Use the exact same face from the reference

Ozair AI

Prompt

Use the exact same face from the reference image and generate a 4-grid casual portrait collage — the energy of real candid moments captured in a single room, film grain aesthetic, completely unforced and human. Same simple setting across all four frames — a warm neutral textured wall in the background, a grid of small polaroid photos pinned casually to the wall behind her, soft warm practical room lighting, the same black oversized crew neck t-shirt throughout. Everything consistent, everything real. Each grid a completely different expression and pose — all natural, none performed: **Top left** — big genuine open smile, full teeth, eyes completely alive and crinkled, head slightly forward, pure unfiltered joy radiating. The smile that happens when someone says something actually funny. **Top right** — one hand raised loosely near the chin or cheek, body at a subtle angle, expression soft and thoughtful, lips slightly parted, eyes holding a quiet calm intensity. Contemplative and effortlessly beautiful. **Bottom left** — pure side profile, face turned completely away from camera, just the profile of the nose lips and jaw visible, hair falling naturally, expression neutral and clean. The frame that works because of what it hides. **Bottom right** — both hands raised in a casual playful shrug, a scrunched nose smile, eyes half closed in laughter, the most unguarded and silly expression of the four — completely human and lovable. Film grain heavy and analog throughout all four frames — warm tones, slightly underexposed feel, the specific look of a 35mm point and shoot camera. Consistent lighting and color across all four. Polaroid grid on the wall visible and slightly out of focus in each frame. Natural hair loose and real in every shot. Color grading warm and vintage — muted tones, lifted shadows, the exact aesthetic of the reference. "OzairAI" subtly in the lower-right corner of the full grid. Square 1:1 overall grid format. Ultra photorealistic, 8K — four moments, one person, infinite personality.

2.5K views · 2,032 characters

How to use this prompt

Copy the full prompt with the Copy Prompt button.
Open Nano Banana 2 in Gemini or Google AI Studio and paste it — attach your own photo as a reference to apply the style to it.
Generate, then tweak one detail at a time (subject, colors, framing) to remix the result.

FAQ

Where do I run this Nano Banana 2 prompt?: Use the Gemini app or Google AI Studio and choose image generation, then paste the prompt. Nano Banana 2 is Google's Gemini image model and is especially good at editing an existing photo from a single instruction.
Can I use my own photo with Nano Banana 2?: Yes — that's its strength. Upload your photo as a reference in Gemini, paste the prompt, and Nano Banana 2 transfers the style while keeping your subject recognizable. Most Nano Banana 2 prompts are written for this photo-edit workflow.
Is Nano Banana 2 free?: The Gemini app and Google AI Studio may offer access with usage limits. PicGens lets you copy the displayed prompt for reference, but public availability does not establish a licence; check the source and current platform terms.

More like this

@meng_dagg695

@kingofdairyque

@ProperPrompter

@TechieBySA

View on X

Prompt details from the source text

These notes expose only instructions that are observable in the shared prompt or source metadata. A field is marked as not specified when the source does not state it; no output has been inferred or rewritten.

Use and setup

Use case: Recorded category: Portraits.
Reference image: Reference-image instruction found: reference image and generate a 4-grid casual portrait collage — the energy of real candid moments captured in a single room, film grain aesthetic, completely unforced and human.
Output ratio or size: Explicit size/aspect signal: 1:1.
Variables or slots: No reusable variable or slot is stated.

Prompt breakdown

Subject: Not specified in the source prompt.
Composition: Not specified in the source prompt.
Camera: Not specified in the source prompt.
Lighting: Not specified in the source prompt.
Material: Not specified in the source prompt.
Text or typography: Not specified in the source prompt.
Negative requirements: Not specified in the source prompt.

Recorded model:Nano Banana 2(source metadata; verify fit in your own workflow)

Use the exact same face from the reference | Nano Banana 2 Prompt

Prompt details from the source text

Use and setup

Prompt breakdown