* Ugly workaround to accept deprecated predict_epsilon when loading
schedulers using from_pretrained.
* make style
* Remove import no longer in use.
* Apply suggestions from code review
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
* Use config.prediction_type everywhere
* Add a couple of Flax prediction type tests.
* make style
* fix register deprecated arg
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
