AI 5 min read

Cherry 2.O viralizes a GPT Image 2 prompt for fashion editorials in continuous composition

@Mind_Boticni publishes a prompt for ChatGPT on X: six fashion moments of the same Japanese model merged into a single square image, luxury magazine style without grid or collage.

Verified Editorial standards
Fashion editorial composition: six moments of the same model with colored backgrounds and organic transitions
Result of the prompt: haute couture sequence with the same face in six different attitudes, merged without a grid. Source: @Mind_Boticni

On June 19, Cherry 2.O (@Mind_Boticni) posted on X an example generated with GPT Image 2 in ChatGPT and linked the full prompt in a thread reply. The template asks for something unusual: not six separate photos, but a single square composition where six fashion moments of the same model coexist, superimposed with smooth transitions — no grid, no white borders and no collage effect.

AI Prompt · How to do it

Editorial GPT Image 2: model with black curls in continuous multicolor composition

Example posted by Cherry 2.O on June 19, 2026. @Mind_Boticni

Steps

  1. Open chatgpt.com with image generation (GPT Image 2).
  2. Upload a reference image of the face you want to keep.
  3. Copy the prompt below; Adjust features if your model is not the one in the example (hair, beard, aesthetics).
  4. Outputs in square format; If a grid appears, repeat adding: “no grid, seamless overlap only.”

Prompt to copy

Reference image inspired. Create a continuous high-fashion editorial sequence featuring the same stylish Japanese male (Reference image) model with consistent facial identity, thick curly black hair, subtle beard, and modern luxury Tokyo aesthetics. Six independent fashion moments should exist within one square composition, but they must merge together organically like a luxury magazine spread. Images overlap naturally with soft transitions and varying sizes. Absolutely no grid, no equal spacing, no panel borders, no white dividers, no collage effect. The entire image should feel like one cinematic composition rather than six separate pictures. Every appearance must show a completely different attitude, body language, and camera perspective: • Dramatic worm's-eye view, model sitting backwards on a chair with one arm hanging casually, looking down toward the camera. • Extreme close-up shot from below with messy curls, hand partially covering lips, mysterious expression. • Dynamic walking shot captured from behind and slightly above, turning his head toward camera over the shoulder. • Wide-angle lens perspective with the camera almost touching the ground, one foot close to the lens creating strong depth and fashion energy. • Candid movement shot captured while adjusting jacket sleeves, body leaning sideways with natural motion blur. • Powerful editorial pose inspired by luxury campaigns, standing with crossed legs and one hand inside pocket, photographed with a dramatic Dutch angle. Different luxurious monochrome outfits in white, black, cream, navy blue, charcoal grey, and beige. Each appearance has a unique bold background color including crimson red, electric blue, emerald green, golden yellow, purple gradient, and burnt orange. Fashion week atmosphere, Vogue Italia editorial style, cinematic storytelling, exaggerated perspective, magazine-quality composition, ultra-realistic photography. Photographed with Fujifilm GFX100S, 35mm and 80mm lenses, f/2.0, shallow depth of field, HDR, professional color grading, masterpiece, 4k. continuous composition, overlapping images, floating editorial moments, organic arrangement, irregular sizes, seamless transitions, no grid, no collage borders, no panel lines, no frames, no white spacing, no dividers, no text, no watermark.

Text in English according to the original thread. Requires reference image. Respect image rights if you use other people's portraits. The author tags the post as “Made with AI.”

What makes this prompt special

Most fashion prompts ask for “an editorial photo” or a “4-panel collage.” Cherry 2.O insists on the opposite: continuous composition, irregular sizes, organic overlap and explicit prohibition of grids, frames and white dividers. That pushes the model towards a single magazine spread-type poster, not a contact sheet.

The block of six perspectives—extreme low angle view, close-up from below, walking seen from behind, wide angle with foot to the lens, casual gesture with motion blur and Dutch pose— forces the attitude and camera to vary in each appearance. The backgrounds (crimson red, electric blue, emerald green, etc.) and monochromatic outfits (white, black, cream, navy...) add editorial contrast without mixing too many clothes per figure.

Personalization

Change “Japanese male” and the physical description to your reference. For women or another urban style, replace “modern luxury Tokyo aesthetics” with Paris, Seoul or Mexico City. If the result still looks like a collage, reinforce at the end: single unified canvas, images bleed into each other.

Before publishing

GPT Image 2 may require payment plan depending on region. Do not use portraits of third parties without permission. Review OpenAI's policies for content generated with real faces.

Most read

What readers are engaging with right now.