clip-interrogator

Match your image to a generated and optimised text prompt for reuse in text-to-image models to transform your visuals into artworks. Endless possibilities await!

Hold: 0

Required: 10,000 $wRAI

20.8k runs

Demo

Examples

Input

image

Click to select a file to input

Input prompt

clip_model_name

Choose ViT-L for Stable Diffusion 1, and ViT-H for Stable Diffusion 2 mode

mode

Prompt mode (best takes 10-20 seconds, fast takes 1-2 seconds).

Hold at least 10,000 wRAI to use this model

Multi AI platform is completely free, but most models are only accessible to wRAI token holders. If you have any questions, feel free to ask in our Telegram chat

Output

Download

Input

clip_model_name

ViT-L-14/openai

image

mode

best

Output

Download

Input

clip_model_name

ViT-L-14/openai

image

mode

best

Output

Download

Readme

The CLIP Interrogator uses the OpenAI CLIP models to test a given image against a variety of artists, mediums, and styles to study how the different models see the content of the image. It also combines the results with BLIP caption to suggest a text prompt to create more images similar to what was given.