Stable diffusion text2img conversion script. (huggingface#154)

* begin text2img conversion script

* add fn to convert config

* create config if not provided

* update imports and use UNet2DConditionModel

* fix imports, layer names

* fix unet coversion

* add function to convert VAE

* fix vae conversion

* update main

* create text model

* update config creating logic for unet

* fix config creation

* update script to create and save pipeline

* remove unused imports

* fix checkpoint loading

* better name

* save progress

* finish

* up

* up

Co-authored-by: Patrick von Platen <[email protected]>