Use the first uploaded image as the ONLY and PRIMARY reference for the main human subject. Preserve the person’s facial identity with high accuracy including facial structure, jawline, eye spacing, nose shape, lip shape, skin tone, hairstyle, and overall likeness. The person must remain clearly recognizable as the same individual.
Use the second uploaded image as the companion subject in the scene. Recreate the subject from the second image realistically with natural biological details such as real skin texture, natural hair strands, realistic eyes, and lifelike body proportions. The second subject must NOT appear like a toy, plastic figure, cartoon mascot, or stylized character.
Create a photobox-style environment similar to a small photo booth room where the walls and floor share the same single color.
ROOM DESIGN
The scene takes place inside a compact photobox room with three walls and the floor visible.
All surfaces (walls and floor) share the same solid color.
The color of the room should be randomly selected such as:
orange, pink, mint green, sky blue, yellow, purple, red, teal, or pastel tones.
The space should feel like a modern photobooth studio.
POSE RULES
Main subject:
The person faces the camera and always performs a peace sign gesture while smiling naturally.
Second subject:
The AI should analyze the second subject and select a suitable pose.
If the second subject appears feminine or cute:
– affectionate or playful pose
– hugging, leaning close, holding the arm, or cute interaction
If the second subject does not appear feminine or cute:
– relaxed natural pose beside the main subject
INTERACTION
Both subjects should feel like friends taking a fun photobox picture.
LIGHTING
photobox studio lighting
soft front lighting
even illumination
soft shadows
CAMERA
slightly wide photobox lens
top slightly angled camera like photobooth perspective
COMPOSITION
both subjects centered
natural scale between subjects
full body or half body visible
STYLE
realistic photobox photography
natural textures
high detail skin and hair
Ultra high detail, crisp focus, vibrant colors, realistic materials, professional photobox aesthetic, no watermark, no text, 9:16 vertical composition.