* Add `final_sigma_zero` to UniPCMultistep
Effectively the same trick as DDIM's `set_alpha_to_one` and
DPM's `final_sigma_type='zero'`.
Currently False by default but maybe this should be True?
* `final_sigma_zero: bool` -> `final_sigmas_type: str`
Should 1:1 match DPM Multistep now.
* Set `final_sigmas_type='sigma_min'` in UniPC UTs
* Initial commit
* Implemented block lora
- implemented block lora
- updated docs
- added tests
* Finishing up
* Reverted unrelated changes made by make style
* Fixed typo
* Fixed bug + Made text_encoder_2 scalable
* Integrated some review feedback
* Incorporated review feedback
* Fix tests
* Made every module configurable
* Adapter to new lora test structure
* Final cleanup
* Some more final fixes
- Included examples in `using_peft_for_inference.md`
- Added hint that only attns are scaled
- Removed NoneTypes
- Added test to check mismatching lens of adapter names / weights raise error
* Update using_peft_for_inference.md
* Update using_peft_for_inference.md
* Make style, quality, fix-copies
* Updated tutorial;Warning if scale/adapter mismatch
* floats are forwarded as-is; changed tutorial scale
* make style, quality, fix-copies
* Fixed typo in tutorial
* Moved some warnings into `lora_loader_utils.py`
* Moved scale/lora mismatch warnings back
* Integrated final review suggestions
* Empty commit to trigger CI
* Reverted emoty commit to trigger CI
---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
* speed up test_vae_slicing in animatediff
* speed up test_karras_schedulers_shape for attend and excite.
* style.
* get the static slices out.
* specify torch print options.
* modify
* test run with controlnet
* specify kwarg
* fix: things
* not None
* flatten
* controlnet img2img
* complete controlet sd
* finish more
* finish more
* finish more
* finish more
* finish the final batch
* add cpu check for expected_pipe_slice.
* finish the rest
* remove print
* style
* fix ssd1b controlnet test
* checking ssd1b
* disable the test.
* make the test_ip_adapter_single controlnet test more robust
* fix: simple inpaint
* multi
* disable panorama
* enable again
* panorama is shaky so leave it for now
* remove print
* raise tolerance.
* Bug fix for controlnetpipeline check_image
Bug fix for controlnetpipeline check_image when using multicontrolnet and prompt list
* Update test_inference_multiple_prompt_input function
* Update test_controlnet.py
add test for multiple prompts and multiple image conditioning
* Update test_controlnet.py
Fix format error
---------
Co-authored-by: Lvkesheng Shen <45848260+Fantast416@users.noreply.github.com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
* add remove_all_hooks
* a few more fix and tests
* up
* Update src/diffusers/pipelines/pipeline_utils.py
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>
* split tests
* add
---------
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>
* feat: support dora loras from community
* safe-guard dora operations under peft version.
* pop use_dora when False
* make dora lora from kohya work.
* fix: kohya conversion utils.
* add a fast test for DoRA compatibility..
* add a nightly test.
* Add properties and `IPAdapterTesterMixin` tests for `StableDiffusionPanoramaPipeline`
* Update torch manual seed to use `torch.Generator(device=device)`
* Refactor 📞🔙 to support `callback_on_step_end`
* make fix-copies
* debugging
* let's see the numbers
* let's see the numbers
* let's see the numbers
* restrict tolerance.
* increase inference steps.
* shallow copy of cross_attentionkwargs
* remove print
* 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
* Initial commit
* Removed copy hints, as in original SDXLControlNetPipeline
Removed copy hints, as in original SDXLControlNetPipeline, as the `make fix-copies` seems to have issues with the @property decorator.
* Reverted changes to ControlNetXS
* Addendum to: Removed changes to ControlNetXS
* Added test+docs for mixture of denoiser
* Update docs/source/en/using-diffusers/controlnet.md
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
* Update docs/source/en/using-diffusers/controlnet.md
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
* [bug] Fix float/int guidance scale not working in `StableVideoDiffusionPipeline`
* Add test to disable CFG on SVD
---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
* move model helper function in pipeline to EfficiencyMixin
---------
Co-authored-by: YiYi Xu <yixu310@gmail.com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
* DPMMultistep rescale_betas_zero_snr
* DPM upcast samples in step()
* DPM rescale_betas_zero_snr UT
* DPMSolverMulti move sample upcast after model convert
Avoids having to re-use the dtype.
* Add a newline for Ruff
* Make LoRACompatibleConv padding_mode work.
* Format code style.
* add fast test
* Update src/diffusers/models/lora.py
Simplify the code by patrickvonplaten.
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
* code refactor
* apply patrickvonplaten suggestion to simplify the code.
* rm test_lora_layers_old_backend.py and add test case in test_lora_layers_peft.py
* update test case.
---------
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: YiYi Xu <yixu310@gmail.com>
