smoretalk / clip-interrogator-turbo

@pharmapsychotic 's CLIP-Interrogator, but 3x faster and more accurate. Specialized on SDXL.

  • Public
  • 1.4M runs
  • L40S

Input

image
*file

Input image

string

Prompt Mode: fast takes 1-2 seconds, best takes 15-25 seconds.

Default: "best"

Output

a painting of a yellow car parked in front of a house with trees in the, by Makoto Shinkai, featured on pixiv, makoto shinkai. high detail, by makoto shinkai, in style of makoto shinkai, makoto shinkai art style, makoto shinkai. —h 2160, anime keyframe
Generated in

This example was created by a different version, smoretalk/clip-interrogator-turbo:f66767bb.

Run time and cost

This model costs approximately $0.0011 to run on Replicate, or 909 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 L40S GPU hardware. Predictions typically complete within 2 seconds.

Readme

@pharmapsychotic ‘s CLIP-Interrogator, but fully-optimized version. You can get more exact prompt from an image with 3x faster speed. To create cool reference-based image, visit https://flamel.app/