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
Ultra-detailed 3D plush cartoon character, inspired by classic animated TV style, standing in center frame, full body visible. Character designed as a soft toy with realistic fluffy fur texture, smooth rounded shapes, vibrant saturated colors, big expressive eyes, cute proportions, Using the image of [Doraemon's] character, [Nobita carries Doraemon on his back]. High-resolution Pixar-style 3D rendering, soft studio lighting, subtle rim light, clean gradient background (blue tone), cinematic lighting, depth of field, highly detailed fur strands, soft shadows under feet, glossy nose, toy-like material, ultra sharp 8K render. Centered composition, minimal background, character facing camera, symmetrical pose, adorable expression.
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-detailed 3D plush cartoon character, inspired by classic animated TV style, standing in center frame, full body visible. Character designed as a soft toy with realistic fluffy fur texture, smooth rounded shapes, vibrant saturated colors, big expressive eyes, cute proportions, Using the image of [Doraemon's] character, [Nobita carries Doraemon on his back]. High-resolution Pixar-style 3D rendering, soft studio lighting, subtle rim light, clean gradient background (blue tone), cinematic lighting, depth of field, highly detailed fur strands, soft shadows under feet, glossy nose, toy-like material, ultra sharp 8K render. Centered composition, minimal background, character facing camera, symmetrical pose, adorable expression."
}
JSON
珐琅彩琉璃艺术风格，金属质感，制作一枚冰箱贴，写着"西湖·杭州 WEST LAKE"字样。冰箱贴以断桥拱形轮廓为基底外形，金色金属边框包边。画面描绘西湖经典风景：断桥残雪、湖面莲叶、楼外楼画舫、雷峰塔剪影、三潭印月石灯、粉色桃花与垂柳。左侧点缀龙井茶叶图案，右侧装饰杭绣扇面。采用珐琅彩填色工艺：湖水呈透明翠绿，金属线勾勒波纹细节。浅咖色背景，正面展示，所有元素严格控制在基底轮廓范围内，布局美观协调，产品摄影质感，8K细节
Full-body 3D stylized anthropomorphic cartoon dog character wearing modern streetwear, oversized neon green hoodie, cargo pants, chunky sneakers, reflective sunglasses, silver chain necklace. Confident relaxed pose with hands in pockets. Minimal studio background in solid lime green. Soft studio lighting, smooth shadows, high detail fabric texture, Pixar-quality 3D render, ultra-clean composition, centered framing, fashion editorial character design, 8K resolution.
A cinematic poster-style artwork featuring an intense close-up of a man’s eyes centered horizontally across the frame. Only the eyes and part of the face are visible through a narrow horizontal strip, surrounded by deep black negative space above and below. The face is illustrated in a high-contrast, graphic-novel style with bold red, black, and orange tones, dramatic shadows, sharp highlights, and a gritty, intense mood. The eyes look fierce, emotional, and determined, with slightly messy hair. Use the provided image for eye reference
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 cinematic poster-style artwork featuring an intense close-up of a man’s eyes centered horizontally across the frame. Only the eyes and part of the face are visible through a narrow horizontal strip, surrounded by deep black negative space above and below. The face is illustrated in a high-contrast, graphic-novel style with bold red, black, and orange tones, dramatic shadows, sharp highlights, and a gritty, intense mood. The eyes look fierce, emotional, and determined, with slightly messy hair. Use the provided image for eye reference"
}
JSON
A high-detail artistic 3D portrait of the person in the photo, reimagined as a fragmented sculptural mask. The face is vertically split: one side is made of matte charcoal-black stone with deep cracks, while the other side is polished, radiant leaf gold. The entire composition is overlaid on a dark architectural blueprint background featuring intricate gold grid lines, technical diagrams, and elegant golden serif typography. Cinematic lighting, hyper-realistic textures, Kintsugi-inspired aesthetic, luxury conceptual art, 8k resolution, moody and sophisticated atmosphere.
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-detail artistic 3D portrait of the person in the photo, reimagined as a fragmented sculptural mask. The face is vertically split: one side is made of matte charcoal-black stone with deep cracks, while the other side is polished, radiant leaf gold. The entire composition is overlaid on a dark architectural blueprint background featuring intricate gold grid lines, technical diagrams, and elegant golden serif typography. Cinematic lighting, hyper-realistic textures, Kintsugi-inspired aesthetic, luxury conceptual art, 8k resolution, moody and sophisticated atmosphere."
}
JSON
Create an exaggerated stylized 3D caricature character portrait with strong intentional deformation and a clean, controlled surface finish. Use the person from the ATTACHED REFERENCE PHOTO. Preserve the subject’s identity, facial likeness, skin tone, and defining features, but reinterpret them into a bold caricatured 3D form with an elongated neck, oversized head-to-neck ratio, droopy eyelids, heavy lips, and slightly asymmetrical facial structure. Render as a human-like 3D character with smooth, studio-clean skin and intentionally designed detail, avoiding random texture or noise. Style with bold accessories such as round or oval glasses, hoop earrings, gold chains, headscarves or bandanas, and street-luxury clothing. Use neutral studio lighting with soft shadows and even illumination, no dramatic contrast, against a plain neutral grey or off-white background. The overall aesthetic should feel weird, fashion-forward, collectible, and character-driven rather than cute or realistic. Ultra high definition, premium cinematic 3D render quality, hyper realistic hyper realism, clean materials, no freckles, no dirt, no grain, no noise, no speckling, no text, no logos, no watermarks. 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": "Create an exaggerated stylized 3D caricature character portrait with strong intentional deformation and a clean, controlled surface finish. Use the person from the ATTACHED REFERENCE PHOTO. Preserve the subject’s identity, facial likeness, skin tone, and defining features, but reinterpret them into a bold caricatured 3D form with an elongated neck, oversized head-to-neck ratio, droopy eyelids, heavy lips, and slightly asymmetrical facial structure. Render as a human-like 3D character with smooth, studio-clean skin and intentionally designed detail, avoiding random texture or noise. Style with bold accessories such as round or oval glasses, hoop earrings, gold chains, headscarves or bandanas, and street-luxury clothing. Use neutral studio lighting with soft shadows and even illumination, no dramatic contrast, against a plain neutral grey or off-white background. The overall aesthetic should feel weird, fashion-forward, collectible, and character-driven rather than cute or realistic. Ultra high definition, premium cinematic 3D render quality, hyper realistic hyper realism, clean materials, no freckles, no dirt, no grain, no noise, no speckling, no text, no logos, no watermarks. Aspect ratio 4:5"
}
JSON
A street-style map of [CITY_NAME] placed on a {MAP_SURFACE}, with a photorealistic miniature version of [CITY_NAME] emerging from it [LANDMARK_1],[LANDMARK_2],[LANDMARK_3], [NATURE_ELEMENT], [URBAN_LIFE_ELEMENT], [ICONIC_TRANSPORT],and EXTRA_DETAIL.All elements grow from the map like a 3D urban diorama. Studio soft lighting, cinematic depth, 2:3 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": "A street-style map of [CITY_NAME] placed on a {MAP_SURFACE}, with a photorealistic miniature version of [CITY_NAME] emerging from it [LANDMARK_1],[LANDMARK_2],[LANDMARK_3], [NATURE_ELEMENT], [URBAN_LIFE_ELEMENT], [ICONIC_TRANSPORT],and EXTRA_DETAIL.All elements grow from the map like a 3D urban diorama. Studio soft lighting, cinematic depth, 2:3 format"
}
JSON
A creative 3D illusion artwork of a cute young girl stepping out of a spiral notebook page placed on a wooden desk. The notebook has lined paper with handwritten text at the top. The girl looks semi-realistic 3D cartoon style, soft wavy brown hair, natural makeup, sweet smile, wearing a pastel crop top and high-waisted light grey jeans with white sneakers. Her lower body appears sketched in pencil on the notebook while the upper body looks realistic and popping out of the page.
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 creative 3D illusion artwork of a cute young girl stepping out of a spiral notebook page placed on a wooden desk. The notebook has lined paper with handwritten text at the top. The girl looks semi-realistic 3D cartoon style, soft wavy brown hair, natural makeup, sweet smile, wearing a pastel crop top and high-waisted light grey jeans with white sneakers. Her lower body appears sketched in pencil on the notebook while the upper body looks realistic and popping out of the page."
}
JSON
An architectural blueprint of {BUILDING_NAME} placed on a {SURFACE}, with a photorealistic miniature under-construction version of {BUILDING_NAME} emerging from it — {STRUCTURAL_ELEMENT_1}, {STRUCTURAL_ELEMENT_2}, {STRUCTURAL_ELEMENT_3}, {CONSTRUCTION_DETAIL}, {WORKER_SCENE}, {MATERIAL_ELEMENT}, and {EXTRA_DETAIL}. All elements grow from the blueprint like a 3D architectural diorama, steel beams rising from the drawn lines, scaffolding threading through the paper. Studio soft lighting, cinematic depth, 2:3
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": "An architectural blueprint of {BUILDING_NAME} placed on a {SURFACE}, with a photorealistic miniature under-construction version of {BUILDING_NAME} emerging from it — {STRUCTURAL_ELEMENT_1}, {STRUCTURAL_ELEMENT_2}, {STRUCTURAL_ELEMENT_3}, {CONSTRUCTION_DETAIL}, {WORKER_SCENE}, {MATERIAL_ELEMENT}, and {EXTRA_DETAIL}. All elements grow from the blueprint like a 3D architectural diorama, steel beams rising from the drawn lines, scaffolding threading through the paper. Studio soft lighting, cinematic depth, 2:3"
}
JSON
[BRAND NAME]: Enter the brand name here. Goal: Generate a hyper-realistic studio photograph where the stylized logo icon of [BRAND NAME] is a physical 3D ice sculpture lying directly on a snowy surface. Constraint: NO TEXT inside or immediately near the central ice icon. Only the bottom signature. Light, airy background. 1. THE CENTRAL ICE ARTIFACT - Main Subject: A large, 3D volumetric sculpture in the exact shape of the [BRAND NAME] logo icon. - Material: Crafted from high-purity crystalline ice with intricate internal textures, frost needles, and frozen air bubbles. - Details: The surface of the ice logo is covered with small, realistic water droplets and light condensation. - Perspective: The logo is positioned at a 3/4 angle, lying horizontally on the snow to show its depth and thickness. 2. ENVIRONMENT & LAYOUT - View: Eye-level macro perspective, 3/4 view. - Surface: The logo is resting on a field of crisp, detailed, white powdery snow. - Background: A flawless, uniform, very light pale blue and white gradient background (much lighter than the original). - Shadow: A soft, realistic shadow is cast on the snow directly beneath the ice icon to ground it. 3. BOTTOM BRAND SIGNATURE (CRITICAL) - Placement: A clean horizontal signature block centered at the bottom of the frame, far below the ice artifact. - Elements: A tiny, flat, minimalist black version of the [BRAND NAME] logo icon on the left. - Text: The word "[BRAND NAME]" in a clean, bold, black sans-serif typeface immediately to the right of the tiny logo. - Scale: The signature is very small and subtle compared to the main ice sculpture. 4. AESTHETIC - Premium product photography, cold and crisp atmosphere, hyper-realistic 8k resolution, cinematic lighting, ultra-detailed textures.
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": "[BRAND NAME]: Enter the brand name here. Goal: Generate a hyper-realistic studio photograph where the stylized logo icon of [BRAND NAME] is a physical 3D ice sculpture lying directly on a snowy surface. Constraint: NO TEXT inside or immediately near the central ice icon. Only the bottom signature. Light, airy background. 1. THE CENTRAL ICE ARTIFACT - Main Subject: A large, 3D volumetric sculpture in the exact shape of the [BRAND NAME] logo icon. - Material: Crafted from high-purity crystalline ice with intricate internal textures, frost needles, and frozen air bubbles. - Details: The surface of the ice logo is covered with small, realistic water droplets and light condensation. - Perspective: The logo is positioned at a 3/4 angle, lying horizontally on the snow to show its depth and thickness. 2. ENVIRONMENT & LAYOUT - View: Eye-level macro perspective, 3/4 view. - Surface: The logo is resting on a field of crisp, detailed, white powdery snow. - Background: A flawless, uniform, very light pale blue and white gradient background (much lighter than the original). - Shadow: A soft, realistic shadow is cast on the snow directly beneath the ice icon to ground it. 3. BOTTOM BRAND SIGNATURE (CRITICAL) - Placement: A clean horizontal signature block centered at the bottom of the frame, far below the ice artifact. - Elements: A tiny, flat, minimalist black version of the [BRAND NAME] logo icon on the left. - Text: The word \"[BRAND NAME]\" in a clean, bold, black sans-serif typeface immediately to the right of the tiny logo. - Scale: The signature is very small and subtle compared to the main ice sculpture. 4. AESTHETIC - Premium product photography, cold and crisp atmosphere, hyper-realistic 8k resolution, cinematic lighting, ultra-detailed textures."
}
JSON
Epic 3D scene: a weathered passport lies open, its visa stamps erupting into the destinations they represent. Each ink impression becomes a portal—[CITY 1] rises in miniature from one stamp with [DETAIL 1], [CITY 2] pushes through another with [DETAIL 2], [CITY 3] manifests with [DETAIL 3]. [LANDMARK 1], [LANDMARK 2], and [LANDMARK 3] stand at different scales across the pages. Flight paths arc overhead as glowing golden trajectories weaving between all the worlds. Coffee stains become lakes. Worn edges erode into coastlines. [ATMOSPHERIC ELEMENT 1] drifts from one destination while [ATMOSPHERIC ELEMENT 2] swirls near another. Dramatic raking light, tilt-shift depth of field, 8K, UE5, cinematic lighting. The bureaucratic document transformed into a living archive of adventures.
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": "Epic 3D scene: a weathered passport lies open, its visa stamps erupting into the destinations they represent. Each ink impression becomes a portal—[CITY 1] rises in miniature from one stamp with [DETAIL 1], [CITY 2] pushes through another with [DETAIL 2], [CITY 3] manifests with [DETAIL 3]. [LANDMARK 1], [LANDMARK 2], and [LANDMARK 3] stand at different scales across the pages. Flight paths arc overhead as glowing golden trajectories weaving between all the worlds. Coffee stains become lakes. Worn edges erode into coastlines. [ATMOSPHERIC ELEMENT 1] drifts from one destination while [ATMOSPHERIC ELEMENT 2] swirls near another. Dramatic raking light, tilt-shift depth of field, 8K, UE5, cinematic lighting. The bureaucratic document transformed into a living archive of adventures."
}
JSON
Create a high-quality stylized 3D render of a clear, translucent glass skeleton wearing black-rimmed glasses sitting at a wooden desk. The skeleton MUST be looking down at an open textbook and holding a yellow highlighter, actively highlighting a line of text. The scene MUST feature a warm gold desk lamp on the right side casting a cozy, yellow light that creates glossy reflections on the skeleton's surface. The desk is cluttered with a white coffee mug, a stack of hardcover books on the right, and scattered pens and pastel pink and yellow highlighters. The background MUST be a solid, soft pink wall. The overall aesthetic should be warm, studious, and visually soft. Do not include any text overlays or watermarks.
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 high-quality stylized 3D render of a clear, translucent glass skeleton wearing black-rimmed glasses sitting at a wooden desk. The skeleton MUST be looking down at an open textbook and holding a yellow highlighter, actively highlighting a line of text. The scene MUST feature a warm gold desk lamp on the right side casting a cozy, yellow light that creates glossy reflections on the skeleton's surface. The desk is cluttered with a white coffee mug, a stack of hardcover books on the right, and scattered pens and pastel pink and yellow highlighters. The background MUST be a solid, soft pink wall. The overall aesthetic should be warm, studious, and visually soft. Do not include any text overlays or watermarks."
}
JSON
A miniature isometric architectural diorama of [LANDMARK NAME], accurately reflecting its real-world structure and proportions, placed on a small floating base with subtle surrounding buildings and landscape elements inspired by [CITY / COUNTRY]. Realistic materials and natural textures, physically accurate stone, concrete, metal, and glass surfaces. True-to-life color palette based on the actual landmark, muted and realistic tones. Off-white studio background with soft, natural lighting, gentle shadows, and clean composition. High-detail, realistic yet refined 3D render, premium architectural model aesthetic, no people, no text.
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 miniature isometric architectural diorama of [LANDMARK NAME], accurately reflecting its real-world structure and proportions, placed on a small floating base with subtle surrounding buildings and landscape elements inspired by [CITY / COUNTRY]. Realistic materials and natural textures, physically accurate stone, concrete, metal, and glass surfaces. True-to-life color palette based on the actual landmark, muted and realistic tones. Off-white studio background with soft, natural lighting, gentle shadows, and clean composition. High-detail, realistic yet refined 3D render, premium architectural model aesthetic, no people, no text."
}
JSON
Abstract liquid typography spelling "text", thick transparent water-gel material, hyper realistic refraction and subtle caustics, realistic surface tension, sculpted droplet forms merged into smooth letter curves, glossy highlights, micro bubbles inside the gel, soft contact shadows on a pure white seamless background, scattered water droplets on the surface with sharp specular reflections, studio lighting, crisp photorealistic 3D render, macro detail, sharp focus, 8k, 1:1, no watermark, no extra text
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": "Abstract liquid typography spelling \"text\", thick transparent water-gel material, hyper realistic refraction and subtle caustics, realistic surface tension, sculpted droplet forms merged into smooth letter curves, glossy highlights, micro bubbles inside the gel, soft contact shadows on a pure white seamless background, scattered water droplets on the surface with sharp specular reflections, studio lighting, crisp photorealistic 3D render, macro detail, sharp focus, 8k, 1:1, no watermark, no extra text"
}
JSON
Using the provided reference_image as the primary source for identity, clothing colors, and visual attributes, create a full-body 3D stylized anthropomorphic cartoon version of the character. Preserve facial structure, body proportions, silhouette, and distinctive traits exactly as in the reference_image. The outfit must match the clothing colors from the reference_image. Extract and apply the exact dominant and secondary colors from the reference_image to the hoodie, cargo pants, and sneakers. Do not introduce new colors. Do not default to orange or neon green unless they exist in the reference_image. Modern streetwear styling is allowed, but color palette must strictly follow the reference_image. Confident relaxed pose with hands in pockets. Minimal studio background using the dominant background color sampled from the reference_image, or a harmonized tone derived from it. Soft studio lighting, smooth shadows, high-detail fabric texture, Pixar-quality 3D render, ultra-clean composition, centered framing, 8K resolution. Add enforcement: “Strict color adherence to reference_image. No automatic color substitution.
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": "Using the provided reference_image as the primary source for identity, clothing colors, and visual attributes, create a full-body 3D stylized anthropomorphic cartoon version of the character. Preserve facial structure, body proportions, silhouette, and distinctive traits exactly as in the reference_image. The outfit must match the clothing colors from the reference_image. Extract and apply the exact dominant and secondary colors from the reference_image to the hoodie, cargo pants, and sneakers. Do not introduce new colors. Do not default to orange or neon green unless they exist in the reference_image. Modern streetwear styling is allowed, but color palette must strictly follow the reference_image. Confident relaxed pose with hands in pockets. Minimal studio background using the dominant background color sampled from the reference_image, or a harmonized tone derived from it. Soft studio lighting, smooth shadows, high-detail fabric texture, Pixar-quality 3D render, ultra-clean composition, centered framing, 8K resolution. Add enforcement: “Strict color adherence to reference_image. No automatic color substitution."
}
JSON
Create a hyperrealistic, surreal spherical panorama of [CITY NAME], with its most iconic landmarks and architecture seamlessly curving around the top of a planet-like surface, forming a cohesive miniature world. Integrate sleek, modern 3D typography spelling “[CITY NAME]” naturally into the urban landscape, harmonized with the environment rather than floating unnaturally. The scene is viewed from a top-down, orbiting perspective, emphasizing the tiny-planet effect and spherical distortion while maintaining architectural clarity. Soft, natural daylight filters through a partly cloudy sky, casting gentle, realistic shadows across lush greenery, streets, trees, and buildings. The background transitions smoothly into a dramatic, swirling sky, enhancing the surreal atmosphere without overpowering the city. Use a natural yet vivid color palette — crisp greens, soft blues, and muted earth tones appropriate to [CITY NAME]. Render in a polished, photorealistic style with fine architectural detail, realistic textures, atmospheric depth, and high visual fidelity.
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 hyperrealistic, surreal spherical panorama of [CITY NAME], with its most iconic landmarks and architecture seamlessly curving around the top of a planet-like surface, forming a cohesive miniature world. Integrate sleek, modern 3D typography spelling “[CITY NAME]” naturally into the urban landscape, harmonized with the environment rather than floating unnaturally. The scene is viewed from a top-down, orbiting perspective, emphasizing the tiny-planet effect and spherical distortion while maintaining architectural clarity. Soft, natural daylight filters through a partly cloudy sky, casting gentle, realistic shadows across lush greenery, streets, trees, and buildings. The background transitions smoothly into a dramatic, swirling sky, enhancing the surreal atmosphere without overpowering the city. Use a natural yet vivid color palette — crisp greens, soft blues, and muted earth tones appropriate to [CITY NAME]. Render in a polished, photorealistic style with fine architectural detail, realistic textures, atmospheric depth, and high visual fidelity."
}
JSON
Create a super cute, hyper-realistic 3D render of a toddler girl who is a younger version of the person in the provided reference photo. The facial structure must strongly match the reference image. Accurately replicate the exact eye shape, eye color, skin tone, lip shape, nose structure, cheek fullness, eyebrow shape, and overall facial proportions. The toddler version should clearly resemble the same person at a younger age while maintaining realistic childlike softness and rounded features. If any accessory (such as an earring or similar detail) appears in the reference image, replicate it accurately in size, colour, and placement. Expression: Distinctly grumpy and pouty. Chin resting on her left palm. One eye slightly squinted in mild annoyance. Eyebrows gently furrowed. Lips pushed forward in a stubborn pout. Expression must feel natural and emotionally believable, not exaggerated. Hair: Hairstyle should be adapted from the reference image while keeping it toddler-appropriate. Styled in a messy high bun with soft, natural baby hair strands framing the face. Outfit: White short-sleeve t-shirt under classic blue denim overalls with visible stitching and metal clasps. Pose & Background: Sitting cross-legged on a clean white studio background. Feet slightly angled toward the camera. Balanced composition with full body visible. Style & Quality: Ultra-detailed Pixar/Disney-inspired 3D animation aesthetic. Professional CGI rendering. 1:1 aspect ratio. 8K resolution. Sharp focus. Cinematic studio lighting with soft subsurface scattering on the skin. Smooth textures, realistic fabric physics, soft global illumination, and natural shadow falloff.
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 super cute, hyper-realistic 3D render of a toddler girl who is a younger version of the person in the provided reference photo. The facial structure must strongly match the reference image. Accurately replicate the exact eye shape, eye color, skin tone, lip shape, nose structure, cheek fullness, eyebrow shape, and overall facial proportions. The toddler version should clearly resemble the same person at a younger age while maintaining realistic childlike softness and rounded features. If any accessory (such as an earring or similar detail) appears in the reference image, replicate it accurately in size, colour, and placement. Expression: Distinctly grumpy and pouty. Chin resting on her left palm. One eye slightly squinted in mild annoyance. Eyebrows gently furrowed. Lips pushed forward in a stubborn pout. Expression must feel natural and emotionally believable, not exaggerated. Hair: Hairstyle should be adapted from the reference image while keeping it toddler-appropriate. Styled in a messy high bun with soft, natural baby hair strands framing the face. Outfit: White short-sleeve t-shirt under classic blue denim overalls with visible stitching and metal clasps. Pose & Background: Sitting cross-legged on a clean white studio background. Feet slightly angled toward the camera. Balanced composition with full body visible. Style & Quality: Ultra-detailed Pixar/Disney-inspired 3D animation aesthetic. Professional CGI rendering. 1:1 aspect ratio. 8K resolution. Sharp focus. Cinematic studio lighting with soft subsurface scattering on the skin. Smooth textures, realistic fabric physics, soft global illumination, and natural shadow falloff."
}
JSON
A Realistic First Person (Pov) Selfie Taken With An Outside Arm, In The Same Clothes As In The Uploaded Photo. Close-up Of Me Hugging Tom, The Cartoon Gray Cat From Tom And Jerry, With A Small Smile (Jerry Can Be Looking Out Of My Shoulder Or My Pocket). Photorealistic Environment: Studio Set, Office Interior, Warm Light, Props, Spotlights And Cables In The Background. Tom Is A Strongly Stylized Toon 3d: Cel-shading, Multi-proportions, Clear Contour, No Realistic Fur, Not Live-action. Organic: Zoom To The Chest, Contact Of Hugs, Single Light, Natural Shadows. 4k.natural shadows. 4k.
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 Realistic First Person (Pov) Selfie Taken With An Outside Arm, In The Same Clothes As In The Uploaded Photo. Close-up Of Me Hugging Tom, The Cartoon Gray Cat From Tom And Jerry, With A Small Smile (Jerry Can Be Looking Out Of My Shoulder Or My Pocket). Photorealistic Environment: Studio Set, Office Interior, Warm Light, Props, Spotlights And Cables In The Background. Tom Is A Strongly Stylized Toon 3d: Cel-shading, Multi-proportions, Clear Contour, No Realistic Fur, Not Live-action. Organic: Zoom To The Chest, Contact Of Hugs, Single Light, Natural Shadows. 4k.natural shadows. 4k."
}
JSON
A hand-drawn treasure map on aged parchment, with the adventure erupting into three-dimensional quest. {STARTING_POINT} rises at the map's edge with {DEPARTURE_SCENE}, the dotted path becomes an actual trail traversing {TERRAIN_1} with {DANGER_1}, passing {LANDMARK_1} where {OBSTACLE_1} awaits. {TERRAIN_2} features {WILDLIFE_1} and {ENVIRONMENTAL_HAZARD}. The X marking the spot glows beneath {FINAL_LOCATION}, treasure partially visible, {GUARDIAN_ELEMENT} protecting it. Miniature expedition party frozen mid-journey at various points along the route. Torn edges of the map become cliffs. Coffee stains become lakes. Burn marks become scorched earth from battles past. Candlelight flicker, adventure novel lighting, 8K, the map as the story it promises.
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 hand-drawn treasure map on aged parchment, with the adventure erupting into three-dimensional quest. {STARTING_POINT} rises at the map's edge with {DEPARTURE_SCENE}, the dotted path becomes an actual trail traversing {TERRAIN_1} with {DANGER_1}, passing {LANDMARK_1} where {OBSTACLE_1} awaits. {TERRAIN_2} features {WILDLIFE_1} and {ENVIRONMENTAL_HAZARD}. The X marking the spot glows beneath {FINAL_LOCATION}, treasure partially visible, {GUARDIAN_ELEMENT} protecting it. Miniature expedition party frozen mid-journey at various points along the route. Torn edges of the map become cliffs. Coffee stains become lakes. Burn marks become scorched earth from battles past. Candlelight flicker, adventure novel lighting, 8K, the map as the story it promises."
}
JSON
Use a user-uploaded image as the source and convert the person into a stylized 3D character while preserving identity, facial structure, pose, hairstyle, clothing, and overall composition exactly as shown in the photo. The result should clearly resemble the real person. The visual style is a stylized 3D character with a soft minimal cartoon 3D aesthetic, inspired by Pixar-like visuals but more minimal, toy-figure renders, and clean product-style character design. The balance should favor stylization over realism without changing the person’s real-world appearance. Skin should appear as smooth matte plastic with a soft, uniform texture and gentle subsurface scattering. Facial features should remain faithful to the original image while being simplified in form. The expression should stay neutral and natural to the source photo. Lighting should be clean and controlled, similar to a studio softbox setup, with very soft shadows, low contrast, and subtle highlights. The background should be a solid [BACKGROUND COLOR] with no gradient. The camera should feel front-facing with a medium close-up framing, similar to a 50mm lens, with no distortion. Output quality should be high resolution with clean edges, no noise, strong style consistency, and a clearly non-photorealistic finish.
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": "Use a user-uploaded image as the source and convert the person into a stylized 3D character while preserving identity, facial structure, pose, hairstyle, clothing, and overall composition exactly as shown in the photo. The result should clearly resemble the real person. The visual style is a stylized 3D character with a soft minimal cartoon 3D aesthetic, inspired by Pixar-like visuals but more minimal, toy-figure renders, and clean product-style character design. The balance should favor stylization over realism without changing the person’s real-world appearance. Skin should appear as smooth matte plastic with a soft, uniform texture and gentle subsurface scattering. Facial features should remain faithful to the original image while being simplified in form. The expression should stay neutral and natural to the source photo. Lighting should be clean and controlled, similar to a studio softbox setup, with very soft shadows, low contrast, and subtle highlights. The background should be a solid [BACKGROUND COLOR] with no gradient. The camera should feel front-facing with a medium close-up framing, similar to a 50mm lens, with no distortion. Output quality should be high resolution with clean edges, no noise, strong style consistency, and a clearly non-photorealistic finish."
}
JSON
Create a high-quality 3D metallic typography composition of the title [MOVIE / SERIES NAME], set against a dark, textured background that reflects the tone, genre, and emotional atmosphere of the story, delivering a cinematic, premium visual impact. Each individual letter is sculpted as a cinematic form, seamlessly merging a different iconic scene from the movie or series into the letter itself. Scenes are translated into architectural elements, environments, characters, props, lighting, and atmospheric details, transformed into elegant, readable letterforms rather than literal collages. Every letter acts as a mini visual narrative, instantly recognizable to fans, while no two letters repeat the same scene or story moment. The full title feels cohesive, balanced, and unified as a single artwork. The typography is rendered in polished metallic materials (gold, silver, steel, or [COLOR]), featuring realistic reflections, fine engravings, and subtle surface wear for cinematic authenticity. Dramatic studio lighting with soft rim highlights and deep shadows enhances depth, scale, and mood, blending seamlessly with the embedded scenes. Ultra-sharp focus, premium 3D render quality, cinematic depth of field, luxury title-card aesthetic, ultra-high resolution. No cartoon style, no flat illustration — pure cinematic realism with sculptural artistry.
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 high-quality 3D metallic typography composition of the title [MOVIE / SERIES NAME], set against a dark, textured background that reflects the tone, genre, and emotional atmosphere of the story, delivering a cinematic, premium visual impact. Each individual letter is sculpted as a cinematic form, seamlessly merging a different iconic scene from the movie or series into the letter itself. Scenes are translated into architectural elements, environments, characters, props, lighting, and atmospheric details, transformed into elegant, readable letterforms rather than literal collages. Every letter acts as a mini visual narrative, instantly recognizable to fans, while no two letters repeat the same scene or story moment. The full title feels cohesive, balanced, and unified as a single artwork. The typography is rendered in polished metallic materials (gold, silver, steel, or [COLOR]), featuring realistic reflections, fine engravings, and subtle surface wear for cinematic authenticity. Dramatic studio lighting with soft rim highlights and deep shadows enhances depth, scale, and mood, blending seamlessly with the embedded scenes. Ultra-sharp focus, premium 3D render quality, cinematic depth of field, luxury title-card aesthetic, ultra-high resolution. No cartoon style, no flat illustration — pure cinematic realism with sculptural artistry."
}
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.