Text to Image
Mini-Me Character Composite Image — AI Image Prompt
A complex prompt for creating a composite image with 3D chibi characters interacting with a real person isolated from a photo. - AIPinMaker

Prompt
Based on this image, centering on the person in the photo, please generate an "emotional composite image where mini-me characters come alive and move around." [Core Concept] "My little alter-egos in my daily life" Cute, playful, yet aesthetic direction Instagram aesthetic + an image with a story [1. Person Processing - Crucial] The original person must be cut out/isolated from the background (Absolutely no changes to the face or pose allowed).
Place the person in the center or slightly towards the front of the scene. Add natural shadows. Add a thin white border around the person's outline (like a sticker, but not too thick). [2. Mini-Me Character Generation - Core] Generate multiple "mini-me characters" based on the person. Style: {argument name="style" default="3D cute SD (Super Deformed/Chibi) characters (Roblox or pixel styles are acceptable)"}. Must reflect the exact facial features, hairstyle, and clothing of the person. [Mini-Me Characteristics]
Small size (palm-sized feel). Multiple characters appearing ({argument name="count" default="around 3 to 7 characters"}). [3. Mini-Me Actions - Crucial] Each character must be actively doing something. Examples: {argument name="actions" default="Jumping and playing Waving hands Mimicking the person Sitting on an object Climbing on the person's shoulder or head Looking like they are talking to each other"} 👉 "Static/frozen characters are strictly prohibited" [4. Placement & Direction]
Place them naturally on top of books / bags / shoulders / the floor / hands, etc. Place some in front of the person and some behind → to create a sense of depth and space. Add shadows as if they actually exist in the physical space. [5. Title Generation - Core Feature] Analyze the mood of the image and automatically generate a short, aesthetic text title. [Title Rules] 2 to 5 words long. Do not explain; just convey the "vibe." Avoid overly trendy internet slang. Natural and aesthetic tone.
[Example Vibes/Titles] Today's moment Just a good day Little joys of the day My own timing Small happiness Recording this moment Just found it funny 👉 Must "generate a new title that fits the mood of the image" [6. Title Placement] Place some text behind the person. Place some text in front. 👉 Create a three-dimensional layered composition. Do not make the text too large (maintain the aesthetic vibe). Use a soft font style. [7. Doodles & Sticker Elements]
Add handwritten-style doodles (thin pen feel). Examples: Arrows → Circles for emphasis Stars ✨ Hearts ♡ Dotted lines 👉 Only add 3 to 6 elements (do not overdo it) [8. Auxiliary Text (Optional)] Small sticker-like text. Examples: mini me today mood lol daily [9. Overall Style] Bright and warm tones. Maintain natural colors. Avoid looking too much like CG (computer graphics). Aim for a "real photo + cute composite" feel. [10. Prohibitions] No changing the person's face.
No characters looking out of place or disconnected from the scene. No game UI styles. No excessive filters or effects. No card-news (infographic) style text blocks.10:["$","main",null,Prompt breakdown
- Subject
- Isolated central person from the source photo with exact face, hairstyle, clothing and pose preserved, plus multiple mini-me duplicates
- Style
- 3D cute SD chibi characters blended into real-photo composite, thin white sticker border around the main figure, Instagram aesthetic
- Lighting
- Bright warm natural tones with added physical shadows grounding the mini characters in the scene
- Composition
- Depth via characters placed in front of and behind the person, layered text in front and behind, 3-6 handwritten doodles like arrows or hearts
- Mood
- Cute playful narrative of daily little joys through active alter-egos
Remix ideas
- Change actions so two mini-mes climb the person's head while one sits on a foreground book for stronger depth
- Generate the title 'Small happiness' and offset it partially behind the isolated figure using a soft font
- Add exactly four doodles: two stars near waving mini-mes and two dotted lines linking characters on the shoulder
Reference images

How to use this AI Image prompt template
1
Copy the prompt — grab this template’s prompt and negative prompt. 2
Pick a model — choose a recommended AI model for the best match. 3
Generate — open the studio with one click and create your result.
Related templates

Isometric figurine generation prompt for Nano Banana Pro
Create a creative image of Isometric Figurine Generation Prompt For Nano Banana Pro. Style: photorealistic. Composition: balanced and well-framed. Lighting: natural with cinematic mood. Category: photography. Reference: isometric-figurine-generation-prompt-for-nano-banana-pro-5874.

Isometric Figurine from Selfie Prompt Template
Create a portrait image of Isometric Figurine From Selfie Prompt Template. Style: photorealistic. Composition: balanced and well-framed. Lighting: natural with cinematic mood. Category: portrait. Reference: isometric-figurine-from-selfie-prompt-template-5399.

Selfie to Miniature Isometric Figurine Prompt (Simplified)
Create a portrait image of Selfie To Miniature Isometric Figurine Prompt Simplified. Style: photorealistic. Composition: balanced and well-framed. Lighting: natural with cinematic mood. Category: portrait. Reference: selfie-to-miniature-isometric-figurine-prompt-simplified-5688.

3D City Food Stand Grid
Goal: Create a vibrant 2x2 poster grid of four miniature 3D city street-food stands, each shown as an isometric diorama on a small rounded sidewalk base, with bold city-and-food titles above each scene. The image should feel like collectible toy miniatures rendered in polished clay/plastic 3D, highly detailed, cheerful, and social-media friendly. Canvas: Square 1:1 composition divided into exactly 4 equal quadrants by thick black cross-shaped dividers. Each quadrant has a solid bright background color and one centered food-stand diorama with a large playful title at the top. Layout and sections: Use exactly 4 food stands: 1. Top-left: Tokyo Ramen Stand (Tokyo stand title). Red background. A compact Japanese ramen shop with red lanterns, Japanese signage, a glowing red ramen sign, wooden storefront, noren curtains, stools with customers eating at the counter, small crates, a bicycle, cherry blossom accents, and a tiny ramen bowl icon under the title. 2. Top-right: Mexico Taco Stand (Mexico stand title). Green background. A Mexican taco stall with terracotta roof tiles, a large sign reading “TACOS,” green-and-white striped awning, customers on stools, taco ingredients at the counter, cactus plants, a red pickup truck parked beside it, streetlamp, menu boards, and a small taco icon under the title. 3. Bottom-left: NYC Hot Dog Cart (NYC stand title). Yellow background. A New York hot dog cart with metal cart body, blue-and-yellow umbrella, illuminated “HOT DOG” sign, condiment bottles, pretzels or buns, one customer standing in front, subway entrance railing, trash can, street pole with signs, pedestrian signal, and a small hot dog icon under the title. 4. Bottom-right: Paris Crêpe Kiosk (Paris stand title). Sky-blue background. A Paris crêpe kiosk with dark green vintage booth, striped awning, sign reading “PARIS CRÊPES,” customers gathered around the counter, chalkboard menus, ornate streetlamp, flowers, a leafy tree, bicycle, wicker basket, bollards, and a small crêpe icon under the title. Visual style: Cute isometric 3D render, miniature diorama / toy model aesthetic, high detail, soft ambient occlusion, warm tiny lights, crisp shadows, saturated colors, rounded edges, realistic but stylized materials, thick playful white or black display lettering depending on contrast, slightly puffy retro typography. Text content: Titles must be large, legible, and centered near the top of each quadrant. Keep the main shop signs readable where possible: “TACOS,” “HOT DOG,” and “PARIS CRÊPES.” Japanese shop signs can use authentic-looking Japanese characters. Avoid adding extra captions outside the four titles and shop signage. Constraints: Exactly 4 quadrants and exactly 4 diorama food stands. Keep each stand fully visible within its quadrant, with no overlap across the black dividers. No watermark, no logo, no photorealistic humans, no extra panels.36:Tbd2,Goal: Create a vibran

Isometric 3D Miniature Room with Chibi Character Prompt - Nano Banana Pro AI Prompt for Profile / Avatar
An isometric 3D cube-shaped miniature room (shallow cutaway true cube; everything strictly contained within the cube). The room is [Describe the theme, furniture, specific clutter, wall decorations, and key items in detail] (room description). Character: a chibi/figurine-style — [INSERT DESCRIPTION OF THE PERSON FROM YOUR UPLOADED PHOTO HERE] (character description). The character is [ACTION: e.g., sitting on a chair typing, standing and cooking, playing guitar] (action), with a [EXPRESSION: e.g., focused, happy, smiling] (expression) expression. Figure material looks like matte PVC, with big head / small body proportions. Lighting: [ATMOSPHERE NAME] (atmosphere name): [LIGHT SOURCES: e.g., neon blue glow, warm sunlight, golden lamp light] (light sources); realistic reflections and colored shadows. Camera: slightly elevated isometric three-quarter view, front cube edge centered; no elements protruding outside the cube. Photoreal materials with fine detail; neutral backdrop. Ultra-detailed, clean composition; no watermark.3f

3D Miniature Instagram Diorama
Create a creative image of 3d Miniature Instagram Diorama. Style: photorealistic. Composition: balanced and well-framed. Lighting: natural with cinematic mood. Category: photography. Reference: 3d-miniature-instagram-diorama-20760.
Explore more prompts
Browse more AI image and video prompts by category.
FAQ
- Why must the main person's face and pose stay untouched?
- The prompt isolates only the background so the mini-me characters can interact naturally around the unaltered central figure without breaking realism.
- How many mini-me characters should appear by default?
- The prompt suggests 3 to 7 so the scene feels lively yet uncluttered while allowing varied actions like mimicking or shoulder climbing.