mini me with a full-size self — AI photo prompt example
Mini MeWorks withGeminiChatGPT

Mini Me with a Full-Size Self AI Prompt

Upload one clear selfie first — this prompt keeps your own face.

PROMPT

Create an ultra-realistic 4:5 portrait of the person in the uploaded photo, preserving their exact facial features, skin tone and hairstyle. Create a two-person scale illusion: the full-size person holds a miniature figurine of themself, roughly 3cm tall, in their palm. Their faces remain recognizable, with hair and clothing details; the person looks toward the tiny figure. Shot on an 85mm lens at f/3.2, waist-up composition in daylight with the palm and figurine resolved. Natural skin texture, visible pores, film-like tones, no plastic smoothing, no text, no logos, no watermark.

Copied it but the result was off? Tell us which prompt and what went wrong.

How to use it

Copy the prompt above, upload one clear front-facing selfie, and paste both into Gemini or ChatGPT.

Works with

GeminiChatGPT
Back to all prompts

NOTES ON THIS PROMPT

The two-scale self portrait shows one full-size person holding a 3cm duplicate, making the size contrast unmistakable while asking the model to preserve the same identity twice.

Why this prompt works

Light
Soft daylight needs to reach the large face, palm and tiny figure from one direction. That shared source keeps both versions in the same room and produces a small contact shadow under the miniature's feet, the most important evidence that the duplicate actually stands on skin.
Lens
An '85mm lens at f/3.2' flatters the full-size portrait while leaving enough depth for the forward palm. Waist-up framing gives the arm a natural route into the image; a macro lens would isolate the miniature and lose the essential larger person behind it.
Style
This is a practical scale illusion rather than a collage. Matching hair and clothing identifies the 3cm miniature figurine as the same person, while differences in pore size, fabric weave and depth of field establish which body is full-sized and which is tiny.

Four one-line variations

Change one of these at a time. If you change several, you will not know which one moved the result.

Hair colour
Apply 'the same soft auburn tint to both matching hairstyles' and explicitly preserve the uploaded cut on the large person and miniature duplicate.
Background
Move both versions into 'a softly blurred home studio with a neutral plaster wall' while keeping the open palm centered between chest and camera.
Lens
Try '70mm lens at f/4, slightly wider half-body framing' when more arm context is needed without shrinking the 3cm figurine too far.
Light
Replace plain daylight with 'large softbox from camera left and a faint warm rim behind both figures' for a controlled editorial version.

When the result goes wrong

Face warped
If the two faces drift apart, add 'both faces are the exact same uploaded identity, matching eye shape, nose, mouth, skin tone and hairstyle'. Repeat it before the camera line so likeness outranks styling.
Plastic skin
For a glossy miniature, add 'both versions have natural skin pores and real fabric; the small body is living, not molded plastic'. The size difference must come from measurement and perspective rather than material.
Broken hands
When the supporting hand breaks, specify 'one open palm with five distinct relaxed fingers, correct thumb placement, miniature feet centered away from finger joints'. A flat central standing area reduces overlap and duplicated digits.

How it compares to Mini Me Held in a Palm

The held-in-palm prompt concentrates on a tiny person and a hand, often leaving the owner of that hand outside the frame. This version explicitly shows the full-size identity behind their matching miniature, making it the stronger choice for a playful double-self portrait.

See the other prompt

More prompts you might like

mini me desktop figurine — AI photo prompt example
Mini MeWorks withGeminiChatGPTDreamina

Mini Me Desktop Figurine AI Prompt

PROMPT

Create an ultra-realistic 4:5 portrait of the person in the uploaded photo, preserving their exact facial features, skin tone and hairstyle. Reimagine them as a polished 3D miniature figurine standing on a walnut desk beside a keyboard, sketchbook and tiny plant, wearing their original outfit under warm window light. Shot like premium product photography on a 70mm macro lens at f/4, eye-level close composition with convincing scale and soft background blur. Natural skin texture, visible pores, film-like tones, no plastic smoothing, no text, no logos, no watermark.

mini me in a miniature city street — AI photo prompt example
Mini MeWorks withGeminiDreaminaCapCut

Mini Me in a Miniature City Street AI Prompt

PROMPT

Create an ultra-realistic 4:5 portrait of the person in the uploaded photo, preserving their exact facial features, skin tone and hairstyle. Place them as a small 3D character walking through a handcrafted miniature city street, wearing modern streetwear among tiny storefronts, parked bicycles and glowing windows at blue hour. Shot on a 50mm tilt-shift lens at f/5.6, low eye-level composition with leading lines, practical lights and model-scale depth. Natural skin texture, visible pores, film-like tones, no plastic smoothing, no text, no logos, no watermark.