Add Stable Diffusion 2.0 models

[mrauhu]

Hello, @AbdBarho.

Stable Diffusion 2.0 is released.

Models

• 768x768
  https://huggingface.co/stabilityai/stable-diffusion-2
  • https://huggingface.co/stabilityai/stable-diffusion-2/blob/main/768-v-ema.ckpt
• 512x512
  https://huggingface.co/stabilityai/stable-diffusion-2-base
  • https://huggingface.co/stabilityai/stable-diffusion-2-base/resolve/main/512-base-ema.ckpt
• Depth-to-Image
  https://huggingface.co/stabilityai/stable-diffusion-2-depth
  • https://huggingface.co/stabilityai/stable-diffusion-2-depth/blob/main/512-depth-ema.ckpt
• Inpainting
  https://huggingface.co/stabilityai/stable-diffusion-2-inpainting
  • https://huggingface.co/stabilityai/stable-diffusion-2-inpainting/blob/main/512-inpainting-ema.ckpt
• Super-resolution Upscaler Diffusion
  https://huggingface.co/stabilityai/stable-diffusion-x4-upscaler
  • https://huggingface.co/stabilityai/stable-diffusion-x4-upscaler/blob/main/x4-upscaler-ema.ckpt

See also

• [Feature Request]: Support for new 2.0 models | 768x768 resolution + new 512x512 + depth + inpainting AUTOMATIC1111/stable-diffusion-webui#5011

Can you add new models to the download service?

Best wishes,
Sergey.

[AbdBarho]

@mrauhu cool!

It is not backwards compatible so we are going to have to wait for the UIs to get updated.

Exciting stuff!

[ryanbrackney]

Did this ever happen? The download docker compose still only brings in 1.5.

[AbdBarho]

@ryanbrackney #244

It is still in progress, I don't know why but the generated images are incoherent: