
Hyper-realistic IMAX-level Netflix-style cinematic black-and-white studio portrait, 9:16 vertical. Use the uploaded image as the primary visual reference and preserve the exact facial identity, proportions, and defining features. Create a woman wearing a fitted white sleeveless ribbed tank top and medium-wash straight-leg jeans; she is sitting sideways on a round wooden stool with her body curled inward, both knees drawn up close toward her chest, one knee raised prominently in front of her while the other leg folds beneath it, both arms wrapping naturally around her raised legs with her hands gently clasped together around the lower leg and ankle, one bare foot hanging downward near the stool while the other leg remains folded, and her upper body leaning softly toward the raised knee; her head rests sideways against the top of her raised knee, cheek gently touching the denim, face turned toward the camera, eyes looking directly at the viewer with a soft thoughtful gaze, relaxed eyebrows, naturally closed lips and a quiet reflective expression; long dark brown hair with a deep side part, swept back from the forehead and falling loosely behind her head and over the right side of the stool in soft natural waves; fair luminous skin rendered with realistic natural texture and smooth tonal detail; a simple seamless light-gray studio background with a subtle darker gradient near the floor, keeping the stool and subject clearly separated; large soft diffused studio light from the upper left creates gentle illumination across her face, shoulder and arms with smooth shadows beneath the chin, hair and folded legs; refined monochrome colour grading with rich charcoal blacks, clean soft whites, detailed mid-gray tones, gentle contrast, slightly lifted shadows, smooth highlight roll-off, subtle film grain and a classic fine-art black-and-white photographic finish. Negative prompt: altered pose, head not resting on knee, legs straight, hands separated, changed identity, distorted face, distorted anatomy, deformed hands or feets, bad anatomy, extra limbs, text, watermark.
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: 941:1672 · Cinematic · Black & White · 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.