GitLab

* make attn slice recursive

* remove set_attention_slice from blocks

* fix copies

* make enable_attention_slicing base class method of DiffusionPipeline

* fix set_attention_slice

* fix set_attention_slice

* fix copies

* add tests

* up

* up

* up

* update

* up

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

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

* Update bug-report.yml

* Update bug-report.yml

* Update bug-report.yml

small but mighty

up

* [CI] Add slow MPS tests

* fix yml

* temporarily resolve caching

* Tests: fix mps crashes.

* Skip test_load_pipeline_from_git on mps.

Not compatible with float16.

* Increase tolerance, use CPU generator, alt. slices.

* Move to nightly

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

* Add xformers attention to VAE

* Simplify VAE xformers code

* Update src/diffusers/models/attention.py
Co-authored-by: Ilmari Heikkinen <ilmari@fhtr.org>
Co-authored-by: Suraj Patil <surajp815@gmail.com>

* Add parameter safe_serialization to DiffusionPipeline.save_pretrained

* Add option safe_serialization on ModelMixin.save_pretrained

* Add test test_save_safe_serialization

* Black

* Re-trigger the CI

* Fix doc-builder

* Validate files are saved as safetensor in test_save_safe_serialization

- Add the missing `scale_model_input` method to `FlaxLMSDiscreteScheduler`
- Use `jnp.append` for appending to `state.derivatives`
- Use `jnp.delete` to pop from `state.derivatives`

* 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

* Fixed mask+masked_image in sd inpaint pipeline

Those were left unset when inputs are not PIL images

* Fixed formatting

* up

* up

* finish

* finish

* up

* up

* finish

Fixed doc to install from training packages

fix typo, remove incorrect arguments from .train()

* Do not use torch.long in mps

Addresses #1056.

* Use torch.int instead of float.

* Propagate changes.

* Do not silently change float -> int.

* Propagate changes.

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

* 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>

* Conversion SD 2

* finish

Allow returning local path

* Add an explicit `--image_size` to the conversion script

* style

* Fix Flax flip_sin_to_cos

* Adding flip_sin_to_cos
Co-authored-by: Kashif Rasul <kashif.rasul@gmail.com>

* support v prediction in other schedulers

* v heun

* add tests for v pred

* fix tests

* fix test euler a

* v ddpm

* 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

* Correct stacklevel

* fix

* Replace deprecated hub utils in `train_unconditional_ort`

* typo

* Add doc for Stable Diffusion on Habana Gaudi

* Make style

* Add benchmark

* Center-align columns in the benchmark table