Graphic Collage Poster — example generated with this AI prompt
aPrompt byananya Revanna
GPT Image 2

Graphic Collage Poster

A face her face, torn into three separate fragments and scattered across the canvas

The prompt
Create a graphic collage poster. Subject: a face her face, torn into three separate fragments and scattered across the canvas. Upper left: a small fragment showing one eye and brow, tinted red, tilted 30 degrees. Left of centre: a horizontal band showing both eyes only, in high-contrast black and white. Centre and lower right: the largest fragment, a three-quarter view from the brow down to the chin, red-tinted, filling the middle of the frame with dark hair strands falling across it and lips at the lower edge. Action: the fragments are static cut-outs, not a coherent face. Every visible eye stares straight out of the poster. Setting: the setting — flat black, with hard-edged red and white five-pointed stars laid over it at varying sizes and rotations, some cropped by the frame edge. Visual style: torn-paper punk collage — high-contrast halftone photography, heavy grain, scratched and scored surface, one saturated red and pure black and white only. Rough torn edges on every fragment. Composition: portrait poster format, layered flat with no depth or perspective, a large red star behind the central face fragment, a white star at the lower right, a small red star at the top right corner. Lighting: none — flat graphic tinting, no modelled light or shadow. Text inside: at the top right, the phrase "PLACEHOLDER LINE" set vertically in bold lowercase sans, repeated twice side by side, reading bottom to top, in red on black. At the lower left, a small white rounded rectangle containing a star-and-lightning mark in black, with a small copyright symbol beside it. No other text. Constraints: never assemble the fragments into one continuous face, never render photoreal or three-dimensional, never add colours beyond red, black and white, never smooth the torn edges, never remove the grain or scratches, never add a fourth face fragment, never place any real brand logo or wordmark. Output: 3:4 vertical.

More GPT Image 2 prompts

View all 81
Your own model

Your face. Every one of these prompts.

Train a personal profile once, then run any prompt in the library and get photos that stay unmistakably you.

Start generating