
Create a high-quality, photorealistic 3×3 fashion editorial photoshoot collage featuring the person from the reference image. Preserve the person's exact facial identity, facial structure, skin tone, hairstyle, and recognizable features across all nine panels. Outfit & Styling: The subject wears an oversized plain white T-shirt dress and a red vintage polka-dot headscarf tied neatly under the chin. Natural, slightly messy hair frames the face. Minimal makeup with soft rosy cheeks and natural lips. Props & Setting: A bright red folding metal chair and a classic red Coca-Cola can. Clean, seamless light grey studio background with soft, diffused professional lighting. Nine Different Poses: 1. Side-facing seated pose, looking over the shoulder while holding the Coca-Cola can. 2. Front-facing portrait, hands relaxed, with a Coca-Cola can close to the camera in the foreground. 3. Relaxed side pose, leaning against the red chair with the can beside the body. 4. Extending the Coca-Cola can toward the camera. 5. Close-up portrait, playfully winking while holding the can near the cheek. 6. Smiling gently while holding the can near the face. 7. Sitting with knees pulled up, holding the can with both hands. 8. Tilting the head back slightly while raising the can beside the face. 9. Relaxed seated pose, holding the can in one hand and looking directly at the camera. Photography Style: Professional Korean fashion editorial photography, natural candid expressions, realistic skin texture, detailed fabric textures, soft shadows, balanced composition, 85mm portrait lens, premium commercial studio photography. Composition: A perfectly aligned 3×3 contact sheet collage with nine equally sized rectangular photographs, separated by thin white borders. Maintain consistent facial identity, outfit, accessories, chair, lighting, and background throughout all nine panels. Ultra-realistic, high resolution, 4K quality, vertical 3:4 composition.
This image was generated with GPT Image 2.5 by OpenAI. The prompt on this page is the exact text used to create it.
The example was generated with GPT Image 2.5 using: 3:4 · Fashion · Realistic · Portrait. Reusing these settings gives the closest match.
Copy the prompt as-is first, then replace only the subject while keeping the style, lighting, and composition keywords. Generate a few variations — outputs differ between runs.
Yes. Prompts work best as starting points — adjust descriptors, aspect ratio, or style tags to make the output your own.