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
{ "image_generation_prompt": { "subject": { "description": "A photorealistic young woman with brown hair tied back in a ponytail, sitting on a stool.", "pose": "Sitting with one knee raised, hands clasped around her shin, looking slightly to the side with a calm, focused expression.", "clothing": { "top": "Beige t-shirt with a white Nike swoosh logo on the chest.", "bottoms": "Dark blue leggings with a small white swoosh logo on the thigh.", "footwear": "White athletic sneakers." } }, "composition": { "foreground_element": "A large, 3D-rendered white social media frame resembling an Instagram post, physically framing the subject.", "ui_details": { "header": { "profile_picture": "Profile picture of the woman", "username": "Maria", "follow_button": { "text": "FOLLOW", "color": "Blue" } }, "footer_icons": [ { "type": "like", "icon": "Heart", "color": "Red", "state": "Liked" }, { "type": "comment", "icon": "Comment bubble" }, { "type": "share", "icon": "Paper plane" }, { "type": "bookmark", "icon": "Bookmark" } ], "likes_count": 785, "caption": "Freedom isn’t found in comfort. It’s built in the quiet moments where discipline meets belief." } }, "environment": { "setting": "A dimly lit, atmospheric gym background.", "details": "Blurred gym equipment in the shadows, creating a strong depth of field." }, "style": { "visual_style": "3D realistic render using Unreal Engine 5, cinematic and high fidelity.", "lighting": { "subject": "Soft spotlight focused on the woman", "background": "Cool ambient lighting with subtle 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": "{ \"image_generation_prompt\": { \"subject\": { \"description\": \"A photorealistic young woman with brown hair tied back in a ponytail, sitting on a stool.\", \"pose\": \"Sitting with one knee raised, hands clasped around her shin, looking slightly to the side with a calm, focused expression.\", \"clothing\": { \"top\": \"Beige t-shirt with a white Nike swoosh logo on the chest.\", \"bottoms\": \"Dark blue leggings with a small white swoosh logo on the thigh.\", \"footwear\": \"White athletic sneakers.\" } }, \"composition\": { \"foreground_element\": \"A large, 3D-rendered white social media frame resembling an Instagram post, physically framing the subject.\", \"ui_details\": { \"header\": { \"profile_picture\": \"Profile picture of the woman\", \"username\": \"Maria\", \"follow_button\": { \"text\": \"FOLLOW\", \"color\": \"Blue\" } }, \"footer_icons\": [ { \"type\": \"like\", \"icon\": \"Heart\", \"color\": \"Red\", \"state\": \"Liked\" }, { \"type\": \"comment\", \"icon\": \"Comment bubble\" }, { \"type\": \"share\", \"icon\": \"Paper plane\" }, { \"type\": \"bookmark\", \"icon\": \"Bookmark\" } ], \"likes_count\": 785, \"caption\": \"Freedom isn’t found in comfort. It’s built in the quiet moments where discipline meets belief.\" } }, \"environment\": { \"setting\": \"A dimly lit, atmospheric gym background.\", \"details\": \"Blurred gym equipment in the shadows, creating a strong depth of field.\" }, \"style\": { \"visual_style\": \"3D realistic render using Unreal Engine 5, cinematic and high fidelity.\", \"lighting\": { \"subject\": \"Soft spotlight focused on the woman\", \"background\": \"Cool ambient lighting with subtle shadows\" } } } }"
}
JSON
A marque historian's documentation board for [VEHICLE] — [MODEL / VARIANT / YEAR]. Left section: factory documentation including original specification sheet, production line photographs, period advertising, and chassis number registry. Center section: technical illustration showing powertrain in phantom view, suspension geometry, aerodynamic annotations, and material callouts, surrounded by period racing results or ownership provenance. Right section: the vehicle in its defining environment, whether racing circuit, mountain pass, or boulevard, captured with period-appropriate color grading and motion. Visual style transitions from archival document cream through engineering-drawing precision to saturated automotive photography. Title block reading "[VEHICLE NAME] — CHASSIS NO. [NUMBER], [PROVENANCE SUMMARY]".
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 marque historian's documentation board for [VEHICLE] — [MODEL / VARIANT / YEAR]. Left section: factory documentation including original specification sheet, production line photographs, period advertising, and chassis number registry. Center section: technical illustration showing powertrain in phantom view, suspension geometry, aerodynamic annotations, and material callouts, surrounded by period racing results or ownership provenance. Right section: the vehicle in its defining environment, whether racing circuit, mountain pass, or boulevard, captured with period-appropriate color grading and motion. Visual style transitions from archival document cream through engineering-drawing precision to saturated automotive photography. Title block reading \"[VEHICLE NAME] — CHASSIS NO. [NUMBER], [PROVENANCE SUMMARY]\"."
}
JSON
A hyper-stylized, dynamic 3D head portrait floats against a vivid red background with soft volumetric clouds and seamless shading. Only the cartoonish 3D head appears, with no neck visible, and facial features closely matching the reference photo. The head is tilted and fills approximately 80% of the frame. The character displays a fierce, aggressive expression with a wide snarl, revealing teeth adorned with diamond-studded braces. Sharp, angular silver sunglasses with pointed frames fit the face precisely. Additional accessories include chrome earrings and a chunky silver chain necklace. Lighting is bold and metallic, combining strong rim lights from above and behind with a luminous frontal fill that sculpts facial contours and creates glossy skin highlights. The overall look features over-the-top glossy realism, exaggerated proportions, intense reflections, and a futuristic, high-energy aesthetic with partial overlap of elements to enhance depth and dramatic presence. Hyper-detailed 3D forms add vibrant, cinematic intensity and visual impact. 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": "A hyper-stylized, dynamic 3D head portrait floats against a vivid red background with soft volumetric clouds and seamless shading. Only the cartoonish 3D head appears, with no neck visible, and facial features closely matching the reference photo. The head is tilted and fills approximately 80% of the frame. The character displays a fierce, aggressive expression with a wide snarl, revealing teeth adorned with diamond-studded braces. Sharp, angular silver sunglasses with pointed frames fit the face precisely. Additional accessories include chrome earrings and a chunky silver chain necklace. Lighting is bold and metallic, combining strong rim lights from above and behind with a luminous frontal fill that sculpts facial contours and creates glossy skin highlights. The overall look features over-the-top glossy realism, exaggerated proportions, intense reflections, and a futuristic, high-energy aesthetic with partial overlap of elements to enhance depth and dramatic presence. Hyper-detailed 3D forms add vibrant, cinematic intensity and visual impact. Aspect ratio 4:5"
}
JSON
A hyper-detailed, origami-style version of a person, folded from high-quality paper with crisp, clean edges and a realistic paper texture. Intricate geometric folds capture the character’s iconic shape and expressions. Use the same color palette as the reference photo (no black). Place it on a clean studio surface with soft, natural shadows. A minimalist collectible art aesthetic; ultra-photorealistic; 8k, 1080×1080 square.
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, origami-style version of a person, folded from high-quality paper with crisp, clean edges and a realistic paper texture. Intricate geometric folds capture the character’s iconic shape and expressions. Use the same color palette as the reference photo (no black). Place it on a clean studio surface with soft, natural shadows. A minimalist collectible art aesthetic; ultra-photorealistic; 8k, 1080×1080 square."
}
JSON
Create an infographic image of [COUNTRY], combining a realistic photograph or photoreal render of the object with technical annotation overlays placed directly on top. Use black ink–style line drawings and text (technical pen / architectural sketch look) on a pure white studio background, including: •Key component labels •Internal cutaway or exploded-view outlines •Measurements, dimensions, and scale markers •Material callouts and quantities •Arrows indicating function, force, or flow (air, sound, power, pressure) •Simple schematic or sectional diagrams where relevant Include a small flag of the country in the top right corner. Place the title [COUNTRY] inside a hand-drawn technical annotation box in one corner. Style & layout rules: •The real object remains clearly visible beneath the annotations •Annotations feel sketched, technical, and architectural •Clean composition with balanced negative space •Educational, museum-exhibit / engineering-manual vibe Visual style: Minimal technical illustration aesthetic, black linework over realistic imagery, precise but slightly hand-drawn feel. Color palette: White background, black annotation lines and text only. No colors. 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 an infographic image of [COUNTRY], combining a realistic photograph or photoreal render of the object with technical annotation overlays placed directly on top. Use black ink–style line drawings and text (technical pen / architectural sketch look) on a pure white studio background, including: •Key component labels •Internal cutaway or exploded-view outlines •Measurements, dimensions, and scale markers •Material callouts and quantities •Arrows indicating function, force, or flow (air, sound, power, pressure) •Simple schematic or sectional diagrams where relevant Include a small flag of the country in the top right corner. Place the title [COUNTRY] inside a hand-drawn technical annotation box in one corner. Style & layout rules: •The real object remains clearly visible beneath the annotations •Annotations feel sketched, technical, and architectural •Clean composition with balanced negative space •Educational, museum-exhibit / engineering-manual vibe Visual style: Minimal technical illustration aesthetic, black linework over realistic imagery, precise but slightly hand-drawn feel. Color palette: White background, black annotation lines and text only. No colors. Output: 1080×1080, ultra-crisp, social-feed optimized, no watermark."
}
JSON
Create a head-and-shoulders Pixar-style 3D avatar of an edgy person based on the reference image with a black bob, purple hair streak, and a small nose ring. She has a defiant, playful expression, sticking her tongue out with wide, confident eyes while wearing a classic denim jacket. Isolated on a seamless white background, the render features flawless 3D skin and soft cinematic lighting for a clean, minimalist aesthetic.
curl -X POST https://runapi.ai/api/v1/nano_banana/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "nano-banana-2",
"prompt": "Create a head-and-shoulders Pixar-style 3D avatar of an edgy person based on the reference image with a black bob, purple hair streak, and a small nose ring. She has a defiant, playful expression, sticking her tongue out with wide, confident eyes while wearing a classic denim jacket. Isolated on a seamless white background, the render features flawless 3D skin and soft cinematic lighting for a clean, minimalist aesthetic."
}
JSON
A hyper-realistic 3D game guide infographic poster for [GAME]. The in-game world of [GAME] is rendered as a raised, textured terrain map floating on a clean light gray surface — the map shape and landscape must reflect the actual geography and visual aesthetic of [GAME] (urban, western, fantasy, island etc). Iconic in-game locations from [GAME] are placed as miniature 3D sculpted models at their correct in-game positions across the map — each one highly detailed, photorealistic and instantly recognizable to fans. Roads or paths connect key locations as white lines across the terrain. Around the map, floating 3D decorative props and items iconic to [GAME] are scattered on the light gray surface. The official logo of [GAME] is shown as a small detailed object in the upper right corner. Each major location has a bold black label on the map, and beside the map, each location has a neat checklist of its most iconic moments or activities associated with that place, in clean sans-serif typography. A large bold title at the top reads: “THE WORLD OF GAME” in black uppercase typography with [GAME] in heavy bold. The overall aesthetic is premium editorial — soft studio lighting, photorealistic 3D render, white/light gray background, clean layout, 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 hyper-realistic 3D game guide infographic poster for [GAME]. The in-game world of [GAME] is rendered as a raised, textured terrain map floating on a clean light gray surface — the map shape and landscape must reflect the actual geography and visual aesthetic of [GAME] (urban, western, fantasy, island etc). Iconic in-game locations from [GAME] are placed as miniature 3D sculpted models at their correct in-game positions across the map — each one highly detailed, photorealistic and instantly recognizable to fans. Roads or paths connect key locations as white lines across the terrain. Around the map, floating 3D decorative props and items iconic to [GAME] are scattered on the light gray surface. The official logo of [GAME] is shown as a small detailed object in the upper right corner. Each major location has a bold black label on the map, and beside the map, each location has a neat checklist of its most iconic moments or activities associated with that place, in clean sans-serif typography. A large bold title at the top reads: “THE WORLD OF GAME” in black uppercase typography with [GAME] in heavy bold. The overall aesthetic is premium editorial — soft studio lighting, photorealistic 3D render, white/light gray background, clean layout, 4:5 aspect ratio"
}
JSON
A hyper-realistic 3D anatomical human [organ] made from semi-translucent frosted polycarbonate with a milky matte finish, softly diffusing light. Industrial injection-molded detailing, subtle micro-texture, and rounded edges with precision seams. Inside, intricate mechanical components replace organic tissue, micro gears, pistons, circuitry, and engineered chambers visible but softly blurred through the shell. A subtle white Apple logo is naturally embedded on the surface, minimal and not overly obvious. Soft diffused studio lighting, realistic plastic refraction, subtle shadow beneath, centered composition, pure white background, ultra-detailed futuristic biomechanical render, 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 hyper-realistic 3D anatomical human [organ] made from semi-translucent frosted polycarbonate with a milky matte finish, softly diffusing light. Industrial injection-molded detailing, subtle micro-texture, and rounded edges with precision seams. Inside, intricate mechanical components replace organic tissue, micro gears, pistons, circuitry, and engineered chambers visible but softly blurred through the shell. A subtle white Apple logo is naturally embedded on the surface, minimal and not overly obvious. Soft diffused studio lighting, realistic plastic refraction, subtle shadow beneath, centered composition, pure white background, ultra-detailed futuristic biomechanical render, 1:1 aspect ratio."
}
JSON
Ultra-realistic 4:5 vertical format ultra wide angle 13mm selfie of me with Bugs Bunny, Daffy Duck, Porky Pig, Elmer Fudd, Yosemite Sam, Tweety, Sylvester in my studio. I am wearing pale pink t-shirt. We're all making silly, exaggerated faces. High camera angle. Extreme wide lense no fish-eye distortion. Realistic, live action characters no cartoon, cinematic lighting, all realistic characters integrated with stylized realism.
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 4:5 vertical format ultra wide angle 13mm selfie of me with Bugs Bunny, Daffy Duck, Porky Pig, Elmer Fudd, Yosemite Sam, Tweety, Sylvester in my studio. I am wearing pale pink t-shirt. We're all making silly, exaggerated faces. High camera angle. Extreme wide lense no fish-eye distortion. Realistic, live action characters no cartoon, cinematic lighting, all realistic characters integrated with stylized realism."
}
JSON
Transform this movie poster into a child’s crayon drawing on lined notebook paper. Every compositional element, character pose, typography, color palette, and layout is preserved exactly as the original — only the art style has changed. Drawn in colored pencil and crayon with wobbly unsteady lines, uneven coloring that goes slightly outside the lines, basic facial features, simplified anatomy. Background filled with heavy crayon scribble strokes. Lined notebook paper visible underneath, including the red margin line. Text redrawn in shaky hand-lettered crayon matching the original font placement. Flat scan of the drawing, slight paper texture.
curl -X POST https://runapi.ai/api/v1/nano_banana/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "nano-banana-2",
"prompt": "Transform this movie poster into a child’s crayon drawing on lined notebook paper. Every compositional element, character pose, typography, color palette, and layout is preserved exactly as the original — only the art style has changed. Drawn in colored pencil and crayon with wobbly unsteady lines, uneven coloring that goes slightly outside the lines, basic facial features, simplified anatomy. Background filled with heavy crayon scribble strokes. Lined notebook paper visible underneath, including the red margin line. Text redrawn in shaky hand-lettered crayon matching the original font placement. Flat scan of the drawing, slight paper texture."
}
JSON
A dynamic full-body urban illustration of a man (use the exact face from the provided reference image, ensuring high facial accuracy and identity preservation). He wears an oversized white hoodie with subtle black and red accents, paired with loose white track pants and bold, eye-catching white sneakers. The character has a sharp, confident gaze directed forward, conveying intensity and self-assurance. The composition is captured from a dramatic low-angle perspective, emphasizing power and dominance. His stance is strong and grounded, with exaggerated perspective on the sneakers in the foreground for added depth. Surrounding him are fragmented concrete elements and subtle debris, suggesting an urban, gritty environment. The background is a clean white canvas featuring bold red paint splashes and abstract geometric shapes, creating a modern street-art aesthetic. The visual style combines crisp, clean line art with vibrant flat colors and soft cel shading for depth and dimension. The rendering should feel like a high-end urban illustration or stylized editorial artwork. Lighting is bright, even, and diffused across the entire scene, minimizing harsh shadows while maximizing clarity and detail. Ultra-detailed, sharp focus, 8K resolution, vertical composition
curl -X POST https://runapi.ai/api/v1/nano_banana/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "nano-banana-2",
"prompt": "A dynamic full-body urban illustration of a man (use the exact face from the provided reference image, ensuring high facial accuracy and identity preservation). He wears an oversized white hoodie with subtle black and red accents, paired with loose white track pants and bold, eye-catching white sneakers. The character has a sharp, confident gaze directed forward, conveying intensity and self-assurance. The composition is captured from a dramatic low-angle perspective, emphasizing power and dominance. His stance is strong and grounded, with exaggerated perspective on the sneakers in the foreground for added depth. Surrounding him are fragmented concrete elements and subtle debris, suggesting an urban, gritty environment. The background is a clean white canvas featuring bold red paint splashes and abstract geometric shapes, creating a modern street-art aesthetic. The visual style combines crisp, clean line art with vibrant flat colors and soft cel shading for depth and dimension. The rendering should feel like a high-end urban illustration or stylized editorial artwork. Lighting is bright, even, and diffused across the entire scene, minimizing harsh shadows while maximizing clarity and detail. Ultra-detailed, sharp focus, 8K resolution, vertical composition"
}
JSON
A clean, minimal 3D isometric diorama of a [CITY TRANSPORT TYPE] stop, featuring a [VEHICLE] paused at a [PLATFORM TYPE], simple [SHELTER / CANOPY], subtle wayfinding signs, smooth concrete surfaces, soft studio lighting, realistic materials, rounded edges, miniature architectural model style, high detail, neutral background.
[BRAND NAME] Act as a High-End CGI Product Photographer and 3D Render Artist specializing in streetwear merch and limited-edition collectibles. PHASE 1: CONCEPT & OBJECT Create a photorealistic CGI product shot of a premium keychain set suspended in mid-air against a neutral gradient studio background. The keychain set consists of THREE elements connected to a single polished silver carabiner clip with a gold-plated split ring: ELEMENT 1 — ACRYLIC TAG: A rectangular acrylic charm (approx. 4:9 ratio, rounded corners, 3mm thick). Layered construction: clear gloss acrylic front panel over a [BRAND NAME]-colored background insert. The background insert carries bold, condensed all-caps typography — autonomously generate a short poetic or brand-relevant phrase (4–8 words) that matches [BRAND NAME]'s tone of voice, set in a heavy condensed grotesque typeface (Bebas Neue / Impact / custom bold). Include [BRAND NAME]'s URL or tagline in small print at the bottom of the insert. Micro-printed fine text fills the lower third as a design texture element. ELEMENT 2 — OVAL MEDALLION CHARM: A die-cut oval hoop/ring shape (donut silhouette, 40mm diameter) made from tinted translucent acrylic or resin. Autonomously determine the iconic brand color of [BRAND NAME] and apply it as the tint (deep saturated, jewel-tone translucency — e.g., gold, cobalt, emerald, crimson). The [BRAND NAME] wordmark is engraved or UV-printed in bold all-caps along the inner curve of the ring. Add 1–2 small iconographic symbols (logo mark, globe icon, cloud glyph) laser-engraved onto the face. Subtle radial sun-ray pattern embossed on the surface. ELEMENT 3 — HARDWARE: Silver anodized aluminum carabiner with knurled locking barrel. Gold-plated brass split ring (key ring loop) at the top. All metal surfaces show micro-scratches and machining marks — no perfect CGI plastic. Industrial precision aesthetic. PHASE 2: MATERIAL & TEXTURE Render all acrylic elements with full Ray Tracing and Subsurface Scattering — light must visibly pass through the tinted acrylic creating internal glow. Apply Fresnel reflection on acrylic edges. Surface imperfections: hairline scratches, micro-dust particles, smudge traces on the clear panel (subtle, editorial-level — not dirty). Metal: PBR metallic workflow — anisotropic specular highlights on the carabiner barrel, brushed finish on the ring. Typography on acrylic must appear screen-printed or UV spot-coated — slight ink texture, not floating. PHASE 3: COMPOSITION & STAGING Levitation shot: the entire keychain set hangs suspended from the top of frame, centered with a 10–15 degree rotation to the right (showing dimensionality). Nothing touches a surface — pure float. Camera angle: slightly below eye-level looking up at ~5 degrees, portrait orientation (4:5 ratio). Depth of Field: focus plane centered on the oval medallion, acrylic tag in sharp secondary focus, top hardware with micro bokeh blur. Aperture equivalent: f/4.0. Negative space: generous — object occupies 55% of frame. PHASE 4: LIGHTING Primary: large octabox soft key light, positioned top-right at 45 degrees — creates clean specular bloom on acrylic edges. Secondary: subtle rim light from bottom-left, cool temperature (5500K), separates the object from background. Background: seamless gradient cyclorama — dark steel blue (#1a2535) at top transitioning to pale silver-grey (#d0d8e0) at bottom. No hard shadows cast. Global Illumination active. Chromatic Aberration: micro-level, visible only on acrylic edges (adds realism, prevents CGI-plastic look). No lens flare. No neon. No HDR overblown highlights. TECH SPECS Render engine: Octane Render or Blender Cycles (path-traced) Resolution: 4096 x 5120px (4:5 portrait) Samples: 4096 minimum Color profile: Adobe RGB, D65 white point Post-processing: subtle film grain overlay (ISO 400 equivalent), +5 clarity, -10 highlights, neutral color grade Output mood: High-end streetwear lookbook / limited drop product page Style references: Kith accessories, Highsnobiety product editorial, Fragment Design merch photography NEGATIVE: No white studio infinity cove. No flat lay. No hand holding the product. No fake bokeh blur filters. No AI plastic sheen. No floating text outside the object.
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] Act as a High-End CGI Product Photographer and 3D Render Artist specializing in streetwear merch and limited-edition collectibles. PHASE 1: CONCEPT & OBJECT Create a photorealistic CGI product shot of a premium keychain set suspended in mid-air against a neutral gradient studio background. The keychain set consists of THREE elements connected to a single polished silver carabiner clip with a gold-plated split ring: ELEMENT 1 — ACRYLIC TAG: A rectangular acrylic charm (approx. 4:9 ratio, rounded corners, 3mm thick). Layered construction: clear gloss acrylic front panel over a [BRAND NAME]-colored background insert. The background insert carries bold, condensed all-caps typography — autonomously generate a short poetic or brand-relevant phrase (4–8 words) that matches [BRAND NAME]'s tone of voice, set in a heavy condensed grotesque typeface (Bebas Neue / Impact / custom bold). Include [BRAND NAME]'s URL or tagline in small print at the bottom of the insert. Micro-printed fine text fills the lower third as a design texture element. ELEMENT 2 — OVAL MEDALLION CHARM: A die-cut oval hoop/ring shape (donut silhouette, 40mm diameter) made from tinted translucent acrylic or resin. Autonomously determine the iconic brand color of [BRAND NAME] and apply it as the tint (deep saturated, jewel-tone translucency — e.g., gold, cobalt, emerald, crimson). The [BRAND NAME] wordmark is engraved or UV-printed in bold all-caps along the inner curve of the ring. Add 1–2 small iconographic symbols (logo mark, globe icon, cloud glyph) laser-engraved onto the face. Subtle radial sun-ray pattern embossed on the surface. ELEMENT 3 — HARDWARE: Silver anodized aluminum carabiner with knurled locking barrel. Gold-plated brass split ring (key ring loop) at the top. All metal surfaces show micro-scratches and machining marks — no perfect CGI plastic. Industrial precision aesthetic. PHASE 2: MATERIAL & TEXTURE Render all acrylic elements with full Ray Tracing and Subsurface Scattering — light must visibly pass through the tinted acrylic creating internal glow. Apply Fresnel reflection on acrylic edges. Surface imperfections: hairline scratches, micro-dust particles, smudge traces on the clear panel (subtle, editorial-level — not dirty). Metal: PBR metallic workflow — anisotropic specular highlights on the carabiner barrel, brushed finish on the ring. Typography on acrylic must appear screen-printed or UV spot-coated — slight ink texture, not floating. PHASE 3: COMPOSITION & STAGING Levitation shot: the entire keychain set hangs suspended from the top of frame, centered with a 10–15 degree rotation to the right (showing dimensionality). Nothing touches a surface — pure float. Camera angle: slightly below eye-level looking up at ~5 degrees, portrait orientation (4:5 ratio). Depth of Field: focus plane centered on the oval medallion, acrylic tag in sharp secondary focus, top hardware with micro bokeh blur. Aperture equivalent: f/4.0. Negative space: generous — object occupies 55% of frame. PHASE 4: LIGHTING Primary: large octabox soft key light, positioned top-right at 45 degrees — creates clean specular bloom on acrylic edges. Secondary: subtle rim light from bottom-left, cool temperature (5500K), separates the object from background. Background: seamless gradient cyclorama — dark steel blue (#1a2535) at top transitioning to pale silver-grey (#d0d8e0) at bottom. No hard shadows cast. Global Illumination active. Chromatic Aberration: micro-level, visible only on acrylic edges (adds realism, prevents CGI-plastic look). No lens flare. No neon. No HDR overblown highlights. TECH SPECS Render engine: Octane Render or Blender Cycles (path-traced) Resolution: 4096 x 5120px (4:5 portrait) Samples: 4096 minimum Color profile: Adobe RGB, D65 white point Post-processing: subtle film grain overlay (ISO 400 equivalent), +5 clarity, -10 highlights, neutral color grade Output mood: High-end streetwear lookbook / limited drop product page Style references: Kith accessories, Highsnobiety product editorial, Fragment Design merch photography NEGATIVE: No white studio infinity cove. No flat lay. No hand holding the product. No fake bokeh blur filters. No AI plastic sheen. No floating text outside the object."
}
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
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"
}
JSON
Epic 3D scene: a weathered field journal lies open on a naturalist's camp table, its pages erupting into the ecosystems they document. Hand-drawn botanical illustrations push upward into living specimens : [PLANT 1] unfurls actual petals, [PLANT 2] releases pollen that drifts across the spread. Pinned insect diagrams detach and take flight. Watercolor landscapes inflate into traversable terrain. Margin notes become tiny expedition camps. Pressed flowers resurrect in time-lapse bloom. A specimen jar on the page contains an actual swimming creature. Field sketches of [ANIMAL] step off the paper, leaving graphite footprints. Coffee-stained pages become amber pools. Canvas tent visible beyond, lantern light mixing with fireflies, the smell of pine and old paper, 8K, photorealistic documentary aesthetic
curl -X POST https://runapi.ai/api/v1/nano_banana/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "nano-banana-2",
"prompt": "Epic 3D scene: a weathered field journal lies open on a naturalist's camp table, its pages erupting into the ecosystems they document. Hand-drawn botanical illustrations push upward into living specimens : [PLANT 1] unfurls actual petals, [PLANT 2] releases pollen that drifts across the spread. Pinned insect diagrams detach and take flight. Watercolor landscapes inflate into traversable terrain. Margin notes become tiny expedition camps. Pressed flowers resurrect in time-lapse bloom. A specimen jar on the page contains an actual swimming creature. Field sketches of [ANIMAL] step off the paper, leaving graphite footprints. Coffee-stained pages become amber pools. Canvas tent visible beyond, lantern light mixing with fireflies, the smell of pine and old paper, 8K, photorealistic documentary aesthetic"
}
JSON
Surrounding the realistic main subject are multiple cute, 3D-style chibi miniatures of the same person, with identical facial features, hairstyle, body proportions, and outfit. The chibi figures are naturally distributed around the subject, interacting playfully with her or nearby elements in a charming, non-intrusive way. Overlay the image with vibrant, hand-drawn doodle effects: soft white outlines around the subject, playful sparkles, doodle hearts, tiny flowers, smiley icons, and floating white handwritten phrases like "shine", "bright day", and "happy". The style seamlessly blends hyper-realistic photography with colorful, soft cartoon illustrations. Keep the original face, body shape, and proportions of the main subject unchanged. aspect ratio 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": "Surrounding the realistic main subject are multiple cute, 3D-style chibi miniatures of the same person, with identical facial features, hairstyle, body proportions, and outfit. The chibi figures are naturally distributed around the subject, interacting playfully with her or nearby elements in a charming, non-intrusive way. Overlay the image with vibrant, hand-drawn doodle effects: soft white outlines around the subject, playful sparkles, doodle hearts, tiny flowers, smiley icons, and floating white handwritten phrases like \"shine\", \"bright day\", and \"happy\". The style seamlessly blends hyper-realistic photography with colorful, soft cartoon illustrations. Keep the original face, body shape, and proportions of the main subject unchanged. aspect ratio 2:3"
}
JSON
Create a premium Pixar-style 3D character sticker set that is clearly recognizable as the same person. Use the uploaded image as the ONLY facial reference. Output Requirements: 3×3 grid layout (9 stickers total) Final aspect ratio: 4:5 Ultra high resolution (8K) Clean cream background Each sticker is separated with clear spacing Add a subtle drop shadow under each sticker for depth Character Identity (VERY IMPORTANT): MUST preserve exact facial structure, hairstyle, grooming details, and unique features from the uploaded image Maintain high likeness accuracy Do NOT over beautify or alter identity beyond recognition Style: Pixar-style 3D animation Glossy, high-end rendering Soft global illumination Smooth shading High-detail facial textures Framing: All stickers must be head and shoulders (portrait close-up) only No full-body or mid-body shots allowed Focus tightly on face and upper shoulders to emphasize expressions Outfit: Modern casual and slightly stylized clothing Each sticker must have a different outfit (no repetition at all) Clean, minimal, and visually appealing for sticker use Expressions & Poses (9 variations): 1. Happy smile 2. Laughing 3. Cool (with sunglasses) 4. Angry/serious 5. Surprised 6. Thinking 7. Wink 8. Love (heart eyes and heart gesture) 9. Thumbs up Sticker Design: Bold, clean outline Slightly exaggerated cartoon proportions Strong emphasis on facial expressions Optimized for digital sticker platforms Each sticker must have a smooth rounded bottom cutout (semi-curved base) No text Lighting: Soft studio lighting Subtle rim light for depth and separation Goal: Create a highly engaging, cute, and expressive sticker pack that feels premium and collectable.
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 premium Pixar-style 3D character sticker set that is clearly recognizable as the same person. Use the uploaded image as the ONLY facial reference. Output Requirements: 3×3 grid layout (9 stickers total) Final aspect ratio: 4:5 Ultra high resolution (8K) Clean cream background Each sticker is separated with clear spacing Add a subtle drop shadow under each sticker for depth Character Identity (VERY IMPORTANT): MUST preserve exact facial structure, hairstyle, grooming details, and unique features from the uploaded image Maintain high likeness accuracy Do NOT over beautify or alter identity beyond recognition Style: Pixar-style 3D animation Glossy, high-end rendering Soft global illumination Smooth shading High-detail facial textures Framing: All stickers must be head and shoulders (portrait close-up) only No full-body or mid-body shots allowed Focus tightly on face and upper shoulders to emphasize expressions Outfit: Modern casual and slightly stylized clothing Each sticker must have a different outfit (no repetition at all) Clean, minimal, and visually appealing for sticker use Expressions & Poses (9 variations): 1. Happy smile 2. Laughing 3. Cool (with sunglasses) 4. Angry/serious 5. Surprised 6. Thinking 7. Wink 8. Love (heart eyes and heart gesture) 9. Thumbs up Sticker Design: Bold, clean outline Slightly exaggerated cartoon proportions Strong emphasis on facial expressions Optimized for digital sticker platforms Each sticker must have a smooth rounded bottom cutout (semi-curved base) No text Lighting: Soft studio lighting Subtle rim light for depth and separation Goal: Create a highly engaging, cute, and expressive sticker pack that feels premium and collectable."
}
JSON
{ "prompt": "Ultra-realistic macro scene depicting tiny restoration workers collaboratively repairing an antique pocket watch. Several figures delicately clean intricate brass gears using fine brushes, while others stabilize the open watch casing and hold miniature components in place. The pocket watch lies on a textured natural surface, such as weathered wood or stone, emphasizing age and history. The scene symbolizes time, patience, craftsmanship, and teamwork.", "style": { "photography_type": "Macro photography", "realism": "Ultra-realistic", "mood": "Emotional and cinematic", "lighting": "Soft, warm, directional lighting with gentle highlights and natural shadows", "depth_of_field": "Shallow depth of field with sharp focus on foreground details and smooth background bokeh" }, "composition": { "shot_type": "Close-up macro", "angle": "Slightly elevated perspective", "focus": "Extreme detail on gears, tools, and figurines’ interactions", "framing": "Pocket watch centered with workers distributed naturally across the mechanism" }, "textures_and_details": { "materials": "Aged metal, polished brass gears, worn leather strap, natural surface grain", "details": "Visible dust particles, subtle scratches, fingerprints, and mechanical wear" }, "atmosphere": { "tone": "Warm, nostalgic, hopeful", "symbolism": "Restoration of time through collective effort and care" }, "render_settings": { "aspect_ratio": "4:5", "quality": 2, "resolution": "High-resolution", "style_precision": "Professional studio-level composition" } }
curl -X POST https://runapi.ai/api/v1/nano_banana/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "nano-banana-2",
"prompt": "{ \"prompt\": \"Ultra-realistic macro scene depicting tiny restoration workers collaboratively repairing an antique pocket watch. Several figures delicately clean intricate brass gears using fine brushes, while others stabilize the open watch casing and hold miniature components in place. The pocket watch lies on a textured natural surface, such as weathered wood or stone, emphasizing age and history. The scene symbolizes time, patience, craftsmanship, and teamwork.\", \"style\": { \"photography_type\": \"Macro photography\", \"realism\": \"Ultra-realistic\", \"mood\": \"Emotional and cinematic\", \"lighting\": \"Soft, warm, directional lighting with gentle highlights and natural shadows\", \"depth_of_field\": \"Shallow depth of field with sharp focus on foreground details and smooth background bokeh\" }, \"composition\": { \"shot_type\": \"Close-up macro\", \"angle\": \"Slightly elevated perspective\", \"focus\": \"Extreme detail on gears, tools, and figurines’ interactions\", \"framing\": \"Pocket watch centered with workers distributed naturally across the mechanism\" }, \"textures_and_details\": { \"materials\": \"Aged metal, polished brass gears, worn leather strap, natural surface grain\", \"details\": \"Visible dust particles, subtle scratches, fingerprints, and mechanical wear\" }, \"atmosphere\": { \"tone\": \"Warm, nostalgic, hopeful\", \"symbolism\": \"Restoration of time through collective effort and care\" }, \"render_settings\": { \"aspect_ratio\": \"4:5\", \"quality\": 2, \"resolution\": \"High-resolution\", \"style_precision\": \"Professional studio-level composition\" } }"
}
JSON
Present a clear, 45° top-down isometric miniature 3D cartoon scene of the iconic scene [SCENE NAME] from [MOVIE/SHOW], with soft refined textures, realistic PBR materials, and gentle lifelike lighting. Create a small raised diorama-style base that includes the most recognizable elements of this scene, along with tiny stylized characters if needed (no facial details). Use a clean solid [BACKGROUND COLOR] background. At the top-center, display [MOVIE/SHOW] in large bold text, directly beneath it show [SCENE NAME] in medium text, and place the official logo associated with [MOVIE/SHOW] below the subtext. All text must automatically match the background contrast (white or black). Composition: perfectly centered layout, square 1080x1080, ultra-clean, high-clarity diorama aesthetic.
curl -X POST https://runapi.ai/api/v1/nano_banana/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "nano-banana-2",
"prompt": "Present a clear, 45° top-down isometric miniature 3D cartoon scene of the iconic scene [SCENE NAME] from [MOVIE/SHOW], with soft refined textures, realistic PBR materials, and gentle lifelike lighting. Create a small raised diorama-style base that includes the most recognizable elements of this scene, along with tiny stylized characters if needed (no facial details). Use a clean solid [BACKGROUND COLOR] background. At the top-center, display [MOVIE/SHOW] in large bold text, directly beneath it show [SCENE NAME] in medium text, and place the official logo associated with [MOVIE/SHOW] below the subtext. All text must automatically match the background contrast (white or black). Composition: perfectly centered layout, square 1080x1080, ultra-clean, high-clarity diorama aesthetic."
}
JSON
Present a clear, 45° top-down isometric miniature 3D cartoon scene of [STADIUM], with soft refined textures, realistic PBR materials, and gentle lifelike lighting. Use a clean solid [COLOR] background. At the top-center, display the name of this stadium in large bold text, then directly beneath it show its real seating capacity in medium text, and place the official logo associated with this stadium below the capacity. All text must match the background contrast automatically (white or black). Centered layout
curl -X POST https://runapi.ai/api/v1/nano_banana/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "nano-banana-2",
"prompt": "Present a clear, 45° top-down isometric miniature 3D cartoon scene of [STADIUM], with soft refined textures, realistic PBR materials, and gentle lifelike lighting. Use a clean solid [COLOR] background. At the top-center, display the name of this stadium in large bold text, then directly beneath it show its real seating capacity in medium text, and place the official logo associated with this stadium below the capacity. All text must match the background contrast automatically (white or black). Centered layout"
}
JSON
A cute 3D Pixar-style character portrait of a little girl with big expressive eyes and round glasses, soft smooth skin, and slightly rosy cheeks. She has dark hair styled into two messy space buns tied with red scrunchies. She is wearing a cozy red knitted sweater with white winter patterns and blue denim overalls with small fabric details and light wear. Her arms are crossed casually. A small adorable fennec fox with huge ears and sleepy eyes is resting on her shoulder, leaning against her neck affectionately.
curl -X POST https://runapi.ai/api/v1/nano_banana/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "nano-banana-2",
"prompt": "A cute 3D Pixar-style character portrait of a little girl with big expressive eyes and round glasses, soft smooth skin, and slightly rosy cheeks. She has dark hair styled into two messy space buns tied with red scrunchies. She is wearing a cozy red knitted sweater with white winter patterns and blue denim overalls with small fabric details and light wear. Her arms are crossed casually. A small adorable fennec fox with huge ears and sleepy eyes is resting on her shoulder, leaning against her neck affectionately."
}
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.