
Create a realistic 2×2 photo collage featuring the same young woman in all four panels, photographed at Westminster Bridge in London, with Big Ben and the Houses of Parliament in the background. Character consistency: Maintain the exact same facial identity, facial features, freckles, short tousled light-brown hair, hairstyle, skin tone, and body proportions across all four photos. Outfit: Oversized dark chocolate-brown wool coat, cream knit sweater underneath, and small silver earrings. Panel 1, Top Left: The woman leans against the green bridge railing, resting her cheek on one hand while looking slightly away from the camera. Panel 2, Top Right: She rests her chin on her folded arms over the railing, looking directly at the camera with a subtle smile. Panel 3, Bottom Left: She sits or leans sideways against the railing, gently touching her hair while gazing into the distance. Panel 4, Bottom Right: She stands beside the railing with one hand running through her hair, looking thoughtfully to the side. Environment: Iconic Big Ben, detailed Gothic architecture of the Palace of Westminster, River Thames, green bridge railing, and naturally blurred tourists in winter clothing. Photography style: Ultra-realistic travel photography, natural facial expressions, authentic skin texture, soft winter daylight, partly cloudy blue sky, realistic colors, candid editorial photography, subtle depth of field. Layout: Perfect 2×2 square collage, four equally sized photographs, thin black dividing lines, consistent color grading and lighting. No text, no watermark, no extra panels. Aspect ratio: 1:1, high resolution, photorealistic.
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: 1:1 · Street Photography · 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.