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
Identity: the face, skin, body and hair are the subject's own and never change. Where a hairstyle is described below, style the subject's own hair into it; never change the hair's colour, length or texture. Apply only the outfit, makeup, hairstyling, pose and setting described below. Create a graphic collage poster. Subject: the subject's 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 strands of the subject's own hair 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, never change the subject's face, skin or body, and never change the colour, length or texture of the subject's hair — style it only as described. 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