Image prompt
A complex multi-part prompt used to benchmark AI performance across five different styles and subjects, including clocks, humans, liquids, and games.
Copy directly into the target model and adjust for your input assets.
Create an image consisting of {argument name="panel count" default="five"} sub-images, each with a different style: 1) An analogue clock showing {argument name="time" default="7:42"}. 2) A woman holding cards in her hands. 3) A glass of wine filled to the brim. 4) Real photography of a physical chessboard, fully visible, with all the pieces in their standard starting positions. 5) Two dice, with the numbers clearly visible.
Original source details are kept for attribution and review.
GitHub source：YouMind-OpenLab/gpt-image-2-prompts-search
This page is adapted from YouMind OpenLab GitHub prompt libraries. License: MIT。