DALL-E API to generate json data from image

[N2U]

I wrote a script that does step 1 a while back (and prints the descriptions to a CSV). If you’re interested, you can find it here:

Image Upload / Recognition via Bing Chat

So in the absence of a Clip API, I decided to generate captions for images using Salesforce’s BLIP (Bootstrapped Language Image Pre-training) model. It’s not perfect, but it works and it only uses 32mb of ram Usage The script is intended to be run from the command line. The images should be placed in an ‘images’ directory located in the same directory as the script. The script will process all images in the ‘images’ directory and save the results to a file in the same directory as the script. O…