
Create an ultra-realistic, high-quality 9:16 vertical portrait of the same young woman from the reference image. Preserve her original facial features, face shape, skin tone, eye shape, eyebrows, and overall identity as accurately as possible. She is looking directly at the camera with a calm, gentle expression and her lips completely closed, with absolutely no teeth visible. Her long, thick, glossy dark-brown hair is styled in an elegant half-up braided hairstyle, with two beautiful braids running along both sides of her head and secured with delicate ivory-white ribbon bows. Soft, wispy face-framing strands fall naturally around her cheeks, while the remaining hair flows down over both shoulders in voluminous, silky waves. She wears delicate white floral earrings, a fine silver necklace with a small flower pendant, and an elegant ivory-white dress with a square neckline, textured fabric, and beautiful puff sleeves. Her makeup is soft and feminine, featuring naturally rosy cheeks, subtle eyeliner, long eyelashes, and glossy pink lips that remain fully closed. The background is a cozy, minimalist bedroom with neutral beige walls, a neatly arranged bed with white bedding, small photographs on the wall, trailing green ivy, and subtle decorative items. Use soft natural window lighting, realistic skin texture, detailed individual hair strands, balanced colors, gentle shadows, and professional portrait photography. Composition: centered upper-body portrait, straight-on camera angle, both eyes looking directly at the viewer, symmetrical framing, natural proportions, and a clean, elegant aesthetic. Important: Keep the same recognizable face as the reference image. The mouth must be completely closed, the lips gently touching, and no teeth visible. No sunglasses, no open mouth, no exaggerated smile, no facial distortion, no extra fingers, no artificial plastic skin, no text, no watermark. Vertical aspect ratio 9:16, photorealistic, highly detailed, 4K quality.
This image was generated with GPT Image 2 by OpenAI. The prompt on this page is the exact text used to create it.
The example was generated with GPT Image 2 using: 899:1600 · 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.