GPT Image Prompt
Use the provided image strictly as the identity reference: preserve her recognizable oval face, soft Korean-style features, clear skin, natural lips, calm eyes, and short airy bob haircut. Create one final photorealistic vertical image made of exactly two stacked portrait panels, like a modern Korean beauty magazine diptych. The upper and lower panels must be the same width, stacked vertically with a clean horizontal cut between them. No text, no labels, no watermark.
Shared styling across both panels: saturated crimson red studio wall, pale butter-yellow silk camisole, asymmetric pearl hair clips on one side, thin chain necklace, glossy natural makeup, a few loose strands across the cheek, pearly skin highlights, realistic skin texture, editorial flash.
Expression concept: restrained editorial laugh.
Upper panel: close shoulder-up three-quarter portrait. Sidona has a small luminous laugh, eyes slightly crescent-shaped, lips parted just enough to show warmth, cheekbones raised, still elegant and controlled rather than cute. One hand rests across the collarbone with glossy nails visible.
Lower panel: left-side profile of the same Sidona in a clear laughing pause. Her cheek is lifted, eye gently crescent-shaped, lips curved into a soft profile smile, chin relaxed, as if she just laughed under her breath. Keep the side profile refined and magazine-like, with the pearl clips sharply visible.
Lighting and filter: soft editorial flash, creamy skin highlights, gentle red-wall shadow, warm pastel crimson grade, Fujifilm Pro 400H inspired softness with a touch more saturation, natural pores, mild bloom on pearls. Camera: 85-90mm portrait lens, shallow depth of field, vertical 9:16 diptych composition. Avoid neutral blank profile, childish grin, extra people, distorted hands, plastic skin.
How to use: Copy and paste this prompt into ChatGPT, Gemini, Nano Banana, or your favorite AI image tool. If it mentions LoRA, reference image, uploaded photo, or identity reference, upload your own photo first. No reference photo? Replace the character with a clear age, gender, and nationality, such as “25-year-old Japanese woman” or “30-year-old American man”.
Nanobanana Prompt
How to use: Copy and paste this prompt into ChatGPT, Gemini, Nano Banana, or your favorite AI image tool. If it mentions LoRA, reference image, uploaded photo, or identity reference, upload your own photo first. No reference photo? Replace the character with a clear age, gender, and nationality, such as “25-year-old Japanese woman” or “30-year-old American man”.