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
High-quality stylized 3D CGI big-head cartoon render of Harry Potter, square profile picture composition, oversized head and small shoulders in a playful Pixar-style caricature. Head and facial features exaggerated while keeping him instantly recognizable: messy dark hair, round glasses, lightning-shaped scar on the forehead, curious and brave expression. Portrait framing focused on the large head with a small portion of the shoulders visible, wearing Hogwarts robe collar and tie. Smooth polished materials, glossy animated film shading with refined Pixar-style character rendering. Soft cinematic lighting creating gentle highlights on the glasses. Minimalist bright magical red background inspired by Hogwarts colors, clean composition optimized for social media profile pictures, ultra-detailed, no text, no watermark.
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": "High-quality stylized 3D CGI big-head cartoon render of Harry Potter, square profile picture composition, oversized head and small shoulders in a playful Pixar-style caricature. Head and facial features exaggerated while keeping him instantly recognizable: messy dark hair, round glasses, lightning-shaped scar on the forehead, curious and brave expression. Portrait framing focused on the large head with a small portion of the shoulders visible, wearing Hogwarts robe collar and tie. Smooth polished materials, glossy animated film shading with refined Pixar-style character rendering. Soft cinematic lighting creating gentle highlights on the glasses. Minimalist bright magical red background inspired by Hogwarts colors, clean composition optimized for social media profile pictures, ultra-detailed, no text, no watermark."
}
JSON
A handcrafted felt miniature scene featuring a soft wool doll character with simplified facial features, round button eyes, rosy cheeks, and a gentle smile. The character wears a dark felt jacket, gray wool t-shirt, and matching trousers, styled in a minimal casual tech look. He is walking on grassy felt terrain alongside a small felt fox companion. Whimsical storybook environment with pastel greenery, soft clouds, and a bright blue sky, subtle miniature rockets blurred in the background. Macro photography style, shallow depth of field, soft natural daylight, stop-motion animation aesthetic, ultra-detailed felt fibers and fabric textures, cozy cinematic mood, high quality.
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": "A handcrafted felt miniature scene featuring a soft wool doll character with simplified facial features, round button eyes, rosy cheeks, and a gentle smile. The character wears a dark felt jacket, gray wool t-shirt, and matching trousers, styled in a minimal casual tech look. He is walking on grassy felt terrain alongside a small felt fox companion. Whimsical storybook environment with pastel greenery, soft clouds, and a bright blue sky, subtle miniature rockets blurred in the background. Macro photography style, shallow depth of field, soft natural daylight, stop-motion animation aesthetic, ultra-detailed felt fibers and fabric textures, cozy cinematic mood, high quality."
}
JSON
A hyper-realistic 3D photo concept showing a hand holding a square polaroid photo labeled “[ELEMENT]”. Inside the photo, there’s a close-up of [ELEMENT], and it flows seamlessly out of the photo frame into the real world, naturally interacting with the surface below. The text “[ELEMENT]” appears printed cleanly on the white border of the photo. Realistic cinematic lighting, ultra-detailed textures, artistic composition
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": "A hyper-realistic 3D photo concept showing a hand holding a square polaroid photo labeled “[ELEMENT]”. Inside the photo, there’s a close-up of [ELEMENT], and it flows seamlessly out of the photo frame into the real world, naturally interacting with the surface below. The text “[ELEMENT]” appears printed cleanly on the white border of the photo. Realistic cinematic lighting, ultra-detailed textures, artistic composition"
}
JSON
Pixar/Disney 3D CGI animated movie poster. Soft volumetric lighting, smooth subsurface skin shading, expressive Pixar-style faces, polished studio render quality. Vertical poster, 3:4 ratio. Show/Movie: [SHOW/MOVIE] Automatically select the 3 most iconic characters from [SHOW/MOVIE]. Render each as a Pixar 3D CGI character with recognizable likeness, wearing their single most iconic outfit. TITLE — LOCKED: Show title at the very top. ALL CAPS. Pure white. Extra bold sans-serif block font. No outlines, no graphic boxes, no mixed case. Large, centered, one line if possible. PANELS — LOCKED: Three vertical panels below the title. Each panel shows ONE character, UPPER BODY from waist up, filling the panel with face large and centered. Panel outline is a bold thick stroke in the most iconic accent color of [SHOW/MOVIE] — vivid and saturated, not dark or muted. ∙Left panel: perfectly straight ∙Center panel: perfectly straight, slightly larger than the side panels ∙Right panel: perfectly straight BACKGROUND — LOCKED FORMAT, VARIABLE PATTERN: Background uses the 2 most iconic colors of [SHOW/MOVIE] — fully saturated, vivid and punchy, NOT darkened or desaturated. High contrast and visually striking. Behind the panels, fill the background with a large abstract graphic pattern directly inspired by the most iconic visual symbol of [SHOW/MOVIE] — blown up, repeating, semi-transparent. Examples: Breaking Bad = oversized molecular/chemical structures in bright yellow-green. Stranger Things = tangled vine tendrils in vivid red. Peaky Blinders = repeating razor blade motif in sharp silver-burgundy. The Sopranos = bold pinstripe pattern in navy and gold. No scenes, no characters, no locations in the background. Pattern only. Overall image must feel bold, vibrant, energetic and eye-catching — like a premium comic poster, not a muted cinematic still. RULES: ∙Upper body only — waist to top of head, face prominent and large inside panel ∙Pure white ALL CAPS bold title only — no other text ∙No character names, no watermarks, no logos, no extra graphic elements ∙Colors must be vivid, saturated and high contrast throughout — no muted, faded or desaturated tones anywhere ∙8K, professional Pixar studio render quality
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": "Pixar/Disney 3D CGI animated movie poster. Soft volumetric lighting, smooth subsurface skin shading, expressive Pixar-style faces, polished studio render quality. Vertical poster, 3:4 ratio. Show/Movie: [SHOW/MOVIE] Automatically select the 3 most iconic characters from [SHOW/MOVIE]. Render each as a Pixar 3D CGI character with recognizable likeness, wearing their single most iconic outfit. TITLE — LOCKED: Show title at the very top. ALL CAPS. Pure white. Extra bold sans-serif block font. No outlines, no graphic boxes, no mixed case. Large, centered, one line if possible. PANELS — LOCKED: Three vertical panels below the title. Each panel shows ONE character, UPPER BODY from waist up, filling the panel with face large and centered. Panel outline is a bold thick stroke in the most iconic accent color of [SHOW/MOVIE] — vivid and saturated, not dark or muted. ∙Left panel: perfectly straight ∙Center panel: perfectly straight, slightly larger than the side panels ∙Right panel: perfectly straight BACKGROUND — LOCKED FORMAT, VARIABLE PATTERN: Background uses the 2 most iconic colors of [SHOW/MOVIE] — fully saturated, vivid and punchy, NOT darkened or desaturated. High contrast and visually striking. Behind the panels, fill the background with a large abstract graphic pattern directly inspired by the most iconic visual symbol of [SHOW/MOVIE] — blown up, repeating, semi-transparent. Examples: Breaking Bad = oversized molecular/chemical structures in bright yellow-green. Stranger Things = tangled vine tendrils in vivid red. Peaky Blinders = repeating razor blade motif in sharp silver-burgundy. The Sopranos = bold pinstripe pattern in navy and gold. No scenes, no characters, no locations in the background. Pattern only. Overall image must feel bold, vibrant, energetic and eye-catching — like a premium comic poster, not a muted cinematic still. RULES: ∙Upper body only — waist to top of head, face prominent and large inside panel ∙Pure white ALL CAPS bold title only — no other text ∙No character names, no watermarks, no logos, no extra graphic elements ∙Colors must be vivid, saturated and high contrast throughout — no muted, faded or desaturated tones anywhere ∙8K, professional Pixar studio render quality"
}
JSON
Hyper-stylized dynamic 3D floating head portrait of the attached reference image, perfectly centered, upright, symmetrical, filling 80% of the 4:5 frame. No neck. No shoulder edges. Clean cut-out. Subject floating in white space.Predominantly white background enhanced with subtle tonal gradients and soft volumetric glow. A thin luminous neon halo ring glows behind the head, slightly diffused but clean and circular. Facial features match reference photo precisely. Expression: confident, dominant smirk with focused eye contact. Diamond-studded braces sparkle under sharp lighting. Sleek silver sports sunglasses reflect digital stadium lights and neon streaks. Chrome stud earrings and polished silver chain subtly visible. Official lakers shirt strictly front view chest logo and sponsor visible only. Lighting combines bright frontal fill with strong rim lights. Subtle neon reflections trace along jawline edges. Micro lens flares appear at high-intensity highlights. White-on-white energy with controlled neon accents. Futuristic champion aura. Glossy skin, exaggerated reflections, cinematic intensity. Aspect ratio 4:5.
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": "Hyper-stylized dynamic 3D floating head portrait of the attached reference image, perfectly centered, upright, symmetrical, filling 80% of the 4:5 frame. No neck. No shoulder edges. Clean cut-out. Subject floating in white space.Predominantly white background enhanced with subtle tonal gradients and soft volumetric glow. A thin luminous neon halo ring glows behind the head, slightly diffused but clean and circular. Facial features match reference photo precisely. Expression: confident, dominant smirk with focused eye contact. Diamond-studded braces sparkle under sharp lighting. Sleek silver sports sunglasses reflect digital stadium lights and neon streaks. Chrome stud earrings and polished silver chain subtly visible. Official lakers shirt strictly front view chest logo and sponsor visible only. Lighting combines bright frontal fill with strong rim lights. Subtle neon reflections trace along jawline edges. Micro lens flares appear at high-intensity highlights. White-on-white energy with controlled neon accents. Futuristic champion aura. Glossy skin, exaggerated reflections, cinematic intensity. Aspect ratio 4:5."
}
JSON
Vertical 4:5 surreal 3D scene featuring a photorealistic character generated strictly from the attached reference image (accurate facial likeness, skin texture, age, proportions). Front-facing view, camera slightly above eye level, the character riding his own scooter or motorbike directly on top of the blue GPS route line itself, moving forward toward a red destination pin. The character wears culturally neutral, realistic urban clothing inspired by [COUNTRY], with accurate fabric behavior and natural riding posture. Below, a stylized GPS-style city map of [CITY] fills the scene. A chaos zone at [LANDMARK / AREA] shows dense miniature cars, people, buildings, trees, and urban clutter concentrated near the destination. Natural daylight, cinematic shadows, sharp focus on the character, and subtle depth of field on the map. High-end concept-art quality combining photoreal human + stylized miniature city.
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": "Vertical 4:5 surreal 3D scene featuring a photorealistic character generated strictly from the attached reference image (accurate facial likeness, skin texture, age, proportions). Front-facing view, camera slightly above eye level, the character riding his own scooter or motorbike directly on top of the blue GPS route line itself, moving forward toward a red destination pin. The character wears culturally neutral, realistic urban clothing inspired by [COUNTRY], with accurate fabric behavior and natural riding posture. Below, a stylized GPS-style city map of [CITY] fills the scene. A chaos zone at [LANDMARK / AREA] shows dense miniature cars, people, buildings, trees, and urban clutter concentrated near the destination. Natural daylight, cinematic shadows, sharp focus on the character, and subtle depth of field on the map. High-end concept-art quality combining photoreal human + stylized miniature city."
}
JSON
3D Pixar-style animated girl shown in a 6-panel grid, same character with short brown hair and big blue eyes, different emotions (happy, shocked, angry, caring, confident, thumbs up), colorful solid backgrounds (yellow, blue, red, pink, purple, green), soft studio lighting, smooth 3D render, vibrant colors, ultra-detailed, 4K, animated movie quality.
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": "3D Pixar-style animated girl shown in a 6-panel grid, same character with short brown hair and big blue eyes, different emotions (happy, shocked, angry, caring, confident, thumbs up), colorful solid backgrounds (yellow, blue, red, pink, purple, green), soft studio lighting, smooth 3D render, vibrant colors, ultra-detailed, 4K, animated movie quality."
}
JSON
A highly detailed pebble mosaic portrait of a beautiful woman, where the entire image is constructed from thousands of smooth natural stones and pebbles. The pebbles vary in size and color to form realistic facial features, hair, skin tones, and clothing patterns. The woman has long flowing hair and is wearing a richly patterned red traditional dress. The background is also composed of carefully arranged river stones creating a textured mosaic wall. Ultra-detailed stone texture, gemini natural earthy colors, soft lighting, artistic stone mosaic craftsmanship, gemini photorealistic composition, 8k resolution, intricate pebble placement, handcrafted mosaic art style.
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": "A highly detailed pebble mosaic portrait of a beautiful woman, where the entire image is constructed from thousands of smooth natural stones and pebbles. The pebbles vary in size and color to form realistic facial features, hair, skin tones, and clothing patterns. The woman has long flowing hair and is wearing a richly patterned red traditional dress. The background is also composed of carefully arranged river stones creating a textured mosaic wall. Ultra-detailed stone texture, gemini natural earthy colors, soft lighting, artistic stone mosaic craftsmanship, gemini photorealistic composition, 8k resolution, intricate pebble placement, handcrafted mosaic art style."
}
JSON
Create a miniature 3D isometric diorama showing the invention of [INVENTION NAME] at the moment of [KEY BREAKTHROUGH]. Camera angle around 40° from above. Textures feel soft and polished. Materials follow realistic PBR rules. Lighting feels natural and balanced. The raised base includes tools, workshop elements, notes, and early prototypes. Tiny stylized inventors interact with objects. Faces are visible and recognizable with clean shapes and expressions. Background stays solid [BACKGROUND COLOR]. Top center text shows [INVENTION NAME] in bold. Second line shows [YEAR OR INVENTOR]. A simple line icon of the invention sits below. Text color adapts to background contrast.
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": "Create a miniature 3D isometric diorama showing the invention of [INVENTION NAME] at the moment of [KEY BREAKTHROUGH]. Camera angle around 40° from above. Textures feel soft and polished. Materials follow realistic PBR rules. Lighting feels natural and balanced. The raised base includes tools, workshop elements, notes, and early prototypes. Tiny stylized inventors interact with objects. Faces are visible and recognizable with clean shapes and expressions. Background stays solid [BACKGROUND COLOR]. Top center text shows [INVENTION NAME] in bold. Second line shows [YEAR OR INVENTOR]. A simple line icon of the invention sits below. Text color adapts to background contrast."
}
JSON
A high-resolution, photorealistic three-panel composition featuring a woman with long, voluminous wavy brown hair and elegant features, integrated into an abstract mixed-media collage background. Panel Layout: Left Panel (Vertical, full height): A tall portrait of the woman looking upwards at a dramatic angle, wearing a mustard yellow turtleneck. Cinematic lighting highlights her face and hair, with strong shadows and depth. Top Right Panel (Square): A close-up angled side profile, soft gaze to the right, wearing a black modern blazer with minimal jewelry. Expression is calm and confident. Bottom Right Panel (Square): A slightly top-down perspective, playful yet elegant pose, wearing a white textured dress, subtle smile, natural lighting. Art Style & Background (applies to all panels): The image is layered with an abstract mixed-media collage background incorporating geometric shapes like circles and rectangles in ochre, burnt orange, and charcoal grey. Include textural elements such as vintage parchment paper, blueprint-style technical sketches, and subtle floral etchings. Use a flat graphic design overlay that partially blends into each outfit, seamlessly merging the 3D subject with 2D modernist art. Overall Style: Cinematic lighting, fine art photography aesthetic, ultra-detailed, 8K resolution, modern editorial fashion magazine layout.
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": "A high-resolution, photorealistic three-panel composition featuring a woman with long, voluminous wavy brown hair and elegant features, integrated into an abstract mixed-media collage background. Panel Layout: Left Panel (Vertical, full height): A tall portrait of the woman looking upwards at a dramatic angle, wearing a mustard yellow turtleneck. Cinematic lighting highlights her face and hair, with strong shadows and depth. Top Right Panel (Square): A close-up angled side profile, soft gaze to the right, wearing a black modern blazer with minimal jewelry. Expression is calm and confident. Bottom Right Panel (Square): A slightly top-down perspective, playful yet elegant pose, wearing a white textured dress, subtle smile, natural lighting. Art Style & Background (applies to all panels): The image is layered with an abstract mixed-media collage background incorporating geometric shapes like circles and rectangles in ochre, burnt orange, and charcoal grey. Include textural elements such as vintage parchment paper, blueprint-style technical sketches, and subtle floral etchings. Use a flat graphic design overlay that partially blends into each outfit, seamlessly merging the 3D subject with 2D modernist art. Overall Style: Cinematic lighting, fine art photography aesthetic, ultra-detailed, 8K resolution, modern editorial fashion magazine layout."
}
JSON
A cute stylized 3D collectible figurine inspired by Cristiano Ronaldo, with short styled hair and an athletic build, wearing a modern football kit and standing confidently with hands on hips. Next to him is a large Kinder Joy egg featuring a cartoon avatar of the same football star printed on the shell. The scene is placed on a wooden table with soft natural lighting, shallow depth of field, cozy indoor background with blurred plants, highly detailed Pixar-style 3D render, glossy toy texture, cinematic lighting, ultra-detailed product photography, designer toy aesthetic. ⚽🥚
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": "A cute stylized 3D collectible figurine inspired by Cristiano Ronaldo, with short styled hair and an athletic build, wearing a modern football kit and standing confidently with hands on hips. Next to him is a large Kinder Joy egg featuring a cartoon avatar of the same football star printed on the shell. The scene is placed on a wooden table with soft natural lighting, shallow depth of field, cozy indoor background with blurred plants, highly detailed Pixar-style 3D render, glossy toy texture, cinematic lighting, ultra-detailed product photography, designer toy aesthetic. ⚽🥚"
}
JSON
hyper-realistic food photography of a pancake shaped precisely like the [brand name] logo, natural golden-brown pancake texture, soft porous surface with realistic bubbles, slightly crispy edges, placed on a pure white background, minimal composition, soft natural shadow beneath, top-down flat lay perspective, subtle bite taken from one edge revealing fluffy interior, realistic crumb texture, soft diffused studio lighting, ultra detailed, clean commercial aesthetic, sharp focus
A clean, minimal 3D isometric diorama of a [BUILDING TYPE] section, featuring [INTERIOR / EXTERIOR ELEMENTS] visible in a [CUTAWAY / OPEN STYLE], simple [STRUCTURAL FRAME], subtle [INFORMATIONAL SIGNAGE], smooth [MATERIAL FINISH], soft studio lighting, realistic materials, rounded edges, miniature architectural model style, high detail, neutral background.
Transform the person from the attached photo into a smooth stylized 3D cartoon character in the same style as the reference. Keep all real facial features fully recognizable but translated into exaggerated proportions (elongated head, big eyelids, soft rounded shapes). Skin should look glossy and plastic-like with clean gradients and subtle highlights. Use soft studio lighting, a solid [COLOR] color background, and high-end Pixar- inspired rendering. Simplify details, add gentle rim light, and preserve the person's hairstyle and accessories in stylized form. The final look must match the clean polished 3D aesthetic of the reference, 4:5 dimension.
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": "Transform the person from the attached photo into a smooth stylized 3D cartoon character in the same style as the reference. Keep all real facial features fully recognizable but translated into exaggerated proportions (elongated head, big eyelids, soft rounded shapes). Skin should look glossy and plastic-like with clean gradients and subtle highlights. Use soft studio lighting, a solid [COLOR] color background, and high-end Pixar- inspired rendering. Simplify details, add gentle rim light, and preserve the person's hairstyle and accessories in stylized form. The final look must match the clean polished 3D aesthetic of the reference, 4:5 dimension."
}
JSON
Hyper-realistic full-body portrait of a woman, using the exact pose from the uploaded photo, transformed into a stylish female doll. she stands confidently with arms crossed on a giant Microsoft Surface Tablet as a platform, wearing urban streetwear (black hoodie, jeans, sneakers) and sleek red tech glasses. Surrounding him in a dynamic, floating arrangement are masculine graphic design tools: a futuristic camera with blue holographic glow, a geometric computer mouse with electric sparks, a digital pen creating digital wireframe trails, a floating Pantone swatch book in bold blue and black colors, and a minimalist black coffee mug with binary code steam. The scene features a vibrant blue and orange color scheme with dynamic lighting. Cyberpunk aesthetic, neon accents, particle effects. Style is a blend of 3D animation and tech photography. Sharp focus, cinematic lighting, 8k resolution.
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": "Hyper-realistic full-body portrait of a woman, using the exact pose from the uploaded photo, transformed into a stylish female doll. she stands confidently with arms crossed on a giant Microsoft Surface Tablet as a platform, wearing urban streetwear (black hoodie, jeans, sneakers) and sleek red tech glasses. Surrounding him in a dynamic, floating arrangement are masculine graphic design tools: a futuristic camera with blue holographic glow, a geometric computer mouse with electric sparks, a digital pen creating digital wireframe trails, a floating Pantone swatch book in bold blue and black colors, and a minimalist black coffee mug with binary code steam. The scene features a vibrant blue and orange color scheme with dynamic lighting. Cyberpunk aesthetic, neon accents, particle effects. Style is a blend of 3D animation and tech photography. Sharp focus, cinematic lighting, 8k resolution."
}
JSON
A hyper-realistic, 8k, medium shot photograph captured with a standard lens and shallow depth of field, showcasing a surreal indoor scene with cinematic lighting. The composition features a normal-sized woman, using the uploaded face as reference, sitting cross-legged inside a colossal, highly detailed Kinder Joy egg that functions as a swing chair. The giant egg is split, with its white interior forming the seat and the orange, textured exterior visible, suspended by dark metal chains from a curved, dark metal stand. The woman wears a black t-shirt and blue and white plaid pajama pants, holding a small white teacup with both hands, looking directly at the viewer with a calm and relaxed expression. To the left in the foreground, on a highly detailed polished wooden table, stands another gigantic, fully wrapped Kinder Joy egg, exhibiting intricate foil texture and branding. To the right of the swing's base, also on the table, are miniature props: a vintage-style wooden radio with white dials and a tiny bonsai tree in a small pot. The lighting is soft, warm, and directional from the left, casting subtle shadows and highlighting the highly detailed textures of the egg wrappers, the woman’s clothing, and the wooden surface. The background is a softly blurred, warm-toned interior wall, creating a pleasing bokeh effect.
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": "A hyper-realistic, 8k, medium shot photograph captured with a standard lens and shallow depth of field, showcasing a surreal indoor scene with cinematic lighting. The composition features a normal-sized woman, using the uploaded face as reference, sitting cross-legged inside a colossal, highly detailed Kinder Joy egg that functions as a swing chair. The giant egg is split, with its white interior forming the seat and the orange, textured exterior visible, suspended by dark metal chains from a curved, dark metal stand. The woman wears a black t-shirt and blue and white plaid pajama pants, holding a small white teacup with both hands, looking directly at the viewer with a calm and relaxed expression. To the left in the foreground, on a highly detailed polished wooden table, stands another gigantic, fully wrapped Kinder Joy egg, exhibiting intricate foil texture and branding. To the right of the swing's base, also on the table, are miniature props: a vintage-style wooden radio with white dials and a tiny bonsai tree in a small pot. The lighting is soft, warm, and directional from the left, casting subtle shadows and highlighting the highly detailed textures of the egg wrappers, the woman’s clothing, and the wooden surface. The background is a softly blurred, warm-toned interior wall, creating a pleasing bokeh effect."
}
JSON
Create a hyper-realistic miniature planet showcasing [KASHMIR] with famous landmarks seamlessly curving around the spherical surface. Position bold 3D white text “[KASHMIR]” naturally integrated across the lush green central parkland with realistic shadows and dimensional depth. Capture from a top-down orbiting angle that emphasizes the dramatic planet curvature. Use soft golden hour daylight filtering through partly cloudy skies, casting gentle shadows on emerald grass and surrounding trees. The background should blend into a swirling atmospheric sky. Apply vibrant greens, warm earth tones, and soft blues. Render in polished photorealistic style with fine architectural detail. 1080x1080 format.
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": "Create a hyper-realistic miniature planet showcasing [KASHMIR] with famous landmarks seamlessly curving around the spherical surface. Position bold 3D white text “[KASHMIR]” naturally integrated across the lush green central parkland with realistic shadows and dimensional depth. Capture from a top-down orbiting angle that emphasizes the dramatic planet curvature. Use soft golden hour daylight filtering through partly cloudy skies, casting gentle shadows on emerald grass and surrounding trees. The background should blend into a swirling atmospheric sky. Apply vibrant greens, warm earth tones, and soft blues. Render in polished photorealistic style with fine architectural detail. 1080x1080 format."
}
JSON
A highly detailed 3D caricature of a cheerful man with an oversized head, a big smile showcasing large teeth, and curly voluminous hair. He is wearing a short-sleeved white button-up shirt, brown high-waisted pants with a belt, and traditional sandals. His pose is casual and friendly, with one hand touching his chin in a thoughtful manner. The art style is semi-realistic with exaggerated cartoonish features, set aw against a clean white background.""A highly detailed 3D caricature of a cheerful man with an oversized head, a big smile showcasing large teeth, and curly voluminous hair. He is wearing a short-sleeved white button-up shirt, brown high-waisted pants with a belt, and traditional sandals. His pose is casual and friendly, with one hand touching his chin in a thoughtful manner. The art style is semi-realistic with exaggerated cartoonish features, set against a clean white background.
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": "A highly detailed 3D caricature of a cheerful man with an oversized head, a big smile showcasing large teeth, and curly voluminous hair. He is wearing a short-sleeved white button-up shirt, brown high-waisted pants with a belt, and traditional sandals. His pose is casual and friendly, with one hand touching his chin in a thoughtful manner. The art style is semi-realistic with exaggerated cartoonish features, set aw against a clean white background.\"\"A highly detailed 3D caricature of a cheerful man with an oversized head, a big smile showcasing large teeth, and curly voluminous hair. He is wearing a short-sleeved white button-up shirt, brown high-waisted pants with a belt, and traditional sandals. His pose is casual and friendly, with one hand touching his chin in a thoughtful manner. The art style is semi-realistic with exaggerated cartoonish features, set against a clean white background."
}
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.