when I input a image url and told GPT-4 to describe it, GPT-4 said:
I’m sorry, but I cannot view or process images as I am a text-based AI model. If you could describe the image to me or provide some context, I’d be happy to help you with any questions or information you need.
Why and how can I fix it to make it work?
GPT is a language model. It can only work with text, it cannot see anything.