Cinematic 3D Mini-Me Scene

GPT image 2 on chatgpt

Prompt
Create a high-quality cinematic 3D mini-me scene featuring six versions of the same person: one normal-sized version and five ultra-mini versions of herself.
Main Character
The normal-sized woman is seated or leaning naturally at a cozy wooden table in a warm indoor café/home environment. She has a soft, happy smile and looks affectionately toward the tiny version she is holding.

Give the main character a cute natural hairstyle inspired by the reference scene: short-to-medium dark hair with soft natural volume and light face-framing strands, while keeping the facial identity completely unchanged.

Dress her in a simple cozy outfit inspired by the reference image: a clean white basic T-shirt underneath a black cardigan with subtle horizontal white stripes, paired with comfortable light-colored pants. Keep the clothing modest, casual, simple, and realistic.

Mini Characters

Create five ultra-mini versions of the exact same woman with identical facial identity, hairstyle, hair color, skin tone, and matching outfit.

Make the mini characters adorable 2.5–3 heads tall, premium 3D animated characters with realistic hair, detailed clothing, expressive faces, natural anatomy, and exactly five fingers.

One mini version is being gently lifted by the main character using the thumb and index finger, holding ONLY the fabric of the mini character's clothing near the shoulder/collar area. The fingers must never grip the neck or body directly.

The lifted mini character is suspended in the air with arms and legs naturally spread out, looking surprised but cute and playful.

Position the other four mini versions around the main character:

one sitting on her shoulder

one climbing or holding onto her cardigan sleeve

one standing beside her on the table

one sitting near the front edge of the table with a cute playful pose

Make every mini character clearly recognizable as the same person as the main character.

Environment

Create a cozy warm indoor setting resembling a stylish café or comfortable home.

Use a wooden tabletop in the foreground, warm brown furniture, softly blurred background, subtle ambient lights, and a cozy evening atmosphere.

Add gentle reflections and realistic contact shadows so the miniature characters feel physically present in the scene.

Composition

Vertical 9:16 composition.

The main character should dominate the frame while all five mini versions remain clearly visible. Use strong perspective and a dramatic size contrast between the normal-sized woman and the tiny versions.

The camera should be positioned slightly above table level with a medium close-up cinematic framing.

Visual Style

Ultra-detailed cinematic 3D CGI, premium animated-film quality, realistic skin texture, highly detailed silky hair, realistic fabric fibers, physically accurate lighting, soft warm illumination, subtle depth of field, cinematic bokeh, realistic shadows, polished 3D rendering, expressive eyes, cute humorous atmosphere, high-end commercial photography quality, extremely detailed, 4K.

Identity & Accuracy

Exactly six characters total — one normal-sized woman and five miniature versions.

All six must have the same recognizable face and consistent identity.

No extra characters, no duplicate characters, no distorted faces, no face swapping, no identity drift, no deformed hands, no extra fingers, no missing fingers, no duplicate limbs, no text, no watermark.

Aspect ratio: 9:16 vertical.