* begin animatediff img2video and video2video
* revert animatediff to original implementation
* add img2video as pipeline
* update
* add vid2vid pipeline
* update imports
* update
* remove copied from line for check_inputs
* update
* update examples
* add multi-batch support
* fix __init__.py files
* move img2vid to community
* update community readme and examples
* fix
* make fix-copies
* add vid2vid batch params
* apply suggestions from review
Co-Authored-By: Dhruv Nair <dhruv.nair@gmail.com>
* add test for animatediff vid2vid
* torch.stack -> torch.cat
Co-Authored-By: Dhruv Nair <dhruv.nair@gmail.com>
* make style
* docs for vid2vid
* update
* fix prepare_latents
* fix docs
* remove img2vid
* update README to :main
* remove slow test
* refactor pipeline output
* update docs
* update docs
* merge community readme from :main
* final fix i promise
* add support for url in animatediff example
* update example
* update callbacks to latest implementation
* Update src/diffusers/pipelines/animatediff/pipeline_animatediff_video2video.py
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
* Update src/diffusers/pipelines/animatediff/pipeline_animatediff_video2video.py
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
* fix merge
* Apply suggestions from code review
* remove callback and callback_steps as suggested in review
* Update tests/pipelines/animatediff/test_animatediff_video2video.py
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
* fix import error caused due to unet refactor in #6630
* fix numpy import error after tensor2vid refactor in #6626
* make fix-copies
* fix numpy error
* fix progress bar test
---------
Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>
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
* [Fix] Multiple image conditionings in a single batch for `StableDiffusionControlNetPipeline`.
* Refactor `check_inputs` in `StableDiffusionControlNetPipeline` to avoid redundant codes.
* Make the behavior of MultiControlNetModel to be the same to the original ControlNetModel
* Keep the code change minimum for nested list support
* Add fast test `test_inference_nested_image_input`
* Remove redundant check for nested image condition in `check_inputs`
Remove `len(image) == len(prompt)` check out of `check_image()`
Co-authored-by: YiYi Xu <yixu310@gmail.com>
* Better `ValueError` message for incompatible nested image list size
Co-authored-by: YiYi Xu <yixu310@gmail.com>
* Fix syntax error in `check_inputs`
* Remove warning message for multi-ControlNets with multiple prompts
* Fix a typo in test_controlnet.py
Co-authored-by: YiYi Xu <yixu310@gmail.com>
* Add test case for multiple prompts, single image conditioning in `StableDiffusionMultiControlNetPipelineFastTests`
* Improved `ValueError` message for nested `controlnet_conditioning_scale`
* Documenting the behavior of image list as `StableDiffusionControlNetPipeline` input
---------
Co-authored-by: YiYi Xu <yixu310@gmail.com>
* debug
* debug test_with_different_scales_fusion_equivalence
* use the right method.
* place it right.
* let's see.
* let's see again
* alright then.
* add a comment.
* add: test to check if peft loras are loadable in non-peft envs.
* add torch_device approrpiately.
* fix: get_dummy_inputs().
* test logits.
* rename
* debug
* debug
* fix: generator
* new assertion values after fixing the seed.
* shape
* remove print statements and settle this.
* to update values.
* change values when lora config is initialized under a fixed seed.
* update colab link
* update notebook link
* sanity restored by getting the exact same values without peft.
* Add unload_ip_adapter method
* Update attn_processors with original layers
* Add test
* Use set_default_attn_processor
---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
* add adapter_name in fuse
* add tesrt
* up
* fix CI
* adapt from suggestion
* Update src/diffusers/utils/testing_utils.py
Co-authored-by: Benjamin Bossan <BenjaminBossan@users.noreply.github.com>
* change to `require_peft_version_greater`
* change variable names in test
* Update src/diffusers/loaders/lora.py
Co-authored-by: Benjamin Bossan <BenjaminBossan@users.noreply.github.com>
* break into 2 lines
* final comments
---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: Benjamin Bossan <BenjaminBossan@users.noreply.github.com>
* EulerAncestral add `rescale_betas_zero_snr`
Uses same infinite sigma fix from EulerDiscrete. Interestingly the
ancestral version had the opposite problem: too much contrast instead of
too little.
* UT for EulerAncestral `rescale_betas_zero_snr`
* EulerAncestral upcast samples during step()
It helps this scheduler too, particularly when the model is using bf16.
While the noise dtype is still the model's it's automatically upcasted
for the add so all it affects is determinism.
---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
* fix: init for vae during pixart tests
* print the values
* add flatten
* correct assertion value for test_inference
* correct assertion values for test_inference_non_square_images
* run styling
* debug test_inference_with_multiple_images_per_prompt
* fix assertion values for test_inference_with_multiple_images_per_prompt
