compare between two images in terms of beauty, color, etc

I have a problem when use shareGPT4V to process multi images in the same time, such as, give the model 2 or more images, and ask it to answer questions about the images, like which one do you like better? The web demo and chat can't solve this problem, so could you provide a special scripts to do this?

Start by reading the shareGPT4V handling used by the web demo and chat for image inputs. Trace how multiple images are passed to the model, then define a script that accepts at least two images and a comparison question, with output showing the model's comparison response.

Written by the indexing model from the issue text.