Examples for using nano-banana-2 through RunAPI from agent tools or API calls. Copy a prompt, then use it in Claude Code, Codex, Cursor, Windsurf, or your backend.
1. claude mcp add runapi -s user -- npx -y @runapi.ai/mcp
2. Restart Claude Code
3. Paste this prompt: Generate an image: "Ultra-realistic 8K full body portrait of [PERSON’S FULL NAME], wearing a clean and pressed white social shirt with folded collar and a small lapel microphone, dark navy-blue dress pants and polished brown social shoes. Casually and unpretentiously leaning against a smooth light gray studio wall; hands are in pockets and one leg is crossed over the other, with relaxed and confident body language. Add to the wall next to them a prominent vector portrait in black and white of their face and bust - with sharp lines and angles, overlapping polygonal shapes and a minimalist modern graphic style, right below the information: “[PERSON’S FULL NAME]”, and below the name: “[PROFESSION]”"
1. codex plugin install runapi-mcp@agents
2. Restart Codex
3. Paste this prompt: Generate an image: "Ultra-realistic 8K full body portrait of [PERSON’S FULL NAME], wearing a clean and pressed white social shirt with folded collar and a small lapel microphone, dark navy-blue dress pants and polished brown social shoes. Casually and unpretentiously leaning against a smooth light gray studio wall; hands are in pockets and one leg is crossed over the other, with relaxed and confident body language. Add to the wall next to them a prominent vector portrait in black and white of their face and bust - with sharp lines and angles, overlapping polygonal shapes and a minimalist modern graphic style, right below the information: “[PERSON’S FULL NAME]”, and below the name: “[PROFESSION]”"
1. npx @runapi.ai/mcp init cursor
2. Restart Cursor
3. Paste this prompt: Generate an image: "Ultra-realistic 8K full body portrait of [PERSON’S FULL NAME], wearing a clean and pressed white social shirt with folded collar and a small lapel microphone, dark navy-blue dress pants and polished brown social shoes. Casually and unpretentiously leaning against a smooth light gray studio wall; hands are in pockets and one leg is crossed over the other, with relaxed and confident body language. Add to the wall next to them a prominent vector portrait in black and white of their face and bust - with sharp lines and angles, overlapping polygonal shapes and a minimalist modern graphic style, right below the information: “[PERSON’S FULL NAME]”, and below the name: “[PROFESSION]”"
1. npx @runapi.ai/mcp init windsurf
2. Restart Windsurf
3. Paste this prompt: Generate an image: "Ultra-realistic 8K full body portrait of [PERSON’S FULL NAME], wearing a clean and pressed white social shirt with folded collar and a small lapel microphone, dark navy-blue dress pants and polished brown social shoes. Casually and unpretentiously leaning against a smooth light gray studio wall; hands are in pockets and one leg is crossed over the other, with relaxed and confident body language. Add to the wall next to them a prominent vector portrait in black and white of their face and bust - with sharp lines and angles, overlapping polygonal shapes and a minimalist modern graphic style, right below the information: “[PERSON’S FULL NAME]”, and below the name: “[PROFESSION]”"
curl -X POST https://runapi.ai/api/v1/nano_banana/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "nano-banana-2",
"prompt": "Ultra-realistic 8K full body portrait of [PERSON’S FULL NAME], wearing a clean and pressed white social shirt with folded collar and a small lapel microphone, dark navy-blue dress pants and polished brown social shoes. Casually and unpretentiously leaning against a smooth light gray studio wall; hands are in pockets and one leg is crossed over the other, with relaxed and confident body language. Add to the wall next to them a prominent vector portrait in black and white of their face and bust - with sharp lines and angles, overlapping polygonal shapes and a minimalist modern graphic style, right below the information: “[PERSON’S FULL NAME]”, and below the name: “[PROFESSION]”"
}
JSON
import { NanoBananaClient } from "@runapi.ai/nano-banana";
const client = new NanoBananaClient({
apiKey: process.env.RUNAPI_API_KEY,
});
const result = await client.textToImage.run({
"model": "nano-banana-2",
"prompt": "Ultra-realistic 8K full body portrait of [PERSON’S FULL NAME], wearing a clean and pressed white social shirt with folded collar and a small lapel microphone, dark navy-blue dress pants and polished brown social shoes. Casually and unpretentiously leaning against a smooth light gray studio wall; hands are in pockets and one leg is crossed over the other, with relaxed and confident body language. Add to the wall next to them a prominent vector portrait in black and white of their face and bust - with sharp lines and angles, overlapping polygonal shapes and a minimalist modern graphic style, right below the information: “[PERSON’S FULL NAME]”, and below the name: “[PROFESSION]”"
});
console.log(result.id);
require "runapi/nano_banana"
client = RunApi::NanoBanana::Client.new
result = client.text_to_image.run(
model: "nano-banana-2",
prompt: "Ultra-realistic 8K full body portrait of [PERSON’S FULL NAME], wearing a clean and pressed white social shirt with folded collar and a small lapel microphone, dark navy-blue dress pants and polished brown social shoes. Casually and unpretentiously leaning against a smooth light gray studio wall; hands are in pockets and one leg is crossed over the other, with relaxed and confident body language. Add to the wall next to them a prominent vector portrait in black and white of their face and bust - with sharp lines and angles, overlapping polygonal shapes and a minimalist modern graphic style, right below the information: “[PERSON’S FULL NAME]”, and below the name: “[PROFESSION]”"
)
puts result.id
package main
import (
"context"
"fmt"
"log"
"net/http"
"os"
"strings"
)
func main() {
body := strings.NewReader("{\"model\":\"nano-banana-2\",\"prompt\":\"Ultra-realistic 8K full body portrait of [PERSON’S FULL NAME], wearing a clean and pressed white social shirt with folded collar and a small lapel microphone, dark navy-blue dress pants and polished brown social shoes. Casually and unpretentiously leaning against a smooth light gray studio wall; hands are in pockets and one leg is crossed over the other, with relaxed and confident body language. Add to the wall next to them a prominent vector portrait in black and white of their face and bust - with sharp lines and angles, overlapping polygonal shapes and a minimalist modern graphic style, right below the information: “[PERSON’S FULL NAME]”, and below the name: “[PROFESSION]”\"}")
req, err := http.NewRequestWithContext(context.Background(), http.MethodPost, "https://runapi.ai/api/v1/nano_banana/text_to_image", body)
if err != nil {
log.Fatal(err)
}
req.Header.Set("Authorization", "Bearer "+os.Getenv("RUNAPI_API_KEY"))
req.Header.Set("Content-Type", "application/json")
resp, err := http.DefaultClient.Do(req)
if err != nil {
log.Fatal(err)
}
defer resp.Body.Close()
fmt.Println(resp.Status)
}
nano-banana-2/api/v1/nano_banana/text_to_imageGet API Key
Murphy magazine fashion editorial photograph. Androgynous model early 30s, sharp bone structure, flawless skin, hair slicked back, neutral composed expression, standing perfectly straight full body centered against a massive polished black marble architectural facade — reflective stone, towering vertical panels, subtle veining, high-gloss luxury surface. Wearing an immaculate oversized black double-breasted long coat single button fastened, black wide-leg trousers with razor sharp centre crease, black leather pointed toe mule, one sculptural black leather architectural bag on left shoulder, designer Louis Vuitton. Left hand on hip, right arm hanging, chin slightly raised, looking directly into lens with complete calm authority. High-gloss cinematic lighting with controlled studio key light from left, cool monochrome highlights carving sharp reflections across coat and marble surface, face precisely sculpted with high contrast shadow and highlight. Background: deep black marble fills entire frame zero sky visible — tonal black on black ultra luxury. Typography overlaid exactly as Murphy magazine cover: top center — “MURPHY” in massive modern serif 90px white, letter-spaced 20px. Below masthead left — “PARIS” in 8px Josefin Sans tracked white caps. Top right — “Fall / Winter 2026” in 9px italic Cormorant Garamond white. Bottom left — editorial headline in stacked Playfair Display italic: “Monochrome” line 1, “Motion,” line 2, “Modern Power.” line 3 — 52px white, “Power.” in metallic silver. Bottom right — “Issue No. 01 · €12.00” in 8px tracked Josefin Sans white. Left edge vertical — “Photography · Styling · Creative Direction” in 7px white caps rotated 90 degrees. Shot on Hasselblad H6D-400C, 85mm, shallow DOF, glossy marble bokeh, HDR, Murphy high-gloss fashion editorial cover, 4:5 portrait
curl -X POST https://runapi.ai/api/v1/nano_banana/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "nano-banana-2",
"prompt": "Murphy magazine fashion editorial photograph. Androgynous model early 30s, sharp bone structure, flawless skin, hair slicked back, neutral composed expression, standing perfectly straight full body centered against a massive polished black marble architectural facade — reflective stone, towering vertical panels, subtle veining, high-gloss luxury surface. Wearing an immaculate oversized black double-breasted long coat single button fastened, black wide-leg trousers with razor sharp centre crease, black leather pointed toe mule, one sculptural black leather architectural bag on left shoulder, designer Louis Vuitton. Left hand on hip, right arm hanging, chin slightly raised, looking directly into lens with complete calm authority. High-gloss cinematic lighting with controlled studio key light from left, cool monochrome highlights carving sharp reflections across coat and marble surface, face precisely sculpted with high contrast shadow and highlight. Background: deep black marble fills entire frame zero sky visible — tonal black on black ultra luxury. Typography overlaid exactly as Murphy magazine cover: top center — “MURPHY” in massive modern serif 90px white, letter-spaced 20px. Below masthead left — “PARIS” in 8px Josefin Sans tracked white caps. Top right — “Fall / Winter 2026” in 9px italic Cormorant Garamond white. Bottom left — editorial headline in stacked Playfair Display italic: “Monochrome” line 1, “Motion,” line 2, “Modern Power.” line 3 — 52px white, “Power.” in metallic silver. Bottom right — “Issue No. 01 · €12.00” in 8px tracked Josefin Sans white. Left edge vertical — “Photography · Styling · Creative Direction” in 7px white caps rotated 90 degrees. Shot on Hasselblad H6D-400C, 85mm, shallow DOF, glossy marble bokeh, HDR, Murphy high-gloss fashion editorial cover, 4:5 portrait"
}
JSON
<instruction> 1. Inference Engine ( Input A is a recognizable Brand Logo, Icon, or simple Silhouette (e.g., The Apple Logo, Nike Swoosh, Batman Symbol, A Heart). Input B is a vast Natural Landscape (e.g., Snowy Mountains, Dense Jungle, Sand Dunes, Ocean Coastline). Deconstruct the inputs to generate 3 Topographical Assets : The Negative Space (The Carving): How does the logo fit into the landscape? (e.g., The main body of the Apple logo is carved out of a snowy mountain peak). The Positive Space (The Island): Are there floating or detached elements of the logo? (e.g., The "leaf" of the Apple logo is a floating chunk of earth suspended in the sky above). The Texture (The Biome): What materials make up the shape? (e.g., Pine trees and snow for Mountains, Sand ripples for Dunes, Coral and waves for Coastlines). 2. Container Goal: "Subliminal Advertising" Landscape Photography. The Perspective: A wide, sweeping Aerial Drone Shot . The landscape stretches out vast and majestic, dominating the frame. The Atmosphere: Dramatic, moody weather. Heavy, swirling clouds, mist, or fog rolling through the valleys. 3. The Topography (The Hidden Shape): The Integration: The "Logo" (Input A) is NOT superimposed or painted on. It is formed entirely by the physical geometry of the terrain. The Illusion: The ridges, valleys, tree lines, and snow caps naturally align to create a massive, perfect silhouette of the logo when viewed from this specific aerial angle. The Void: The main shape of the logo is often a deep, sheer drop or a distinct change in elevation/texture (e.g., a dark pine forest shaped like an apple cut into a white snowy mountain). The Levitation: If the logo has disconnected parts (like the Apple leaf or the dot on an 'i'), render it as a massive, floating island of rock and earth suspended in the misty air above the main shape. 4. Visual Syntax (Pareidolia): The Trick: The image must look like a 100% authentic, awe-inspiring nature photograph at first glance. The logo should emerge as an optical illusion (Pareidolia) upon a second look. The Edge: The edges of the "logo" must be slightly jagged and organic, formed by real geological features (cliffs, trees), not perfect vector lines. 5. Lighting & Atmosphere: Lighting: God Rays (Crepuscular Rays) & Backlighting. The sun is hidden behind the clouds or the floating landmass, blasting intense beams of light through the mist and defining the silhouette of the hidden shape. Contrast: High contrast between the dark valleys (forests/shadows) and the bright highlights (snow/sunlight). Vibe: Cinematic, majestic, and subtly surreal. Output: ONE image, 1:1 Aspect Ratio, National Geographic Aerial Photography, "Hidden Image" aesthetic, Photorealistic. </instruction> 2. <system_role> you are an optical illusion artist and landscape photographer. </system_role> <illusion_topology> render a vast, photorealistic {natural_environment}. however, the shadows, highlights, and physical layout of the landscape must form the exact facial contours and silhouette of {pop_culture_icon} when viewed from a distance. - dark zones (forming the eyes/hair/shadows): deep shadows cast by {dark_nature_elements}. - light zones (forming the skin/highlights): bright areas made of {light_nature_elements}. </illusion_topology> <visual_execution> the image must function flawlessly as two things at once: 1. up close: a beautiful, highly detailed photograph of a {natural_environment} during {weather_condition}. 2. zoomed out: a clear portrait of {pop_culture_icon}. ensure the blending is organic. do not use digital fade overlays. the rocks/trees themselves must form the face. </visual_execution>
curl -X POST https://runapi.ai/api/v1/nano_banana/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "nano-banana-2",
"prompt": "<instruction> 1. Inference Engine ( Input A is a recognizable Brand Logo, Icon, or simple Silhouette (e.g., The Apple Logo, Nike Swoosh, Batman Symbol, A Heart). Input B is a vast Natural Landscape (e.g., Snowy Mountains, Dense Jungle, Sand Dunes, Ocean Coastline). Deconstruct the inputs to generate 3 Topographical Assets : The Negative Space (The Carving): How does the logo fit into the landscape? (e.g., The main body of the Apple logo is carved out of a snowy mountain peak). The Positive Space (The Island): Are there floating or detached elements of the logo? (e.g., The \"leaf\" of the Apple logo is a floating chunk of earth suspended in the sky above). The Texture (The Biome): What materials make up the shape? (e.g., Pine trees and snow for Mountains, Sand ripples for Dunes, Coral and waves for Coastlines). 2. Container Goal: \"Subliminal Advertising\" Landscape Photography. The Perspective: A wide, sweeping Aerial Drone Shot . The landscape stretches out vast and majestic, dominating the frame. The Atmosphere: Dramatic, moody weather. Heavy, swirling clouds, mist, or fog rolling through the valleys. 3. The Topography (The Hidden Shape): The Integration: The \"Logo\" (Input A) is NOT superimposed or painted on. It is formed entirely by the physical geometry of the terrain. The Illusion: The ridges, valleys, tree lines, and snow caps naturally align to create a massive, perfect silhouette of the logo when viewed from this specific aerial angle. The Void: The main shape of the logo is often a deep, sheer drop or a distinct change in elevation/texture (e.g., a dark pine forest shaped like an apple cut into a white snowy mountain). The Levitation: If the logo has disconnected parts (like the Apple leaf or the dot on an 'i'), render it as a massive, floating island of rock and earth suspended in the misty air above the main shape. 4. Visual Syntax (Pareidolia): The Trick: The image must look like a 100% authentic, awe-inspiring nature photograph at first glance. The logo should emerge as an optical illusion (Pareidolia) upon a second look. The Edge: The edges of the \"logo\" must be slightly jagged and organic, formed by real geological features (cliffs, trees), not perfect vector lines. 5. Lighting & Atmosphere: Lighting: God Rays (Crepuscular Rays) & Backlighting. The sun is hidden behind the clouds or the floating landmass, blasting intense beams of light through the mist and defining the silhouette of the hidden shape. Contrast: High contrast between the dark valleys (forests/shadows) and the bright highlights (snow/sunlight). Vibe: Cinematic, majestic, and subtly surreal. Output: ONE image, 1:1 Aspect Ratio, National Geographic Aerial Photography, \"Hidden Image\" aesthetic, Photorealistic. </instruction> 2. <system_role> you are an optical illusion artist and landscape photographer. </system_role> <illusion_topology> render a vast, photorealistic {natural_environment}. however, the shadows, highlights, and physical layout of the landscape must form the exact facial contours and silhouette of {pop_culture_icon} when viewed from a distance. - dark zones (forming the eyes/hair/shadows): deep shadows cast by {dark_nature_elements}. - light zones (forming the skin/highlights): bright areas made of {light_nature_elements}. </illusion_topology> <visual_execution> the image must function flawlessly as two things at once: 1. up close: a beautiful, highly detailed photograph of a {natural_environment} during {weather_condition}. 2. zoomed out: a clear portrait of {pop_culture_icon}. ensure the blending is organic. do not use digital fade overlays. the rocks/trees themselves must form the face. </visual_execution>"
}
JSON
FAQ
Using nano-banana-2 prompts
What is %{model}?
%{model} is available through RunAPI as part of the unified model catalog. These prompts show practical input patterns that agents and backend services can reuse.
How do I use these prompts?
Copy any prompt and paste it into Claude Code, Codex, Cursor, or Windsurf after installing the RunAPI MCP Server. Developers can also copy the API example and send the prompt directly.
Do these prompts cost money to browse?
Browsing and copying prompt examples is free. Generation requests only cost money when you call a RunAPI model with your API key.
Can I adapt the prompts for production?
Yes. Treat each prompt as a starting point, then add your brand rules, output dimensions, safety constraints, and application-specific context before using it in production.