* Fix multi-gpu case
* Prefer previously created `unwrap_model()` function
For `torch.compile()` generalizability
* `chore: update unwrap_model() function to use accelerator.unwrap_model()`
* Add vae_roundtrip.py example
* Add cuda support to vae_roundtrip
* Move vae_roundtrip.py into research_projects/vae
* Fix channel scaling in vae roundrip and also support taesd.
* Apply ruff --fix for CI gatekeep check
---------
Co-authored-by: Álvaro Somoza <asomoza@users.noreply.github.com>
* Trim all the trailing white space in the whole repo
* Remove unnecessary empty places
* make style && make quality
* Trim trailing white space
* trim
---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
* find & replace all FloatTensors to Tensor
* apply formatting
* Update torch.FloatTensor to torch.Tensor in the remaining files
* formatting
* Fix the rest of the places where FloatTensor is used as well as in documentation
* formatting
* Update new file from FloatTensor to Tensor
* 7879 - adjust documentation to use naruto dataset, since pokemon is now gated
* replace references to pokemon in docs
* more references to pokemon replaced
* Japanese translation update
---------
Co-authored-by: bghira <bghira@users.github.com>
* add scheduled pseudo-huber loss training scripts
See #7488
* add reduction modes to huber loss
* [DB Lora] *2 multiplier to huber loss cause of 1/2 a^2 conv.
pairing of c6495def1f
* [DB Lora] add option for smooth l1 (huber / delta)
Pairing of dd22958caa
* [DB Lora] unify huber scheduling
Pairing of 19a834c3ab
* [DB Lora] add snr huber scheduler
Pairing of 47fb1a6854
* fixup examples link
* use snr schedule by default in DB
* update all huber scripts with snr
* code quality
* huber: make style && make quality
---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
* 7529 do not disable autocast for cuda devices
* Remove typecasting error check for non-mps platforms, as a correct autocast implementation makes it a non-issue
* add autocast fix to other training examples
* disable native_amp for dreambooth (sdxl)
* disable native_amp for pix2pix (sdxl)
* remove tests from remaining files
* disable native_amp on huggingface accelerator for every training example that uses it
* convert more usages of autocast to nullcontext, make style fixes
* make style fixes
* style.
* Empty-Commit
---------
Co-authored-by: bghira <bghira@users.github.com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
* Add properties and `IPAdapterTesterMixin` tests for `StableDiffusionPanoramaPipeline`
* Fix variable name typo and update comments
* Update deprecated `output_type="numpy"` to "np" in test files
* Discard changes to src/diffusers/pipelines/stable_diffusion_panorama/pipeline_stable_diffusion_panorama.py
* Update test_stable_diffusion_panorama.py
* Update numbers in README.md
* Update get_guidance_scale_embedding method to use timesteps instead of w
* Update number of checkpoints in README.md
* Add type hints and fix var name
* Fix PyTorch's convention for inplace functions
* Fix a typo
* Revert "Fix PyTorch's convention for inplace functions"
This reverts commit 74350cf65b.
* Fix typos
* Indent
* Refactor get_guidance_scale_embedding method in LEditsPPPipelineStableDiffusionXL class
* support and example launch for sdxl turbo
* White space fixes
* Trailing whitespace character
* ruff format
* fix guidance_scale and steps for turbo mode
---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: Radames Ajna <radamajna@gmail.com>
* add tags for diffusers training
* add tags for diffusers training
* add tags for diffusers training
* add tags for diffusers training
* add tags for diffusers training
* add tags for diffusers training
* add dora tags for drambooth lora scripts
* style
* move model helper function in pipeline to EfficiencyMixin
---------
Co-authored-by: YiYi Xu <yixu310@gmail.com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
* fix minsnr implementation for v-prediction case
* format code
* always compute snr when snr_gamma is specified
---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
* initial commit for unconditional/class-conditional consistency training script
* make style
* Add entry for consistency training script in community README.
* Move consistency training script from community to research_projects/consistency_training
* Add requirements.txt and README to research_projects/consistency_training directory.
* Manually revert community README changes for consistency training.
* Fix path to script after moving script to research projects.
* Add option to load U-Net weights from pretrained model.
---------
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
* move unets to module 🦋
* parameterize unet-level import.
* fix flax unet2dcondition model import
* models __init__
* mildly depcrecating models.unet_2d_blocks in favor of models.unets.unet_2d_blocks.
* noqa
* correct depcrecation behaviour
* inherit from the actual classes.
* Empty-Commit
* backwards compatibility for unet_2d.py
* backward compatibility for unet_2d_condition
* bc for unet_1d
* bc for unet_1d_blocks
* base template file - train_instruct_pix2pix.py
* additional import and parser argument requried for lora
* finetune only instructpix2pix model -- no need to include these layers
* inject lora layers
* freeze unet model -- only lora layers are trained
* training modifications to train only lora parameters
* store only lora parameters
* move train script to research project
* run quality and style code checks
* move train script to a new folder
* add README
* update README
* update references in README
---------
Co-authored-by: Rahul Raman <rahulraman@gmail.com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
* add: experimental script for diffusion dpo training.
* random_crop cli.
* fix: caption tokenization.
* fix: pixel_values index.
* fix: grad?
* debug
* fix: reduction.
* fixes in the loss calculation.
* style
* fix: unwrap call.
* fix: validation inference.
* add: initial sdxl script
* debug
* make sure images in the tuple are of same res
* fix model_max_length
* report print
* boom
* fix: numerical issues.
* fix: resolution
* comment about resize.
* change the order of the training transformation.
* save call.
* debug
* remove print
* manually detaching necessary?
* use the same vae for validation.
* add: readme.
