Saved by Jason Shen
Lore AI Newsletter #7: Stable Diffusion 2.0
Key features of the 2.0 release
- New text-to-image diffusion models using a brand new text encoder (OpenCLIP). Result: improved image quality, although not everyone likes the style.
- Super-resolution upscaler diffusion models which enhance the resolution of images by a factor of 4.
- Depth-to-image diffusion model which infers the depth of an input