wrglbr / clip-interrogator

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.

clip-interrogator

This is a fork of https://github.com/pharmapsychotic/clip-interrogator that has been ported to python and can be run in the terminal. It has also been given the ability to process batches of images.

Setup

python setup.py 

Usage

Run:

python cli.py -i https://i.ytimg.com/vi/0k1xU4Kp5Go/maxresdefault.jpg

Options:

• -i URL or path to image to interrogate
• -f File with a list of images to interrogate
• -o Output file to save prompts to, defaults to stdout

Changes to file list loop

• Now loops through every file in list, runs, and saves prompt to a .txt file with the same name as the original image, in the same directory