Image to prompt with BLIP and CLIP
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
 
 
pharmapsychotic 0a87f2b013
Merge pull request #1 from altryne/patch-1
3 years ago
data Fixed some mangled artist names 3 years ago
LICENSE Initial commit 3 years ago
README.md Ported my CLIP Interrogator over to colab to share 3 years ago
clip_interrogator.ipynb Note about stable diffustion 3 years ago

README.md

clip-interrogator

Open In Colab

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.