Prompts
EN

Image prompt Posters & Typography Customizable

Four-Poster Fashion Editorial Series From a Portrait

A set of four vertical posters built from one uploaded portrait, each with a different typographic layout while the palette, type family and photographic look stay consistent. The result reads as a single editorial campaign.

Shared byLarus Canus Original post
Model
GPT Image 2
Type
4 images
Aspect ratio
9:16
Shared
21 Sep 2026
Likes on X
87
Make it yoursSwap in your own details: 2 blanks to fill

Use uploaded portraitMint green / red / blue / yellow / custom

Image prompt

2,263 characters

Create four independent portrait poster variations from the uploaded photo, all belonging to the same visual system. Portrait: [use uploaded portrait] Main color: [mint green / red / blue / yellow / custom] Typography theme: [SIGNAL / MOTION / ECHO / MINT, or custom words] Aspect ratio: 9:16 Keep the same person, facial identity, hairstyle, outfit, photographic realism, color palette, typography family, and editorial art direction across all four posters. The four posters must feel like one cohesive fashion editorial series, but each must use a clearly different layout concept: 1. Vertical Type Layering Use oversized condensed typography as a strong vertical spine. Let letters move in front of and behind the portrait, creating clear depth and layered interaction. 2. Sliced Portrait Split the portrait into several clean horizontal sections and slightly offset each slice. Keep the face recognizable and beautiful. Avoid RGB glitch, noise, or digital distortion. 3. Echo Portrait Show the same subject twice using contrasting scale or orientation, such as one normal portrait and one enlarged flipped portrait. Use repeated typography or outline type to create a visual “echo.” 4. Portrait Inside Oversized Type Use huge bold typography as the main composition. Let parts of the face, eyes, lips, hair, or shoulders appear through and between the letterforms, so the portrait becomes integrated into the typography. Use a modern fashion-editorial aesthetic with oversized condensed sans-serif type, strong portrait photography, clean geometric structure, generous negative space, fine rules, small meaningful editorial text, and subtle graphic blocks. Keep the information hierarchy clear: large typography first, portrait second, small editorial text third. Use meaningful supporting copy related to the visual concept rather than random placeholder text. Keep skin realistic with natural texture, realistic hair strands, natural fabric folds, and photographic lighting. Avoid plastic skin, CGI appearance, excessive retouching, random symbols, meaningless text, heavy UI graphics, sparkles, numbering, NO., VOL., and decorative clutter. Generate all four as separate standalone 9:16 posters, not combined into a single collage.

How to use it

Upload a clear portrait first, since the whole series is built around that photo. Keep the palette, typography family and editorial direction lines intact so the four posters still read as one set, and swap only the main colour and the theme words to make it yours. It was shared as a GPT Image 2 prompt, and the four posters are meant to be generated as separate standalone 9:16 images for a lookbook or social carousel.

#Poster#Editorial#Portrait#Fashion#Text in Image#Magazine Cover

Featured inFashion editorial AI prompts

Shared publicly on X on 21 Sep 2026. All credit for this prompt and its result goes to its creator. Is this yours? Ask for an update or removal.

2,263 characters

Questions about this prompt

Which AI model was this prompt made with?

It was shared as a GPT Image 2 prompt, and the image on this page is the result the creator got with it. Other models can read the same text, but the result will look different.

Can I change the details in this prompt?

Yes. It has 2 parts you can swap: use uploaded portrait, mint green / red / blue / yellow / custom. Open the prompt studio, fill them in and copy your version; anything you leave empty keeps the original wording.

Who made this prompt?

It was shared publicly on X by @MrLarus on 21 Sep 2026. The prompt and its result belong to them, and this page links to the original post.

More from @MrLarus