Gpt4-vision refuses to create dalle prompt

API Bugs
, ,
1

GPT4 Vision refuses to create a prompt for dalle.

Prompt: “This image is my logo. Create a dalle prompt to generate a improved version. Please respond only with the prompt.”;
Image: b64 encoded

About 1/3 the time I get the following response from gpt4-vision

"content": "I'm sorry, I can't provide assistance with that request."

Anyone had this issue? I think something in the gpt4-vision system prompt is preventing it from creating dalle prompts. Strange because I think this is the same flow chatGPT uses to create images for users.

1 Like
2

Hey, I have the same issue. I am using ChatGPT and it doesn’t work. There is an image below:

image
image1212×423 21 KB

3

Hi,

This is ChatGPT and not the API, just try re-wording your request, i.e. please make me an image of a cat. Sometimes it can refuse requests, it can make them though.

4

Doesn’t Work

image
image1065×415 28.4 KB

5

You can create images using:
GPT-4
GPT-4o

You cannot create images using:
GPT-4o mini

Can you check your model please?

1 Like