
Hyper-realistic IMAX-level Netflix-style dramatic low-key backlit side-profile 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 dark traditional outfit with subtle embroidered trim and a delicate necklace visible along the shoulder and neckline; she stands in a pure left-facing side profile with her head slightly lowered, chin gently angled downward, neck relaxed, shoulders turned only slightly away from the camera, creating a clean silhouette from forehead to nose, lips and chin; her eyes are lowered and mostly hidden in shadow, eyebrows relaxed, lips softly closed with a calm introspective expression and no visible smile; her dark hair is styled in a loose high bun with a decorative hair clip, while wispy bangs and loose strands fall around the forehead, cheek and neck, with longer strands extending behind her shoulder; fair luminous porcelain skin with a bright ivory to light beige tone and a neutral-cool undertone, but most of the facial surface remains intentionally hidden in deep shadow; a completely black background surrounds the figure, with no visible environmental details; a strong warm golden backlight is positioned directly behind and slightly above her, tracing an intense glowing rim along the outer hair strands, forehead, nose bridge, lips, chin, neck, shoulder and clothing edge, while the front of her face remains dramatically underexposed and almost completely black, revealing only extremely subtle warm facial contours, creating a striking silhouette effect; deep cinematic colour grading built around near-black shadows, rich amber and burnt-gold highlights, very warm rim light, extremely high contrast, crushed blacks, controlled highlight roll-off, minimal ambient fill, slightly warm white balance and subtle film grain, with the golden light appearing luminous and concentrated against the pure black surroundings for a moody, mysterious fine-art cinematic finish. Negative prompt: changed identity, front-facing pose, visible bright face, flat lighting, weak backlight, washed shadows, excessive fill light, distorted profile, bad anatomy, 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 · Portrait · Dark. 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.