vivalapanda / conceptual-image-to-image-1.5

Conceptual image-to-image model for Stable Diffusion 1.5

  • Public
  • 1K runs
  • GitHub

Run time and cost

This model costs approximately $0.042 to run on Replicate, or 23 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.

This model runs on Nvidia A100 (80GB) GPU hardware. Predictions typically complete within 30 seconds. The predict time for this model varies significantly based on the inputs.

Readme

This model lets you condition on image content when performing image-to-image with Stable Diffusion.

Combine both structural and conceptual guidance from the initial image for the best results!

A model for SD 2.0 is also available here: https://replicate.com/vivalapanda/conceptual-image-to-image However, our initial test prompts generally did better with SD 1.5 - so you might need to do some more tinkering to figure out where SD 2.0 shines!