YiYi Xu 5990014700 [WIP]Vae preprocessor refactor (PR1) (#3557) ...

VaeImageProcessor.preprocess refactor

* refactored VaeImageProcessor 
   -  allow passing optional height and width argument to resize()
   - add convert_to_rgb
* refactored prepare_latents method for img2img pipelines so that if we pass latents directly as image input, it will not encode it again
* added a test in test_pipelines_common.py to test latents as image inputs
* refactored img2img pipelines that accept latents as image: 
   - controlnet img2img, stable diffusion img2img , instruct_pix2pix

---------

Co-authored-by: yiyixuxu <yixu310@gmail,com>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

2023-06-05 07:11:00 -10:00

..

__init__.py

[AltDiffusion] add tests (#1311)

2022-11-16 15:40:26 +01:00

test_alt_diffusion_img2img.py

Refactor full determinism (#3485)

2023-05-22 11:15:11 +01:00

test_alt_diffusion.py

[WIP]Vae preprocessor refactor (PR1) (#3557)

2023-06-05 07:11:00 -10:00