Five-Panel Style Benchmark — Clock, Cards, Chess & More
A multi-subject prompt that generates five distinct images in one request, testing an AI's accuracy across clocks, hands, liquids, boards, and dice.
Create an image consisting of argpanel count: five sub-images, each with a different style: 1) An analogue clock showing argtime: 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.
About this prompt
A multi-subject prompt that generates five distinct images in one request, testing an AI's accuracy across clocks, hands, liquids, boards, and dice. Use it as a Concept Art starting point for GPT Image 2: keep the visual structure and style constraints intact, then swap in your own subject, brand, or scene.
Common directions include gptimage2api prompts, gptimage2api, and en. Treat these tags as creative cues; the prompt structure and preview image are the more useful guide.
Start by replacing panel count and time, then keep the camera, composition, and material cues in the same order. This makes the output easier to compare across variations.
How to use this prompt
- Copy the entire prompt text.
- Choose an advanced image-generation model (e.g., Sora 2, Midjourney).
- Edit variables like
panel countortimeinside the curly braces to customize. - Paste the prompt into the model's interface and generate.
- Compare the five sub-images for style accuracy and detail fidelity.
