Hello everyone, I’ve been exploring various ways to enhance the functionality of my LLM-based systems, and I’m curious if there are any ways to incorporate images directly into system prompts. If not, why? And will it be possible in the future?

Hello! The linked vision guide just given does not provide any indication about which roles support images for vision. Currently, only gpt-4-turbo-2024-04-09 allows an image to be placed in a “system” role message (and not its substitute, “developer”). It does not perform well, as the “system” role…

Is there any way to utilise images in system prompt?

API

yangzhi.see March 5, 2025, 11:58am 4

Thanks! Do you mind expanding more on why is it “purposefully disallowed in all AI models since”?

Topic		Replies	Views
Allowing Images in Non-User Messages Feedback api	14	1274	May 28, 2025
Gpt-4o Regression, doesn't support images in System and Function messages Feedback gpt-4	5	1365	September 22, 2024
Gpt-4-1106-vision-preview system message possible? API	2	2008	November 30, 2023
Returning image as result of function call to gpt-4-turbo Bugs	11	4825	November 4, 2024
Question on Finetuning: Can you hardcode images or upload image responses via the image_url subkey of content? API	3	211	August 27, 2024

Is there any way to utilise images in system prompt?

Related topics