Identity-Locked Portrait From Uploaded Reference Photo

@AIwithkhan·May 12, 2026·83

Use the uploaded reference image as the strongest identity anchor.

Prompt

Use the uploaded reference image as the strongest identity anchor. The woman must look like the exact same adult woman from the reference image, not a similar person. Preserve her exact facial identity with high priority: same soft oval face, same delicate jawline, same large expressive eyes, same eyelid shape, same glossy natural lips, same small refined nose, same pale smooth skin, and the same long dark wavy hair with soft layered framing around the face. Keep her appearance natural and realistic like a real Korean baseball broadcast capture. Create an ultra-realistic candid KBO baseball broadcast video scene during a lively night game. She is seated in the crowd beside her boyfriend, both wearing matching red-and-white baseball jerseys surrounded by energetic cheering fans. She casually watches the game while softly smiling and laughing with him in a completely natural way. No dialogue, no posing, no cinematic acting. The moment should feel accidental and authentic, like a real live TV broadcast camera briefly focusing on them. She lightly holds yellow cheering sticks and taps them together while reacting to the game. The boyfriend leans in naturally and they share a very short soft kiss lasting about one second, subtle and spontaneous, not overly romantic or dramatic. Immediately after the kiss, she notices the live stadium camera showing them on the giant screen. She becomes shy and slightly embarrassed for a brief moment, then gives a soft cute smile toward the camera while trying not to laugh. Her expression should feel genuine, candid, and unscripted, like a real fan unexpectedly caught on live television. Use realistic Korean baseball TV broadcast cinematography: long telephoto lens compression, slight handheld camera shake, subtle motion blur from cheering fans, realistic stadium lighting, shallow depth of field, authentic skin texture, soft live-broadcast sharpness, imperfect framing, natural crowd movement, true sports broadcast atmosphere, and realistic 16:9 live game composition.

Try this Prompt

Photo Typography Cinematic Hero Portrait Fashion Look Group Scene Low Key Social Media Post Marketing Campaign

How to Use This Prompt

Copy the full prompt text with the copy button above.
Replace any [bracketed] placeholders with your own subject, scene, or details.
Paste it into Gemini / Nano Banana Pro — or hit "Try this Prompt" above to generate here for free — then tweak the wording against the example images.

Style Notes

Photo: Asks the model for photorealistic output — natural lighting, believable skin and materials, camera-like depth of field — rather than illustration or 3D looks.
Typography: Text is part of the artwork. Modern models like Nano Banana Pro can render legible styled lettering, but keep the exact wording short and quoted in the prompt.
Cinematic: Film-style rendering — widescreen framing, dramatic lighting contrast, graded colors (often teal-orange), and a sense of narrative in the scene.
Hero Portrait: A single dominant subject shot like a key visual — tight framing, strong eye contact or pose, background simplified so the character carries the image.
Fashion Look: Editorial fashion styling: garment detail and fabric texture take priority, with model poses and lighting borrowed from magazine shoots.
Group Scene: Multiple characters in one frame — the hardest case for AI consistency; prompts usually assign each figure a position and role explicitly.
Low Key: Predominantly dark frame with selective highlights — moody, dramatic, and very sensitive to where the light source is placed in the prompt.
Social Media Post: Composition and aspect ratio tuned for feeds (Instagram, X, Xiaohongshu): bold focal subject, room for overlay text, colors that survive small screens.
Marketing Campaign: Ad-ready imagery: clear product or message hierarchy, space reserved for copy and logos, and a polished commercial finish.

FAQ

How do I use this prompt with Gemini (Nano Banana Pro)?

Copy the full prompt with the copy button above, paste it into Gemini or any Nano Banana Pro-powered tool, and compare your result with the example images on this page. You can also click "Try this Prompt" to generate directly on this site — free daily generations, no sign-up needed.

Can I customize "Identity-Locked Portrait From Uploaded Reference Photo"?

Yes. Anything in [brackets] is a placeholder meant to be replaced with your own subject or details, and you can freely adjust subject, lighting, or style keywords — small wording changes often produce noticeably different results.

Which AI models does this prompt work with?

It was originally shared for Google's Gemini image models (including Nano Banana Pro). Most text-to-image models will understand it too, though composition and text rendering quality vary by model.