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
A cute 3D chibi-style character leaning against a parked mini chibi Jeep, wearing a clean monochrome outfit: plain t-shirt, straight-fit pants, and minimalist sneakers. Holding a takeaway coffee cup, relaxed confident smile. Big head, expressive eyes, modern fade haircut. Cozy café courtyard with wooden chairs, warm sunlight, soft depth of field, Pixar-quality 3D render, playful yet premium aesthetic, square aspect rat
Create a 45° top-down isometric miniature 3D diorama of [SCENE], including all key objects and tiny stylized people interacting naturally with the environment. Composition: •Include all relevant props, furniture, or items that make the scene recognizable. •Tiny characters can sit, stand, walk, or interact with objects as appropriate. •Soft realistic lighting, gentle shadows, subtle textures, minimal background. •Maintain consistent scale, camera angle, perspective, and style. Visual style: clean, editorial Apple-UI aesthetic, bright yet soft colors, ultra-crisp 3D textures. Background: solid color Crisp White Output: 1080×1080, ultra-crisp, social-feed optimized, 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": "Create a 45° top-down isometric miniature 3D diorama of [SCENE], including all key objects and tiny stylized people interacting naturally with the environment. Composition: •Include all relevant props, furniture, or items that make the scene recognizable. •Tiny characters can sit, stand, walk, or interact with objects as appropriate. •Soft realistic lighting, gentle shadows, subtle textures, minimal background. •Maintain consistent scale, camera angle, perspective, and style. Visual style: clean, editorial Apple-UI aesthetic, bright yet soft colors, ultra-crisp 3D textures. Background: solid color Crisp White Output: 1080×1080, ultra-crisp, social-feed optimized, no watermark."
}
JSON
[PERSONE]. Act as a Creative Director and Master of Visual Metaphor. PHASE 1: DYNAMIC ARCHETYPE LOGIC. Autonomously analyze the core essence of [PERSONE] and assign them a "High-Status Sovereign" role: - If the character is a scientist/intellectual: Depict as a "Grand Archivist" in heavy velvet robes with celestial instruments. - If the character is a rebel/anti-hero: Depict as a "Wasteland Prophet" in deconstructed, layered streetwear and scavenged textures. - If the character is royalty/leader: Depict as a "Divine Monarch" in stiff, ornamental ceremonial attire. - Maintain the stoic, iconographic pose from the reference. PHASE 2: ART STYLE & INK (THE REFERENCE LOOK). Strictly follow the "Neo-Traditional Etching" style. - Bold black ink outlines, intricate cross-hatching, and stippling for shadows. - Color Palette: Deep Ochre, Faded Teal, Jet Black, and Bone White background. PHASE 3: DYNAMIC TYPOGRAPHY. - The massive Gothic/Blackletter halo behind the subject MUST explicitly spell out the name "[PERSONE]". - The font style should adapt to the archetype (e.g., sharp and aggressive for rebels, elegant and structured for scholars). TECH SPECS: 2D flat illustration, white background, ink-bleed effects, high contrast, sharp line-work.
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": "[PERSONE]. Act as a Creative Director and Master of Visual Metaphor. PHASE 1: DYNAMIC ARCHETYPE LOGIC. Autonomously analyze the core essence of [PERSONE] and assign them a \"High-Status Sovereign\" role: - If the character is a scientist/intellectual: Depict as a \"Grand Archivist\" in heavy velvet robes with celestial instruments. - If the character is a rebel/anti-hero: Depict as a \"Wasteland Prophet\" in deconstructed, layered streetwear and scavenged textures. - If the character is royalty/leader: Depict as a \"Divine Monarch\" in stiff, ornamental ceremonial attire. - Maintain the stoic, iconographic pose from the reference. PHASE 2: ART STYLE & INK (THE REFERENCE LOOK). Strictly follow the \"Neo-Traditional Etching\" style. - Bold black ink outlines, intricate cross-hatching, and stippling for shadows. - Color Palette: Deep Ochre, Faded Teal, Jet Black, and Bone White background. PHASE 3: DYNAMIC TYPOGRAPHY. - The massive Gothic/Blackletter halo behind the subject MUST explicitly spell out the name \"[PERSONE]\". - The font style should adapt to the archetype (e.g., sharp and aggressive for rebels, elegant and structured for scholars). TECH SPECS: 2D flat illustration, white background, ink-bleed effects, high contrast, sharp line-work."
}
JSON
Hyper-realistic 3D illustration of Albert Einstein emerging from the pages of a sketchbook drawing, blending a graphite illustration with a lifelike 3D figure. Einstein has his iconic wild white hair, thick moustache, and thoughtful expression, wearing a classic brown tweed coat and white shirt. The open sketchbook lies on a worn wooden artist desk inside a sunlit studio. The pages display a detailed graphite drawing of Albert Einstein, but the paper is dramatically torn and curling outward where Einstein pushes through, transitioning from a flat pencil drawing into a fully rendered 3D figure stepping into reality. One of Einstein’s hands grips the torn edge of the paper while his other arm extends naturally outside the sketchbook, resting on the wooden desk as if stabilizing himself after stepping out of the drawing. His face shows curiosity and wonder, as if discovering the real world. A realistic human hand holding a traditional yellow wooden pencil appears in the foreground near the drawing, suggesting the artist has just finished sketching him moments before he came alive. Around the desk are pencil shavings, a large white eraser, graphite pencils, scattered sketches, paintbrushes, and glass jars filled with art tools. Warm sunlight from a large window illuminates the studio, casting soft shadows and highlighting the textures of paper fibers, graphite shading, wood grain, and skin details. Ultra-realistic rendering, cinematic lighting, high resolution, extremely detailed.
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 3D illustration of Albert Einstein emerging from the pages of a sketchbook drawing, blending a graphite illustration with a lifelike 3D figure. Einstein has his iconic wild white hair, thick moustache, and thoughtful expression, wearing a classic brown tweed coat and white shirt. The open sketchbook lies on a worn wooden artist desk inside a sunlit studio. The pages display a detailed graphite drawing of Albert Einstein, but the paper is dramatically torn and curling outward where Einstein pushes through, transitioning from a flat pencil drawing into a fully rendered 3D figure stepping into reality. One of Einstein’s hands grips the torn edge of the paper while his other arm extends naturally outside the sketchbook, resting on the wooden desk as if stabilizing himself after stepping out of the drawing. His face shows curiosity and wonder, as if discovering the real world. A realistic human hand holding a traditional yellow wooden pencil appears in the foreground near the drawing, suggesting the artist has just finished sketching him moments before he came alive. Around the desk are pencil shavings, a large white eraser, graphite pencils, scattered sketches, paintbrushes, and glass jars filled with art tools. Warm sunlight from a large window illuminates the studio, casting soft shadows and highlighting the textures of paper fibers, graphite shading, wood grain, and skin details. Ultra-realistic rendering, cinematic lighting, high resolution, extremely detailed."
}
JSON
A surreal, high-resolution conceptual image depicting the transition from winter to spring. In the center, a large, realistic metal zipper is unzipped on a snow-covered landscape, revealing a vibrant, lush meadow of green grass and blooming pink spring flowers underneath. The surrounding area is a winter forest with frost-covered trees and deep snow. The sky above is a magical blend of day and night, featuring a bright, radiant sun with lens flares on the left and a deep blue twilight sky filled with sparkling stars on the right. The lighting is cinematic, highlighting the contrast between the cold, icy texture of the snow and the warm, lively colors of the spring meadow.
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 surreal, high-resolution conceptual image depicting the transition from winter to spring. In the center, a large, realistic metal zipper is unzipped on a snow-covered landscape, revealing a vibrant, lush meadow of green grass and blooming pink spring flowers underneath. The surrounding area is a winter forest with frost-covered trees and deep snow. The sky above is a magical blend of day and night, featuring a bright, radiant sun with lens flares on the left and a deep blue twilight sky filled with sparkling stars on the right. The lighting is cinematic, highlighting the contrast between the cold, icy texture of the snow and the warm, lively colors of the spring meadow."
}
JSON
A hyper-detailed 3D frosted translucent glass version of the attached product packaging, maintaining accurate proportions and original colors, semi-transparent material with realistic refraction and soft internal glow, smooth softened corners, subtle surface texture, embossed branding details integrated into the glass, centered on a light gray background, floating gently with a soft shadow below, natural studio lighting, clean minimal layout, high-end product visualization 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 hyper-detailed 3D frosted translucent glass version of the attached product packaging, maintaining accurate proportions and original colors, semi-transparent material with realistic refraction and soft internal glow, smooth softened corners, subtle surface texture, embossed branding details integrated into the glass, centered on a light gray background, floating gently with a soft shadow below, natural studio lighting, clean minimal layout, high-end product visualization style"
}
JSON
\Create an isometric miniature 3D diorama representing the iconic architecture of [COUNTRY NAME] through [FAMOUS STRUCTURE]. Use a 45° top-down view. Apply clean soft textures and realistic PBR materials. Lighting feels balanced and natural. The raised base includes nearby streets, landscape features, and cultural details linked to the structure. Add tiny stylized locals and visitors with heavy facial details. Background stays solid [BACKGROUND COLOR]. Top center text shows [COUNTRY NAME] in bold. Second line shows [STRUCTURE NAME]. Place a minimal architecture icon below. Text color adjusts for 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 an isometric miniature 3D diorama representing the iconic architecture of [COUNTRY NAME] through [FAMOUS STRUCTURE]. Use a 45° top-down view. Apply clean soft textures and realistic PBR materials. Lighting feels balanced and natural. The raised base includes nearby streets, landscape features, and cultural details linked to the structure. Add tiny stylized locals and visitors with heavy facial details. Background stays solid [BACKGROUND COLOR]. Top center text shows [COUNTRY NAME] in bold. Second line shows [STRUCTURE NAME]. Place a minimal architecture icon below. Text color adjusts for contrast."
}
JSON
ME AND MY LITTLE 3D CHIBI IN THE OFFICE Ultra-realistic cinematic portrait of an adult person, with the face fully visible, natural human skin texture with pores and subtle imperfections, and realistic hair strands. The real person is seated in a dental chair in a pink dental office, holding a small 3D miniature of themselves, delicately sitting with crossed legs in a relaxed pose on the palm of one hand. 4:3 horizontal ratio. Features dental office attire with a rose-colored coat and holding a dental mirror in hand. The real person looks at the miniature with clear surprise and slight amusement, raised eyebrows, a soft smile, and expressive eyes. The facial expression appears spontaneous and authentic. The miniature closely resembles the real person in facial structure, hairstyle, and clothing, but rendered in a soft, high-quality 3D chibi style. The miniature has a funny and exaggerated facial expression, lively eyes, and playful moving arms and legs. The stylization is clean and modern, not like a toy, doll, or artificial figure. Both characters wear matching outfits: medium distressed jeans, rose-colored coat with 3/4 bell sleeves finished with lace on cuffs and hems, embroidered with white lace and golden center details, and light white sneakers. Hair according to reference. Makeup: luminous and well-defined skin, light rosy blush, intense eyeshadow in neutral tones, black mascara on eyelashes, and matte pink lips. The scale difference between the realistic woman and the 3D chibi figure is obvious and visually amusing. The background is a realistic office scene with white cabinets containing painting and creative items, a white desk, and a plastic swivel chair, with slight blur and strong depth of field. Professional cinematic lighting with clear separation of objects, soft highlights on the skin, and subtle rim light around both figures. Ultra-detailed textures for the real person. Clean 3D textures with a realistic style for the miniature. Balanced between realism and humor. No surreal distortions.
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": "ME AND MY LITTLE 3D CHIBI IN THE OFFICE Ultra-realistic cinematic portrait of an adult person, with the face fully visible, natural human skin texture with pores and subtle imperfections, and realistic hair strands. The real person is seated in a dental chair in a pink dental office, holding a small 3D miniature of themselves, delicately sitting with crossed legs in a relaxed pose on the palm of one hand. 4:3 horizontal ratio. Features dental office attire with a rose-colored coat and holding a dental mirror in hand. The real person looks at the miniature with clear surprise and slight amusement, raised eyebrows, a soft smile, and expressive eyes. The facial expression appears spontaneous and authentic. The miniature closely resembles the real person in facial structure, hairstyle, and clothing, but rendered in a soft, high-quality 3D chibi style. The miniature has a funny and exaggerated facial expression, lively eyes, and playful moving arms and legs. The stylization is clean and modern, not like a toy, doll, or artificial figure. Both characters wear matching outfits: medium distressed jeans, rose-colored coat with 3/4 bell sleeves finished with lace on cuffs and hems, embroidered with white lace and golden center details, and light white sneakers. Hair according to reference. Makeup: luminous and well-defined skin, light rosy blush, intense eyeshadow in neutral tones, black mascara on eyelashes, and matte pink lips. The scale difference between the realistic woman and the 3D chibi figure is obvious and visually amusing. The background is a realistic office scene with white cabinets containing painting and creative items, a white desk, and a plastic swivel chair, with slight blur and strong depth of field. Professional cinematic lighting with clear separation of objects, soft highlights on the skin, and subtle rim light around both figures. Ultra-detailed textures for the real person. Clean 3D textures with a realistic style for the miniature. Balanced between realism and humor. No surreal distortions."
}
JSON
Create an image in 4:5 ratio, with hyper-realistic aesthetics applied to a premium cartoon/cinematographic manga style, combining extreme realism with high-impact illustrated visual language. The face must be identical to that of the photo sent in 103%, maintaining absolute tidelity the original tactical identity: bone structure, skull shape, proportions, intense expression, eyebrows, eyes, nose, mouth, jaw, mustache, hair and capillary volume. No aesthetic change, identity change, artificial smoothing or stylization that mischaracterizes the face. Male character reference pose. Stroke style inspired by high-level realistic cartoon, with well-defined volumes, deep shadows and clean finish. costume: referenced image, with realistic fabric texture, natural folds and precise lighting. Background composed of black and white comic panels, organized in multiple narrative frames, creating depth, visual context and sensation of an expanded universe. The panels should look like action scenes and graphic narrative, with varied perspective and dynamic composition. Professional cinematic lighting, with soft front main light and dramatic contrast, precise face enhancements, controlled shadows, subtle depth of field, extreme sharpness, visible microdetails, premium rendering finish. Maximum quality, high-budget editorial illustration appearance, full focus on the face, strong visual impact, Realism 333%, no readable texts, no watermarks, no distortions, no artifacts.
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 image in 4:5 ratio, with hyper-realistic aesthetics applied to a premium cartoon/cinematographic manga style, combining extreme realism with high-impact illustrated visual language. The face must be identical to that of the photo sent in 103%, maintaining absolute tidelity the original tactical identity: bone structure, skull shape, proportions, intense expression, eyebrows, eyes, nose, mouth, jaw, mustache, hair and capillary volume. No aesthetic change, identity change, artificial smoothing or stylization that mischaracterizes the face. Male character reference pose. Stroke style inspired by high-level realistic cartoon, with well-defined volumes, deep shadows and clean finish. costume: referenced image, with realistic fabric texture, natural folds and precise lighting. Background composed of black and white comic panels, organized in multiple narrative frames, creating depth, visual context and sensation of an expanded universe. The panels should look like action scenes and graphic narrative, with varied perspective and dynamic composition. Professional cinematic lighting, with soft front main light and dramatic contrast, precise face enhancements, controlled shadows, subtle depth of field, extreme sharpness, visible microdetails, premium rendering finish. Maximum quality, high-budget editorial illustration appearance, full focus on the face, strong visual impact, Realism 333%, no readable texts, no watermarks, no distortions, no artifacts."
}
JSON
Create a 3D isometric miniature diorama showcasing the productivity system [SYSTEM NAME]. Angle remains between 35–45°. Materials feel modern and structured with realistic PBR textures. Lighting is soft but focused. The raised base is divided into functional zones such as planning, execution, tracking, and review. Use connecting paths or arrows to show workflow. Tiny stylized professionals interact with desks, boards, or devices. With heavy facial details. Background remains solid [BACKGROUND COLOR]. Top center shows [SYSTEM NAME] in bold. Below it add a short benefit-focused subtitle. Place a minimal productivity icon underneath. Text automatically adapts.”
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 3D isometric miniature diorama showcasing the productivity system [SYSTEM NAME]. Angle remains between 35–45°. Materials feel modern and structured with realistic PBR textures. Lighting is soft but focused. The raised base is divided into functional zones such as planning, execution, tracking, and review. Use connecting paths or arrows to show workflow. Tiny stylized professionals interact with desks, boards, or devices. With heavy facial details. Background remains solid [BACKGROUND COLOR]. Top center shows [SYSTEM NAME] in bold. Below it add a short benefit-focused subtitle. Place a minimal productivity icon underneath. Text automatically adapts.”"
}
JSON
Create a high-contrast digital comic-style illustration of [PERSON] based strictly on the provided reference image. STRICT IDENTITY LOCK: ∙Preserve exact facial bone structure ∙Preserve exact skin tone ∙Preserve beard density and shape (if applicable) ∙Preserve tattoo placement and design (if visible) ∙Do NOT stylize, redesign, beautify, exaggerate, or cartoonify the face ∙The person must remain clearly recognizable POSE: Upper-body focused composition. Keep the pose exactly the same as in the reference image. STYLE: ∙Bold black ink outlines ∙Strong dynamic line variation ∙Clean comic-book contouring ∙Cross-hatching shading technique (visible hand-drawn hatch lines) ∙No soft airbrush shading ∙No smooth gradient blending ∙Hard shadow planes ∙Graphic novel illustration style COLOR SYSTEM: ∙Flat saturated color blocks ∙High contrast between light and shadow ∙No photorealistic rendering ∙No painterly brush strokes ∙Slight warm skin highlights ∙Clothing colors must match the reference image exactly TEXTURE: ∙Subtle paper grain texture ∙Ink illustration feel ∙Hand-drawn motion lines around arms and shoulders BACKGROUND: ∙Solid flat background color complementary to the subject’s outfit or chosen palette ∙No environment ∙No depth blur ∙Minimalistic ∙Slight grain texture allowed ENERGY DETAILS: ∙Hand-drawn motion lines indicating movement ∙Subtle sketch swirls around the subject ∙Dynamic comic vibration lines LIGHTING: ∙Strong directional light from upper side ∙Hard comic-style shadow edges ∙Deep contrast under arms and jawline ∙Defined muscle contour shadows COMPOSITION: ∙Vertical 4:5 ratio (Instagram optimized) ∙Subject centered ∙Upper torso dominant ∙Clean negative space around figure QUALITY: ∙High resolution ∙Clean line clarity ∙Sharp edges ∙No blur ∙No AI artifact distortion
A high-definition, realistic 3D social media profile picture style. The image features the young English girl with sleek, straight white hair and a clear, detailed face. She is wearing a coordinated Nike brand outfit consisting of a premium black and red Nike tracksuit with a visible swoosh logo. On her feet are classic red, white, and black Nike Air Jordan sneakers. She is sitting on the edge of a white Instagram-style frame, with her legs and one sneaker 'popping out' of the bottom of the frame for a 3D effect. The background inside the frame shows her sitting on a long, perspective-heavy escalator in a dark, gritty subway tunnel filled with colorful graffiti. She is looking down at a smartphone in her hands. The lighting is cinematic, highlighting her white hair and the textures of the Nike fabric."
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-definition, realistic 3D social media profile picture style. The image features the young English girl with sleek, straight white hair and a clear, detailed face. She is wearing a coordinated Nike brand outfit consisting of a premium black and red Nike tracksuit with a visible swoosh logo. On her feet are classic red, white, and black Nike Air Jordan sneakers. She is sitting on the edge of a white Instagram-style frame, with her legs and one sneaker 'popping out' of the bottom of the frame for a 3D effect. The background inside the frame shows her sitting on a long, perspective-heavy escalator in a dark, gritty subway tunnel filled with colorful graffiti. She is looking down at a smartphone in her hands. The lighting is cinematic, highlighting her white hair and the textures of the Nike fabric.\""
}
JSON
An architectural floor plan of {BUILDING_TYPE} spread across a drafting table, with the spaces rising into inhabitable miniature. {ROOM_1} emerges with {FURNITURE_1} and {ACTIVITY_1} in progress, {ROOM_2} rises with {DESIGN_ELEMENT} and {HUMAN_MOMENT}, {ROOM_3} pushes up with {DETAIL_1} and {LIGHTING_1}. Walls exist as both lines and actual partitions simultaneously. Sight lines marked on the plan become actual views between spaces. The mechanical systems in the plan—HVAC, plumbing, electrical—pulse with invisible function. Human circulation patterns appear as ghosted movement trails. Architectural scale figures become actual tiny inhabitants living their tiny lives. Section cuts reveal vertical relationships. The architect's tools surround: scales, pencils, trace paper. Golden design studio light, the plan as promise and proof, 8K, architecture as life container.
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 floor plan of {BUILDING_TYPE} spread across a drafting table, with the spaces rising into inhabitable miniature. {ROOM_1} emerges with {FURNITURE_1} and {ACTIVITY_1} in progress, {ROOM_2} rises with {DESIGN_ELEMENT} and {HUMAN_MOMENT}, {ROOM_3} pushes up with {DETAIL_1} and {LIGHTING_1}. Walls exist as both lines and actual partitions simultaneously. Sight lines marked on the plan become actual views between spaces. The mechanical systems in the plan—HVAC, plumbing, electrical—pulse with invisible function. Human circulation patterns appear as ghosted movement trails. Architectural scale figures become actual tiny inhabitants living their tiny lives. Section cuts reveal vertical relationships. The architect's tools surround: scales, pencils, trace paper. Golden design studio light, the plan as promise and proof, 8K, architecture as life container."
}
JSON
Convert to hyper-realistic 3D CGI collectible figurine render. Physically-based rendering, octane render quality. Preserve the original character design, pose, and outfit exactly. Transform all surfaces into real-world materials: fabric with visible weave and drape, metal with wear, scratches and oxidation, synthetic matte skin. Pure white studio background, clean seamless white backdrop, soft diffused lighting with subtle rim light. No cel shading, no toon rendering. High-end statue/collectible photography aesthetic. Ultra detailed, 8K. Fix and reconstruct all hands and fingers with correct anatomy: natural finger count, proper joint articulation, realistic proportions, no fused or melted digits. Remove all 2D artifacts, compression glitches, and Midjourney inconsistencies. Ensure full anatomical coherence across the entire figure: symmetrical features, clean silhouette, no floating elements, no distorted limbs, no duplicated body parts. Hyper-detailed hair simulation: individual strand rendering, realistic hair clumping, natural flow and gravity, visible scalp at roots, micro flyaways, SSS translucency on hair tips. Every surface pushed to maximum realism: pore-level skin texture, fabric fiber micro-detail, specular highlights on every material, depth in shadows
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": "Convert to hyper-realistic 3D CGI collectible figurine render. Physically-based rendering, octane render quality. Preserve the original character design, pose, and outfit exactly. Transform all surfaces into real-world materials: fabric with visible weave and drape, metal with wear, scratches and oxidation, synthetic matte skin. Pure white studio background, clean seamless white backdrop, soft diffused lighting with subtle rim light. No cel shading, no toon rendering. High-end statue/collectible photography aesthetic. Ultra detailed, 8K. Fix and reconstruct all hands and fingers with correct anatomy: natural finger count, proper joint articulation, realistic proportions, no fused or melted digits. Remove all 2D artifacts, compression glitches, and Midjourney inconsistencies. Ensure full anatomical coherence across the entire figure: symmetrical features, clean silhouette, no floating elements, no distorted limbs, no duplicated body parts. Hyper-detailed hair simulation: individual strand rendering, realistic hair clumping, natural flow and gravity, visible scalp at roots, micro flyaways, SSS translucency on hair tips. Every surface pushed to maximum realism: pore-level skin texture, fabric fiber micro-detail, specular highlights on every material, depth in shadows"
}
JSON
convert anime characters into realistic human portraits Convert character into a photorealistic live-action portrait / fashion editorial photograph, modern cinematic style, high-fashion grade, punchy but natural contrast, refined filmic color science, subtle halation and lens bloom, controlled highlights, soft roll-off, realistic skin pores and texture, lifelike hair strands, premium fabric/material rendering, studio-quality lighting with natural depth, preserve the original camera framing and composition exactly, no text, no logo.
A cinematic studio portrait of a woman seated at a textured stone table against a muted warm gray background. She wears a dark brown satin blouse, subtle evening makeup, and softly layered shoulder-length hair. In front of her is a glass of cold brew coffee with ice and a metal straw. Placed beside it is a glossy 3D chibi figurine of the same woman, with a big rounded head, expressive eyes, soft blush cheeks, and simplified facial features, holding a miniature cold brew glass. The chibi has a high-quality collectible toy look with gentle reflections. Intimate evening café vibe, moody soft lighting, shallow depth of field, realistic human combined with stylized 3D character, cinematic and cozy, 1:1 aspect ratio.
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 studio portrait of a woman seated at a textured stone table against a muted warm gray background. She wears a dark brown satin blouse, subtle evening makeup, and softly layered shoulder-length hair. In front of her is a glass of cold brew coffee with ice and a metal straw. Placed beside it is a glossy 3D chibi figurine of the same woman, with a big rounded head, expressive eyes, soft blush cheeks, and simplified facial features, holding a miniature cold brew glass. The chibi has a high-quality collectible toy look with gentle reflections. Intimate evening café vibe, moody soft lighting, shallow depth of field, realistic human combined with stylized 3D character, cinematic and cozy, 1:1 aspect ratio."
}
JSON
She kneels in a pristine white studio, shot from a low mid angle with a slight upward tilt that emphasizes quiet dominance. She wears a Y2K inspired brown and olive raglan tee with a worn retro star logo reading sssap, paired with oversized distressed wide leg denim cargos and chunky black streetwear shoes. Her messy ponytail and loose strands frame a sharp, defiant gaze, softened by large black wired headphones adding a cyber edge. Soft diffused studio lighting reveals fabric texture and subtle shadows, while her provocative yet controlled expression channels indie sleaze mixed with Harajuku editorial rebellion.
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": "She kneels in a pristine white studio, shot from a low mid angle with a slight upward tilt that emphasizes quiet dominance. She wears a Y2K inspired brown and olive raglan tee with a worn retro star logo reading sssap, paired with oversized distressed wide leg denim cargos and chunky black streetwear shoes. Her messy ponytail and loose strands frame a sharp, defiant gaze, softened by large black wired headphones adding a cyber edge. Soft diffused studio lighting reveals fabric texture and subtle shadows, while her provocative yet controlled expression channels indie sleaze mixed with Harajuku editorial rebellion."
}
JSON
A [ORDINARY OBJECT] as a landmark on an epic journey, tiny [TRAVELERS] resting in its shadow after crossing vast distances visible behind them. Caravans, pack animals, exhausted families. The object marks the halfway point, or the border, or the promised destination. Graffiti and carvings from generations of previous travelers cover its surfaces. Offerings left at its base. Some travelers stay, building permanent settlement. Others push on. Golden hour lighting, dust from the journey still settling, the mundane as waypoint.
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 [ORDINARY OBJECT] as a landmark on an epic journey, tiny [TRAVELERS] resting in its shadow after crossing vast distances visible behind them. Caravans, pack animals, exhausted families. The object marks the halfway point, or the border, or the promised destination. Graffiti and carvings from generations of previous travelers cover its surfaces. Offerings left at its base. Some travelers stay, building permanent settlement. Others push on. Golden hour lighting, dust from the journey still settling, the mundane as waypoint."
}
JSON
A flat-lay collection of exactly 9 hyper-realistic 3D resin fridge magnets arranged on a plain matte white surface, themed around [COUNTRY]. At the very top center, a wide rectangular text magnet spells "COUNTRY" in bold 3D block letters colored in the nation's flag colors. Below it, 8 magnets are arranged in a loose 3-column grid: 3 iconic architectural landmarks as highly detailed sculpted miniature reliefs (cathedrals, towers, castles, monuments), 1 famous painting or portrait reproduced inside a gold ornate picture frame magnet, 1 traditional food dish and 1 drink (wine bottle + glass, or beer stein, etc.) as glossy ceramic sculpted magnets, 1 illustrated vintage-style map magnet of the country with city markers, and 1 additional cultural symbol or landmark. Each magnet has a slightly raised 3D sculpted look with soft drop shadows on the white surface beneath. Warm studio lighting from above, photorealistic product render, perfectly clean white background, top-down flat-lay angle, 4:5 aspect ratio.
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 flat-lay collection of exactly 9 hyper-realistic 3D resin fridge magnets arranged on a plain matte white surface, themed around [COUNTRY]. At the very top center, a wide rectangular text magnet spells \"COUNTRY\" in bold 3D block letters colored in the nation's flag colors. Below it, 8 magnets are arranged in a loose 3-column grid: 3 iconic architectural landmarks as highly detailed sculpted miniature reliefs (cathedrals, towers, castles, monuments), 1 famous painting or portrait reproduced inside a gold ornate picture frame magnet, 1 traditional food dish and 1 drink (wine bottle + glass, or beer stein, etc.) as glossy ceramic sculpted magnets, 1 illustrated vintage-style map magnet of the country with city markers, and 1 additional cultural symbol or landmark. Each magnet has a slightly raised 3D sculpted look with soft drop shadows on the white surface beneath. Warm studio lighting from above, photorealistic product render, perfectly clean white background, top-down flat-lay angle, 4:5 aspect ratio."
}
JSON
Create an infographic image of Mustang GTD combining a realistic photograph or photorealistic render of the object with technical annotation overlays placed directly on top. Use black ink–style line drawings and text (blue Mustang GTD ) on a pure white studio background. Include: •Key component labels •Internal cutaway or exploded-view outlines (where relevant) •Measurements, dimensions, and scale markers •Material callouts and quantities •Arrows indicating function, force, or flow (all the functions that comes with bugatti Chiron) •Simple schematic or sectional diagrams where applicable Place the title Mustang GTD inside a real technical annotation box in one corner. Style & layout rules: •The real object remains clearly visible beneath the annotations(no annotation on the real object) •Annotations look hand-sketched, technical, and architectural •Clean composition with balanced negative space •Educational, museum-exhibit / engineering-manual vibe Visual style: Minimal technical illustration aesthetic. Black linework layered over realistic imagery. Precise but slightly hand-drawn feel. Color palette: Pure white background. Black annotation lines and text only. No colors. Output: 1080 × 1080 resolution Ultra-crisp Social-feed optimized 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": "Create an infographic image of Mustang GTD combining a realistic photograph or photorealistic render of the object with technical annotation overlays placed directly on top. Use black ink–style line drawings and text (blue Mustang GTD ) on a pure white studio background. Include: •Key component labels •Internal cutaway or exploded-view outlines (where relevant) •Measurements, dimensions, and scale markers •Material callouts and quantities •Arrows indicating function, force, or flow (all the functions that comes with bugatti Chiron) •Simple schematic or sectional diagrams where applicable Place the title Mustang GTD inside a real technical annotation box in one corner. Style & layout rules: •The real object remains clearly visible beneath the annotations(no annotation on the real object) •Annotations look hand-sketched, technical, and architectural •Clean composition with balanced negative space •Educational, museum-exhibit / engineering-manual vibe Visual style: Minimal technical illustration aesthetic. Black linework layered over realistic imagery. Precise but slightly hand-drawn feel. Color palette: Pure white background. Black annotation lines and text only. No colors. Output: 1080 × 1080 resolution Ultra-crisp Social-feed optimized No watermark"
}
JSON
A cute, cinematic brand fantasy scene featuring a fluffy white teddy bear mascot emerging from a chilled soda Coca-Cola can, holding a colorful striped straw. The can is placed inside a glowing refrigerator filled with neatly stacked glass soda bottles. Soft neon lighting, pastel reflections, condensation droplets on metal, playful yet premium advertising style. Shallow depth of field, ultra-detailed fur texture, glossy highlights, vibrant red-and-white color pal-ette, whimsical mood, Pixar-level realism, stu-dio-quality lighting, high contrast, square composi-tion, 1080×1080, ultra-HD, commercial brand photog-raphy.
Create a collection of icons representing [Month] through objects, symbols, and moods. They belong together as a single cohesive theme. The background is pure white. Place the month name “[MONTH]” at the top center of the image as a minimal, balanced title, aligned symmetrically above the grid and visually integrated with the overall design. Icons are rendered in a colorful yet calm 3D style, with season-appropriate textures and atmospheric lighting that reflect the essence of [MONTH]. Maintain consistent proportions, materials, and visual language across all icons and the title.
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 collection of icons representing [Month] through objects, symbols, and moods. They belong together as a single cohesive theme. The background is pure white. Place the month name “[MONTH]” at the top center of the image as a minimal, balanced title, aligned symmetrically above the grid and visually integrated with the overall design. Icons are rendered in a colorful yet calm 3D style, with season-appropriate textures and atmospheric lighting that reflect the essence of [MONTH]. Maintain consistent proportions, materials, and visual language across all icons and the title."
}
JSON
Create a cinematic 3D typographic composition spelling [WORD / NAME], where each letter is sculpted from the personality, environment, and emotional arc of [CHARACTER / STORY]. Letters are formed using clothing textures, symbolic props, architecture, and lighting motifs tied to different moments of the narrative. No literal faces — identity is conveyed through silhouettes, posture, materials, and atmosphere. Use premium metallic or stone materials with subtle wear. Dark cinematic background, dramatic rim lighting, deep shadows, ultra-realistic render, film-title 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": "Create a cinematic 3D typographic composition spelling [WORD / NAME], where each letter is sculpted from the personality, environment, and emotional arc of [CHARACTER / STORY]. Letters are formed using clothing textures, symbolic props, architecture, and lighting motifs tied to different moments of the narrative. No literal faces — identity is conveyed through silhouettes, posture, materials, and atmosphere. Use premium metallic or stone materials with subtle wear. Dark cinematic background, dramatic rim lighting, deep shadows, ultra-realistic render, film-title quality."
}
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.