Skip to content
Back to Prompts

The Reference Person. Create A Stylish Fashion Transformation Where The

@AIwithkhan··69

Use the uploaded image as the reference person. Create a stylish fashion transformation where the original person appears alongside a cute mini version of themselves. Maintain facial identity, hairstyle, skin tone, an...

The Reference Person. Create A Stylish Fashion Transformation Where The — image 1
Prompt
Use the uploaded image as the reference person. Create a stylish fashion transformation where the original person appears alongside a cute mini version of themselves. Maintain facial identity, hairstyle, skin tone, and key facial features accurately. Both characters wear matching outfits: oversized chocolate-brown t-shirts, cream wide-leg trousers, beige-and-white sneakers, matching beige baseball caps, black sunglasses, gold accessories, and coordinated brown shoulder bags. The adult version holds a bouquet of fresh white flowers while standing confidently. The mini version stands beside them with the same outfit, pose, accessories, and facial resemblance. Pose them on an elegant European-style city street in front of a luxury building entrance with black doors and stone architecture. Include a small reference image inset box in the top-left corner showing the original uploaded photo. Make the transformation look like a premium AI fashion edit. Ultra-realistic fashion photography, luxury street style, editorial magazine quality, full-body composition, natural daylight, highly detailed clothing textures, realistic shadows, premium color grading, matching outfits, mother-and-mini-me aesthetic, Instagram-worthy fashion campaign, 4K detail, vertical 9: 16 format.

How to Use This Prompt

  1. Copy the full prompt text with the copy button above.
  2. Replace any [bracketed] placeholders with your own subject, scene, or details.
  3. 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.
Poster
Single-image layout designed to be read at a glance: dominant visual, title-friendly composition, high contrast for print or thumbnail.
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.
Character Design
A character presented for reference: readable silhouette, costume and prop details, often multiple angles or expressions in one sheet.
Fashion Look
Editorial fashion styling: garment detail and fabric texture take priority, with model poses and lighting borrowed from magazine shoots.
Architecture
Buildings and structures with believable perspective and materials — wide lenses, strong leading lines, attention to light on facades.
Cartoon
Simplified shapes, exaggerated proportions and expressions, flat or cel-shaded color — reads instantly and stays consistent across characters.
Luxury
Premium cues: rich materials (marble, silk, brushed metal), subdued gold/black palettes, and restrained, spacious composition.

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 "The Reference Person. Create A Stylish Fashion Transformation Where The"?

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.

Related Prompts