add callbacks to denoising step (#5427)
* draft1
* update
* style
* move to the end of loop
* update
* update callbak_on_step_end_inputs
* Revert "update"
This reverts commit 5f9b153183d0cde3b850f14024d2e37ae8c19576.
* Revert "update callbak_on_step_end_inputs"
This reverts commit 44889f4dabad95b7ebb330faa5f1955b5d008c88.
* update
* update test required_optional_params
* remove self.lora_scale
* img2img
* inpaint
* Apply suggestions from code review
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
* fix
* apply feedbacks on img2img + inpaint: keep only important pipeline attributes
* depth
* pix2pix
* make _callback_tensor_inputs an class variable so that we can use it for testing
* add a basic tst for callback
* add a read-only tensor input timesteps + fix tests
* add second test for callback cfg
* sdxl
* sdxl img2img
* sdxl inpaint
* kandinsky prior
* kandinsky decoder
* kandinsky img2img + combined
* kandinsky inpaint
* fix copies
* fix
* consistent default inputs
* fix copies
* wuerstchen_prior prior
* test_wuerstchen_decoder + fix test for prior
* wuerstchen_combined pipeline + skip tests
* skip test for kandinsky combined
* lcm
* remove timesteps etc
* add doc string
* copies
* Update src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion.py
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
* Update src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion.py
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
* make style and improve tests
* up
* up
* fix more
* fix cfg test
* tests for callbacks
* fix for real
* update
* lcm img2img
* add doc
* add doc page to index
---------
Co-authored-by: yiyixuxu <yixu310@gmail,com>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>