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 high fashion magazine pictorial of an Alpine-looking woman in her early 20s who stands still, looking at the camera, turning her head in the center, surrounded by a blurry silhouette of people passing by. She has a calm, stoic look on her face and is wearing a black minimalist outfit. The background is clean, bright and slightly abstract, and emphasizes the contrast between motion blur and static appearance. Editing style, film composition, pure art photography, soft magazine texture, high resolution. --ar 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 high fashion magazine pictorial of an Alpine-looking woman in her early 20s who stands still, looking at the camera, turning her head in the center, surrounded by a blurry silhouette of people passing by. She has a calm, stoic look on her face and is wearing a black minimalist outfit. The background is clean, bright and slightly abstract, and emphasizes the contrast between motion blur and static appearance. Editing style, film composition, pure art photography, soft magazine texture, high resolution. --ar 4:5"
}
JSON
A high-resolution, close-up editorial-style portrait of a young woman standing against a textured gray concrete wall, captured with direct on-camera flash that creates a raw, moody, high-contrast aesthetic. She is positioned slightly angled to the side with her head tilted back and chin lifted, giving an effortlessly cool, candid expression. Her face has a fair, smooth complexion with a natural sheen from the flash, soft rosy blush across the cheeks, minimal eye makeup, lightly defined brows, and glossy natural pink lips that are slightly parted, conveying a relaxed yet confident mood. Wispy strands of her dark brown hair fall loosely across her face, partially covering one eye, while the rest of her hair is pulled back into a low, casual style, enhancing the spontaneous, fashion-editorial feel. Her eyes look slightly upward and past the camera, adding to the detached, artistic vibe. She is wearing a loose-fitting white oversized T-shirt with bold red typography reading “CALIFORNIA” across the chest, along with smaller black text underneath, giving a casual streetwear aesthetic. Small, subtle stud earrings are visible, adding minimal detail without distracting from the overall look. The lighting is harsh and frontal, producing sharp shadows behind her on the wall and emphasizing skin texture, hair strands, and fabric folds, while the background remains simple and uncluttered. The color palette is muted and neutral—gray wall, white shirt, and red lettering—allowing the subject’s face and expression to remain the focal point. The overall atmosphere feels intimate, modern, slightly gritty, and effortlessly stylish, like a candid fashion snapshot captured at night with flash photography. Use this uploaded photo as the only and exact face reference. The generated image must use this same face exactly as shown, without any changes to identity, facial structure, or expression.
curl -X POST https://runapi.ai/api/v1/nano_banana/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "nano-banana-2",
"prompt": "A high-resolution, close-up editorial-style portrait of a young woman standing against a textured gray concrete wall, captured with direct on-camera flash that creates a raw, moody, high-contrast aesthetic. She is positioned slightly angled to the side with her head tilted back and chin lifted, giving an effortlessly cool, candid expression. Her face has a fair, smooth complexion with a natural sheen from the flash, soft rosy blush across the cheeks, minimal eye makeup, lightly defined brows, and glossy natural pink lips that are slightly parted, conveying a relaxed yet confident mood. Wispy strands of her dark brown hair fall loosely across her face, partially covering one eye, while the rest of her hair is pulled back into a low, casual style, enhancing the spontaneous, fashion-editorial feel. Her eyes look slightly upward and past the camera, adding to the detached, artistic vibe. She is wearing a loose-fitting white oversized T-shirt with bold red typography reading “CALIFORNIA” across the chest, along with smaller black text underneath, giving a casual streetwear aesthetic. Small, subtle stud earrings are visible, adding minimal detail without distracting from the overall look. The lighting is harsh and frontal, producing sharp shadows behind her on the wall and emphasizing skin texture, hair strands, and fabric folds, while the background remains simple and uncluttered. The color palette is muted and neutral—gray wall, white shirt, and red lettering—allowing the subject’s face and expression to remain the focal point. The overall atmosphere feels intimate, modern, slightly gritty, and effortlessly stylish, like a candid fashion snapshot captured at night with flash photography. Use this uploaded photo as the only and exact face reference. The generated image must use this same face exactly as shown, without any changes to identity, facial structure, or expression."
}
JSON
Ultra-clean modern recipe infographic. Showcase Pizza in a visually appealing finished form—sliced, plated, or portioned—floating slightly in perspective or angled view. Arrange ingredients, steps, and tips around the dish in a dynamic editorial layout, not restricted to top-down. Ingredients Section: Include icons or mini illustrations for each ingredient with quantities. Arrange them in clusters, lists, or circular flows connected visually to the dish. Steps Section: Show preparation steps with numbered panels, arrows, or lines, forming a logical flow around the main dish. Include small cooking icons (knife, pan, oven, timer) where helpful. Additional Info (optional): Total calories, prep/cook time, servings, spice level—displayed as clean bubbles or badges near the dish. Visual Style: Editorial infographic meets lifestyle food photography. Vibrant, natural food colors, subtle drop shadows, clean vector icons, modern typography, soft gradients or glassmorphism for step panels. Accent colors can highlight key info (calories, prep time). Composition Guidelines: Finished meal as hero visual (perspective or angled) Ingredients and steps flow dynamically around the dish Clear visual hierarchy: dish > steps > ingredients > optional stats Enough negative space to keep design airy and readable Lighting & Background: Soft, natural studio lighting, minimal textured or gradient background for premium editorial feel. 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": "Ultra-clean modern recipe infographic. Showcase Pizza in a visually appealing finished form—sliced, plated, or portioned—floating slightly in perspective or angled view. Arrange ingredients, steps, and tips around the dish in a dynamic editorial layout, not restricted to top-down. Ingredients Section: Include icons or mini illustrations for each ingredient with quantities. Arrange them in clusters, lists, or circular flows connected visually to the dish. Steps Section: Show preparation steps with numbered panels, arrows, or lines, forming a logical flow around the main dish. Include small cooking icons (knife, pan, oven, timer) where helpful. Additional Info (optional): Total calories, prep/cook time, servings, spice level—displayed as clean bubbles or badges near the dish. Visual Style: Editorial infographic meets lifestyle food photography. Vibrant, natural food colors, subtle drop shadows, clean vector icons, modern typography, soft gradients or glassmorphism for step panels. Accent colors can highlight key info (calories, prep time). Composition Guidelines: Finished meal as hero visual (perspective or angled) Ingredients and steps flow dynamically around the dish Clear visual hierarchy: dish > steps > ingredients > optional stats Enough negative space to keep design airy and readable Lighting & Background: Soft, natural studio lighting, minimal textured or gradient background for premium editorial feel. Output: 1080×1080, ultra-crisp, social-feed optimized, no watermark.”"
}
JSON
Create top-down flat lay product photo. Use the uploaded product as the main object, centered. Analyze the product type from the photo and automatically choose matching props/ingredients for an aesthetic flat lay around it (minimal, premium, on-brand). Preserve exact geometry, size, colors, label design, and all text on the product (no changes). Warm beige seamless background, soft directional sunlight, crisp realistic shadow. Ultra-realistic macro product photography, 100mm lens look, f/8, sharp focus, clean composition, no extra text, 8k, format 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": "Create top-down flat lay product photo. Use the uploaded product as the main object, centered. Analyze the product type from the photo and automatically choose matching props/ingredients for an aesthetic flat lay around it (minimal, premium, on-brand). Preserve exact geometry, size, colors, label design, and all text on the product (no changes). Warm beige seamless background, soft directional sunlight, crisp realistic shadow. Ultra-realistic macro product photography, 100mm lens look, f/8, sharp focus, clean composition, no extra text, 8k, format 2:3."
}
JSON
Using the provided reference_image as the primary source for identity, clothing colors, and visual attributes, create a full-body 3D stylized anthropomorphic cartoon version of the character. Preserve facial structure, body proportions, silhouette, and distinctive traits exactly as in the reference_image. The outfit must match the clothing colors from the reference_image. Extract and apply the exact dominant and secondary colors from the reference_image to the hoodie, cargo pants, and sneakers. Do not introduce new colors. Do not default to orange or neon green unless they exist in the reference_image. Modern streetwear styling is allowed, but color palette must strictly follow the reference_image. Confident relaxed pose with hands in pockets. Minimal studio background using the dominant background color sampled from the reference_image, or a harmonized tone derived from it. Soft studio lighting, smooth shadows, high-detail fabric texture, Pixar-quality 3D render, ultra-clean composition, centered framing, 8K resolution. Add enforcement: “Strict color adherence to reference_image. No automatic color substitution.
curl -X POST https://runapi.ai/api/v1/nano_banana/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "nano-banana-2",
"prompt": "Using the provided reference_image as the primary source for identity, clothing colors, and visual attributes, create a full-body 3D stylized anthropomorphic cartoon version of the character. Preserve facial structure, body proportions, silhouette, and distinctive traits exactly as in the reference_image. The outfit must match the clothing colors from the reference_image. Extract and apply the exact dominant and secondary colors from the reference_image to the hoodie, cargo pants, and sneakers. Do not introduce new colors. Do not default to orange or neon green unless they exist in the reference_image. Modern streetwear styling is allowed, but color palette must strictly follow the reference_image. Confident relaxed pose with hands in pockets. Minimal studio background using the dominant background color sampled from the reference_image, or a harmonized tone derived from it. Soft studio lighting, smooth shadows, high-detail fabric texture, Pixar-quality 3D render, ultra-clean composition, centered framing, 8K resolution. Add enforcement: “Strict color adherence to reference_image. No automatic color substitution."
}
JSON
Create a hyperrealistic, surreal spherical panorama of [CITY NAME], with its most iconic landmarks and architecture seamlessly curving around the top of a planet-like surface, forming a cohesive miniature world. Integrate sleek, modern 3D typography spelling “[CITY NAME]” naturally into the urban landscape, harmonized with the environment rather than floating unnaturally. The scene is viewed from a top-down, orbiting perspective, emphasizing the tiny-planet effect and spherical distortion while maintaining architectural clarity. Soft, natural daylight filters through a partly cloudy sky, casting gentle, realistic shadows across lush greenery, streets, trees, and buildings. The background transitions smoothly into a dramatic, swirling sky, enhancing the surreal atmosphere without overpowering the city. Use a natural yet vivid color palette — crisp greens, soft blues, and muted earth tones appropriate to [CITY NAME]. Render in a polished, photorealistic style with fine architectural detail, realistic textures, atmospheric depth, and high visual fidelity.
curl -X POST https://runapi.ai/api/v1/nano_banana/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "nano-banana-2",
"prompt": "Create a hyperrealistic, surreal spherical panorama of [CITY NAME], with its most iconic landmarks and architecture seamlessly curving around the top of a planet-like surface, forming a cohesive miniature world. Integrate sleek, modern 3D typography spelling “[CITY NAME]” naturally into the urban landscape, harmonized with the environment rather than floating unnaturally. The scene is viewed from a top-down, orbiting perspective, emphasizing the tiny-planet effect and spherical distortion while maintaining architectural clarity. Soft, natural daylight filters through a partly cloudy sky, casting gentle, realistic shadows across lush greenery, streets, trees, and buildings. The background transitions smoothly into a dramatic, swirling sky, enhancing the surreal atmosphere without overpowering the city. Use a natural yet vivid color palette — crisp greens, soft blues, and muted earth tones appropriate to [CITY NAME]. Render in a polished, photorealistic style with fine architectural detail, realistic textures, atmospheric depth, and high visual fidelity."
}
JSON
[BRAND NAME] | [SLOGAN]. Act as a Professional Editorial Art Director. PHASE 1: PHYSICS & GROUNDING (THE "STABILITY" RULE). - Analyze [BRAND NAME] category: * CATEGORY A (Active/Sports/Fashion): The subject (person) is in a high-intensity leap, detached from the ground, silhouette against the sky. * CATEGORY B (Automotive/Heavy Goods): The subject (vehicle) must be HEROICALLY GROUNDED. Place the car firmly on a solid surface (asphalt, concrete, or rock). * Perspective: Use an extreme low-angle (worm's-eye view). The car must look massive and dominant, anchored to the bottom of the frame, towering over the viewer. NO floating or flying for vehicles. PHASE 2: DYNAMIC PHOTOGRAPHY & LIGHTING. - Environment: A vast, clear blue sky with minimal soft clouds. - Lighting: Natural, direct sunlight. High-contrast shadows on the subject to emphasize form and texture. - Style: High-end 8k commercial photography. Sharp focus. PHASE 3: TYPOGRAPHY & LAYOUT (MATTE FINISH). - Layout: Use the text from "[SLOGAN]" as massive, ultra-condensed bold sans-serif characters. - Execution: Split "[SLOGAN]" into two parts: one on the far left, one on the far right. - Depth: A part of the subject (e.g., a bumper, a mirror, or a person's limb) must overlap the letters to create a 3D effect. PHASE 4: COLOR STRATEGY (MATTE & REALISTIC). - Graphic Color: NO NEON. Use a solid, matte brand color for the text (e.g., flat Navy for BMW, flat Red for Red Bull). The color must be opaque and non-glowing, resembling high-quality print ink. - Photo Color: Maintain authentic, rich photographic colors for the subject and the sky. The contrast comes from "Flat Graphic vs. Realistic Photo". PHASE 5: FINAL BRANDING. - Logo: Small minimalist [BRAND NAME] logo in the upper corner. - Metadata: Tiny secondary text in a clean sans-serif font at the bottom for a technical/editorial look.
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] | [SLOGAN]. Act as a Professional Editorial Art Director. PHASE 1: PHYSICS & GROUNDING (THE \"STABILITY\" RULE). - Analyze [BRAND NAME] category: * CATEGORY A (Active/Sports/Fashion): The subject (person) is in a high-intensity leap, detached from the ground, silhouette against the sky. * CATEGORY B (Automotive/Heavy Goods): The subject (vehicle) must be HEROICALLY GROUNDED. Place the car firmly on a solid surface (asphalt, concrete, or rock). * Perspective: Use an extreme low-angle (worm's-eye view). The car must look massive and dominant, anchored to the bottom of the frame, towering over the viewer. NO floating or flying for vehicles. PHASE 2: DYNAMIC PHOTOGRAPHY & LIGHTING. - Environment: A vast, clear blue sky with minimal soft clouds. - Lighting: Natural, direct sunlight. High-contrast shadows on the subject to emphasize form and texture. - Style: High-end 8k commercial photography. Sharp focus. PHASE 3: TYPOGRAPHY & LAYOUT (MATTE FINISH). - Layout: Use the text from \"[SLOGAN]\" as massive, ultra-condensed bold sans-serif characters. - Execution: Split \"[SLOGAN]\" into two parts: one on the far left, one on the far right. - Depth: A part of the subject (e.g., a bumper, a mirror, or a person's limb) must overlap the letters to create a 3D effect. PHASE 4: COLOR STRATEGY (MATTE & REALISTIC). - Graphic Color: NO NEON. Use a solid, matte brand color for the text (e.g., flat Navy for BMW, flat Red for Red Bull). The color must be opaque and non-glowing, resembling high-quality print ink. - Photo Color: Maintain authentic, rich photographic colors for the subject and the sky. The contrast comes from \"Flat Graphic vs. Realistic Photo\". PHASE 5: FINAL BRANDING. - Logo: Small minimalist [BRAND NAME] logo in the upper corner. - Metadata: Tiny secondary text in a clean sans-serif font at the bottom for a technical/editorial look."
}
JSON
Create a super cute, hyper-realistic 3D render of a toddler girl who is a younger version of the person in the provided reference photo. The facial structure must strongly match the reference image. Accurately replicate the exact eye shape, eye color, skin tone, lip shape, nose structure, cheek fullness, eyebrow shape, and overall facial proportions. The toddler version should clearly resemble the same person at a younger age while maintaining realistic childlike softness and rounded features. If any accessory (such as an earring or similar detail) appears in the reference image, replicate it accurately in size, colour, and placement. Expression: Distinctly grumpy and pouty. Chin resting on her left palm. One eye slightly squinted in mild annoyance. Eyebrows gently furrowed. Lips pushed forward in a stubborn pout. Expression must feel natural and emotionally believable, not exaggerated. Hair: Hairstyle should be adapted from the reference image while keeping it toddler-appropriate. Styled in a messy high bun with soft, natural baby hair strands framing the face. Outfit: White short-sleeve t-shirt under classic blue denim overalls with visible stitching and metal clasps. Pose & Background: Sitting cross-legged on a clean white studio background. Feet slightly angled toward the camera. Balanced composition with full body visible. Style & Quality: Ultra-detailed Pixar/Disney-inspired 3D animation aesthetic. Professional CGI rendering. 1:1 aspect ratio. 8K resolution. Sharp focus. Cinematic studio lighting with soft subsurface scattering on the skin. Smooth textures, realistic fabric physics, soft global illumination, and natural shadow falloff.
curl -X POST https://runapi.ai/api/v1/nano_banana/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "nano-banana-2",
"prompt": "Create a super cute, hyper-realistic 3D render of a toddler girl who is a younger version of the person in the provided reference photo. The facial structure must strongly match the reference image. Accurately replicate the exact eye shape, eye color, skin tone, lip shape, nose structure, cheek fullness, eyebrow shape, and overall facial proportions. The toddler version should clearly resemble the same person at a younger age while maintaining realistic childlike softness and rounded features. If any accessory (such as an earring or similar detail) appears in the reference image, replicate it accurately in size, colour, and placement. Expression: Distinctly grumpy and pouty. Chin resting on her left palm. One eye slightly squinted in mild annoyance. Eyebrows gently furrowed. Lips pushed forward in a stubborn pout. Expression must feel natural and emotionally believable, not exaggerated. Hair: Hairstyle should be adapted from the reference image while keeping it toddler-appropriate. Styled in a messy high bun with soft, natural baby hair strands framing the face. Outfit: White short-sleeve t-shirt under classic blue denim overalls with visible stitching and metal clasps. Pose & Background: Sitting cross-legged on a clean white studio background. Feet slightly angled toward the camera. Balanced composition with full body visible. Style & Quality: Ultra-detailed Pixar/Disney-inspired 3D animation aesthetic. Professional CGI rendering. 1:1 aspect ratio. 8K resolution. Sharp focus. Cinematic studio lighting with soft subsurface scattering on the skin. Smooth textures, realistic fabric physics, soft global illumination, and natural shadow falloff."
}
JSON
A Realistic First Person (Pov) Selfie Taken With An Outside Arm, In The Same Clothes As In The Uploaded Photo. Close-up Of Me Hugging Tom, The Cartoon Gray Cat From Tom And Jerry, With A Small Smile (Jerry Can Be Looking Out Of My Shoulder Or My Pocket). Photorealistic Environment: Studio Set, Office Interior, Warm Light, Props, Spotlights And Cables In The Background. Tom Is A Strongly Stylized Toon 3d: Cel-shading, Multi-proportions, Clear Contour, No Realistic Fur, Not Live-action. Organic: Zoom To The Chest, Contact Of Hugs, Single Light, Natural Shadows. 4k.natural shadows. 4k.
curl -X POST https://runapi.ai/api/v1/nano_banana/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "nano-banana-2",
"prompt": "A Realistic First Person (Pov) Selfie Taken With An Outside Arm, In The Same Clothes As In The Uploaded Photo. Close-up Of Me Hugging Tom, The Cartoon Gray Cat From Tom And Jerry, With A Small Smile (Jerry Can Be Looking Out Of My Shoulder Or My Pocket). Photorealistic Environment: Studio Set, Office Interior, Warm Light, Props, Spotlights And Cables In The Background. Tom Is A Strongly Stylized Toon 3d: Cel-shading, Multi-proportions, Clear Contour, No Realistic Fur, Not Live-action. Organic: Zoom To The Chest, Contact Of Hugs, Single Light, Natural Shadows. 4k.natural shadows. 4k."
}
JSON
[BRAND NAME]. Act as a Fashion Photographer and Graphic Designer specializing in luxury brand campaign visuals with integrated typography and surreal spatial design. PHASE 1: SPATIAL CONCEPT Create a high-fashion editorial image where architecture and graphic design merge into a theatrical stage. The foundation is a bold geometric floor pattern that extends into forced perspective, creating infinite depth and visual drama. This is not a neutral backdrop – the floor is a protagonist that amplifies brand identity through pattern, color, and spatial illusion. PHASE 2: CHECKERBOARD ARCHITECTURE - Surface: Checkerboard/geometric tile pattern rendered in brand-relevant colors - Perspective: Aggressive forced perspective starting from bottom foreground and receding toward horizon (vanishing point at upper third of frame) - Pattern Logic: Autonomously determine pattern based on [BRAND NAME]: - Color Palette: Incorporate 2-3 signature colors of [BRAND NAME] into floor pattern while maintaining readability - Texture: Photorealistic rendering with subtle reflections and shadows for depth PHASE 3: MODEL & STYLING - Subject: One fashion model (gender-fluid casting) captured mid-motion – dynamic pose suggesting walking, running, or dancing - Outfit: Elevated monochrome look (black, white, or brand-neutral tone) to let floor pattern and typography dominate. Include 1-2 key accessories in [BRAND NAME]'s signature color as hero product focal points - Pose Energy: 70% movement, 30% control – fashion-forward but grounded (avoid floating/unnatural levitation) - Placement: Model positioned in lower-mid frame, interacting spatially with both floor perspective and typography layer - Camera Angle: Low-to-mid angle (waist-to-full body shot) to emphasize floor perspective drama PHASE 4: TYPOGRAPHY INTEGRATION - Brand Script: Oversized handwritten/script version of [BRAND NAME] rendered as flat graphic element behind or around the model - Scale: Typography should be 40-60% of frame width – bold and unmissable but not crushing the model - Color: Signature brand color (autonomously selected), solid fill with clean edges - Interaction: Typography appears to "sit" in the space – model may partially overlap letters, creating layering hierarchy - Logo Lockup: Clean, small brand logo centered in upper portion of frame (10-15% of width) in black or brand color - Treatment: Pure vector aesthetic – no gradients, no shadows, no dimensional effects. Flat color only. PHASE 5: COLOR ORCHESTRATION (AUTONOMOUS) Autonomously research and apply [BRAND NAME]'s iconic color system: - Primary: Identify 1-2 hero brand colors (e.g., Gucci → forest green + red, Tiffany → robin egg blue) - Application: Use primary colors in floor pattern AND typography for visual cohesion - Balance: 60% white/neutral space, 30% brand color saturation, 10% black for anchoring - Accent: Hero product (bag, shoes, accessory) should echo brand color for strategic eye-pull PHASE 6: LIGHTING & ATMOSPHERE - Lighting Setup: High-key fashion lighting with soft shadows – think editorial studio quality - Key Light: 45° front-left to sculpt model, creating gentle shadows on checkerboard - Fill: Ambient fill to prevent harsh contrast while maintaining drama - Floor Treatment: Subtle specular highlights on floor tiles for luxury sheen (not glossy/mirror-like) - Background: Pure white or subtle gradient to white at horizon line – maintains clean editorial feel PHASE 7: TECHNICAL EXECUTION - Mood: Playful luxury – sophisticated but not stiff, energetic but refined - Composition Rule: Dynamic diagonal lines (floor perspective) + vertical anchor (model) + horizontal balance (typography) - Depth Layers: Background (white) → Typography (mid-ground) → Model (foreground) → Floor pattern (spanning all depths) - Post-Production: Magazine-cover polish with color grading that enhances brand palette TECHNICAL SPECS: - Camera Simulation: Phase One XF IQ4 150MP, 80mm lens, f/5.6 for controlled depth - Aspect Ratio: 4:5 (Instagram editorial) or 3:4 (print campaign) - Resolution: 8K output, print-ready sharpness - Color Space: sRGB with vibrant saturation for digital, slight desaturation for luxury print feel - Style Reference: Gucci campaigns by Glen Luchford, Prada visuals, Highsnobiety x luxury collabs, Vogue Italia editorials - Rendering: Photorealistic model and floor, graphic-design-quality typography (hybrid 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": "[BRAND NAME]. Act as a Fashion Photographer and Graphic Designer specializing in luxury brand campaign visuals with integrated typography and surreal spatial design. PHASE 1: SPATIAL CONCEPT Create a high-fashion editorial image where architecture and graphic design merge into a theatrical stage. The foundation is a bold geometric floor pattern that extends into forced perspective, creating infinite depth and visual drama. This is not a neutral backdrop – the floor is a protagonist that amplifies brand identity through pattern, color, and spatial illusion. PHASE 2: CHECKERBOARD ARCHITECTURE - Surface: Checkerboard/geometric tile pattern rendered in brand-relevant colors - Perspective: Aggressive forced perspective starting from bottom foreground and receding toward horizon (vanishing point at upper third of frame) - Pattern Logic: Autonomously determine pattern based on [BRAND NAME]: - Color Palette: Incorporate 2-3 signature colors of [BRAND NAME] into floor pattern while maintaining readability - Texture: Photorealistic rendering with subtle reflections and shadows for depth PHASE 3: MODEL & STYLING - Subject: One fashion model (gender-fluid casting) captured mid-motion – dynamic pose suggesting walking, running, or dancing - Outfit: Elevated monochrome look (black, white, or brand-neutral tone) to let floor pattern and typography dominate. Include 1-2 key accessories in [BRAND NAME]'s signature color as hero product focal points - Pose Energy: 70% movement, 30% control – fashion-forward but grounded (avoid floating/unnatural levitation) - Placement: Model positioned in lower-mid frame, interacting spatially with both floor perspective and typography layer - Camera Angle: Low-to-mid angle (waist-to-full body shot) to emphasize floor perspective drama PHASE 4: TYPOGRAPHY INTEGRATION - Brand Script: Oversized handwritten/script version of [BRAND NAME] rendered as flat graphic element behind or around the model - Scale: Typography should be 40-60% of frame width – bold and unmissable but not crushing the model - Color: Signature brand color (autonomously selected), solid fill with clean edges - Interaction: Typography appears to \"sit\" in the space – model may partially overlap letters, creating layering hierarchy - Logo Lockup: Clean, small brand logo centered in upper portion of frame (10-15% of width) in black or brand color - Treatment: Pure vector aesthetic – no gradients, no shadows, no dimensional effects. Flat color only. PHASE 5: COLOR ORCHESTRATION (AUTONOMOUS) Autonomously research and apply [BRAND NAME]'s iconic color system: - Primary: Identify 1-2 hero brand colors (e.g., Gucci → forest green + red, Tiffany → robin egg blue) - Application: Use primary colors in floor pattern AND typography for visual cohesion - Balance: 60% white/neutral space, 30% brand color saturation, 10% black for anchoring - Accent: Hero product (bag, shoes, accessory) should echo brand color for strategic eye-pull PHASE 6: LIGHTING & ATMOSPHERE - Lighting Setup: High-key fashion lighting with soft shadows – think editorial studio quality - Key Light: 45° front-left to sculpt model, creating gentle shadows on checkerboard - Fill: Ambient fill to prevent harsh contrast while maintaining drama - Floor Treatment: Subtle specular highlights on floor tiles for luxury sheen (not glossy/mirror-like) - Background: Pure white or subtle gradient to white at horizon line – maintains clean editorial feel PHASE 7: TECHNICAL EXECUTION - Mood: Playful luxury – sophisticated but not stiff, energetic but refined - Composition Rule: Dynamic diagonal lines (floor perspective) + vertical anchor (model) + horizontal balance (typography) - Depth Layers: Background (white) → Typography (mid-ground) → Model (foreground) → Floor pattern (spanning all depths) - Post-Production: Magazine-cover polish with color grading that enhances brand palette TECHNICAL SPECS: - Camera Simulation: Phase One XF IQ4 150MP, 80mm lens, f/5.6 for controlled depth - Aspect Ratio: 4:5 (Instagram editorial) or 3:4 (print campaign) - Resolution: 8K output, print-ready sharpness - Color Space: sRGB with vibrant saturation for digital, slight desaturation for luxury print feel - Style Reference: Gucci campaigns by Glen Luchford, Prada visuals, Highsnobiety x luxury collabs, Vogue Italia editorials - Rendering: Photorealistic model and floor, graphic-design-quality typography (hybrid aesthetic)"
}
JSON
Create a 2x2 grid image. In each frame include a medium shot, closeup shot, high angle looking down and extreme low angle view looking up from the sneakers. Utilize a fish eye lens perspective in each frame as well as an aesthetic pose with foreshortening. The character is wearing a dark red bomber jacket, blue jeans and white nike high top sneakers and posing with a different wacky facial expression in each frame. Include white doodle hand drawn elements around them in each frame. Studio photography against a dark blue background. Ensure the background encompasses the entire background, no circular framing.
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 2x2 grid image. In each frame include a medium shot, closeup shot, high angle looking down and extreme low angle view looking up from the sneakers. Utilize a fish eye lens perspective in each frame as well as an aesthetic pose with foreshortening. The character is wearing a dark red bomber jacket, blue jeans and white nike high top sneakers and posing with a different wacky facial expression in each frame. Include white doodle hand drawn elements around them in each frame. Studio photography against a dark blue background. Ensure the background encompasses the entire background, no circular framing."
}
JSON
A hand-drawn treasure map on aged parchment, with the adventure erupting into three-dimensional quest. {STARTING_POINT} rises at the map's edge with {DEPARTURE_SCENE}, the dotted path becomes an actual trail traversing {TERRAIN_1} with {DANGER_1}, passing {LANDMARK_1} where {OBSTACLE_1} awaits. {TERRAIN_2} features {WILDLIFE_1} and {ENVIRONMENTAL_HAZARD}. The X marking the spot glows beneath {FINAL_LOCATION}, treasure partially visible, {GUARDIAN_ELEMENT} protecting it. Miniature expedition party frozen mid-journey at various points along the route. Torn edges of the map become cliffs. Coffee stains become lakes. Burn marks become scorched earth from battles past. Candlelight flicker, adventure novel lighting, 8K, the map as the story it promises.
curl -X POST https://runapi.ai/api/v1/nano_banana/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "nano-banana-2",
"prompt": "A hand-drawn treasure map on aged parchment, with the adventure erupting into three-dimensional quest. {STARTING_POINT} rises at the map's edge with {DEPARTURE_SCENE}, the dotted path becomes an actual trail traversing {TERRAIN_1} with {DANGER_1}, passing {LANDMARK_1} where {OBSTACLE_1} awaits. {TERRAIN_2} features {WILDLIFE_1} and {ENVIRONMENTAL_HAZARD}. The X marking the spot glows beneath {FINAL_LOCATION}, treasure partially visible, {GUARDIAN_ELEMENT} protecting it. Miniature expedition party frozen mid-journey at various points along the route. Torn edges of the map become cliffs. Coffee stains become lakes. Burn marks become scorched earth from battles past. Candlelight flicker, adventure novel lighting, 8K, the map as the story it promises."
}
JSON
Use a user-uploaded image as the source and convert the person into a stylized 3D character while preserving identity, facial structure, pose, hairstyle, clothing, and overall composition exactly as shown in the photo. The result should clearly resemble the real person. The visual style is a stylized 3D character with a soft minimal cartoon 3D aesthetic, inspired by Pixar-like visuals but more minimal, toy-figure renders, and clean product-style character design. The balance should favor stylization over realism without changing the person’s real-world appearance. Skin should appear as smooth matte plastic with a soft, uniform texture and gentle subsurface scattering. Facial features should remain faithful to the original image while being simplified in form. The expression should stay neutral and natural to the source photo. Lighting should be clean and controlled, similar to a studio softbox setup, with very soft shadows, low contrast, and subtle highlights. The background should be a solid [BACKGROUND COLOR] with no gradient. The camera should feel front-facing with a medium close-up framing, similar to a 50mm lens, with no distortion. Output quality should be high resolution with clean edges, no noise, strong style consistency, and a clearly non-photorealistic finish.
curl -X POST https://runapi.ai/api/v1/nano_banana/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "nano-banana-2",
"prompt": "Use a user-uploaded image as the source and convert the person into a stylized 3D character while preserving identity, facial structure, pose, hairstyle, clothing, and overall composition exactly as shown in the photo. The result should clearly resemble the real person. The visual style is a stylized 3D character with a soft minimal cartoon 3D aesthetic, inspired by Pixar-like visuals but more minimal, toy-figure renders, and clean product-style character design. The balance should favor stylization over realism without changing the person’s real-world appearance. Skin should appear as smooth matte plastic with a soft, uniform texture and gentle subsurface scattering. Facial features should remain faithful to the original image while being simplified in form. The expression should stay neutral and natural to the source photo. Lighting should be clean and controlled, similar to a studio softbox setup, with very soft shadows, low contrast, and subtle highlights. The background should be a solid [BACKGROUND COLOR] with no gradient. The camera should feel front-facing with a medium close-up framing, similar to a 50mm lens, with no distortion. Output quality should be high resolution with clean edges, no noise, strong style consistency, and a clearly non-photorealistic finish."
}
JSON
Ultra-realistic studio portrait of a man, close-up headshot, centered composition, neutral expression, sharp facial details, textured skin, clean grooming, wearing a black turtleneck and dark tailored coat, modern minimalist fashion, monochrome black and white photography style, only the glasses in color (Translucent amber-orange frame and lenses ), high contrast lighting, soft studio light, cinematic shadows, editorial fashion photography, plain light background, 85mm lens, shallow depth of field, ultra detailed, photorealistic, magazine quality, 8K.
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 studio portrait of a man, close-up headshot, centered composition, neutral expression, sharp facial details, textured skin, clean grooming, wearing a black turtleneck and dark tailored coat, modern minimalist fashion, monochrome black and white photography style, only the glasses in color (Translucent amber-orange frame and lenses ), high contrast lighting, soft studio light, cinematic shadows, editorial fashion photography, plain light background, 85mm lens, shallow depth of field, ultra detailed, photorealistic, magazine quality, 8K."
}
JSON
A hyperrealistic premium product photography scene of a transparent cosmetic jar labeled “MARINE LIFE” mango and passionfruit body scrub exploding open mid-air, with the white lid floating slightly above the jar and a thick, whipped, golden-yellow scrub bursting upward in a dramatic splash, glossy and textured with visible black passionfruit seeds, surrounded by suspended mango cubes, scored mango halves, and halved passionfruits with glistening pulp, golden liquid droplets and splashes frozen in motion around the jar, the container tilted slightly to the right and centered in frame, shot from a straight-on macro perspective, illuminated by soft yet high-contrast studio lighting from above and slightly behind to create glowing highlights on the wet textures and translucent splashes, subtle shadows beneath the floating elements, a smooth warm beige gradient background enhancing the tropical color palette of saturated yellows, oranges, and deep purple fruit tones, ultra-sharp focus on the jar and scrub with shallow depth of field for the outer fruit, cinematic realism, luxury skincare advertising aesthetic, crisp reflections, 8K photorealistic detail, energetic and fresh mood.
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 hyperrealistic premium product photography scene of a transparent cosmetic jar labeled “MARINE LIFE” mango and passionfruit body scrub exploding open mid-air, with the white lid floating slightly above the jar and a thick, whipped, golden-yellow scrub bursting upward in a dramatic splash, glossy and textured with visible black passionfruit seeds, surrounded by suspended mango cubes, scored mango halves, and halved passionfruits with glistening pulp, golden liquid droplets and splashes frozen in motion around the jar, the container tilted slightly to the right and centered in frame, shot from a straight-on macro perspective, illuminated by soft yet high-contrast studio lighting from above and slightly behind to create glowing highlights on the wet textures and translucent splashes, subtle shadows beneath the floating elements, a smooth warm beige gradient background enhancing the tropical color palette of saturated yellows, oranges, and deep purple fruit tones, ultra-sharp focus on the jar and scrub with shallow depth of field for the outer fruit, cinematic realism, luxury skincare advertising aesthetic, crisp reflections, 8K photorealistic detail, energetic and fresh mood."
}
JSON
Create a moody, ethereal cinematic portrait of a woman with a dramatic over-the-shoulder pose. 1. Pose and Expression • Perspective: subject positioned with her back facing the camera, torso elegantly twisted, looking back over her shoulder, creating a graceful curve along the spine and highlighting shoulder blades • Gaze: direct eye contact with the camera, piercing yet soft expression, chin slightly tucked toward shoulder to evoke intimacy and mystery • Hand Placement: hands gently raised near chest/shoulder, fingers softly interlaced or delicately touching • Hair: loose messy bun with soft wispy strands falling naturally across the face, slightly windswept look 2. Lighting and Color Palette • Lighting: strong side lighting, warm golden-hour sunlight, high contrast chiaroscuro effect, one side illuminated while the other fades into deep shadow • Skin Tone: luminous, glowing, pearlescent skin texture • Color Scheme: earthy muted tones, deep greens, dark browns, soft neutral background, warm skin tones as focal point 3. Wardrobe and Accessories • Outfit: backless silky dress or top, smooth light fabric, paired with dark voluminous sleeves for strong texture contrast • Accessories: elegant drop pearl earrings reflecting light subtly 4. Composition and Atmosphere • Framing: medium close-up shot, framed naturally with blurred foreground leaves for a voyeuristic, through-the-foliage effect • Depth of Field: shallow depth of field, sharp focus on face, soft bokeh in background and foreground • Mood: cinematic, melancholic, romantic, high-fashion editorial style, soft dreamy atmosphere Face reference: soft oval face, smooth glowing skin, symmetrical features, natural makeup, gentle but expressive eyes, slightly parted lips
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 moody, ethereal cinematic portrait of a woman with a dramatic over-the-shoulder pose. 1. Pose and Expression • Perspective: subject positioned with her back facing the camera, torso elegantly twisted, looking back over her shoulder, creating a graceful curve along the spine and highlighting shoulder blades • Gaze: direct eye contact with the camera, piercing yet soft expression, chin slightly tucked toward shoulder to evoke intimacy and mystery • Hand Placement: hands gently raised near chest/shoulder, fingers softly interlaced or delicately touching • Hair: loose messy bun with soft wispy strands falling naturally across the face, slightly windswept look 2. Lighting and Color Palette • Lighting: strong side lighting, warm golden-hour sunlight, high contrast chiaroscuro effect, one side illuminated while the other fades into deep shadow • Skin Tone: luminous, glowing, pearlescent skin texture • Color Scheme: earthy muted tones, deep greens, dark browns, soft neutral background, warm skin tones as focal point 3. Wardrobe and Accessories • Outfit: backless silky dress or top, smooth light fabric, paired with dark voluminous sleeves for strong texture contrast • Accessories: elegant drop pearl earrings reflecting light subtly 4. Composition and Atmosphere • Framing: medium close-up shot, framed naturally with blurred foreground leaves for a voyeuristic, through-the-foliage effect • Depth of Field: shallow depth of field, sharp focus on face, soft bokeh in background and foreground • Mood: cinematic, melancholic, romantic, high-fashion editorial style, soft dreamy atmosphere Face reference: soft oval face, smooth glowing skin, symmetrical features, natural makeup, gentle but expressive eyes, slightly parted lips"
}
JSON
A high-quality photo collage featuring the same person with identical facial features and expression, shown in multiple frames with different hairstyles. Each panel displays a unique hairstyle such as long straight hair, high ponytail, messy bun, pixie cut, braided crown, soft waves, short bob with bangs, low bun, side braid, and loose curls. Consistent neutral outfit and makeup across all images, soft studio lighting, warm blurred background, realistic skin texture, symmetrical face consistency, ultra-detailed, editorial beauty look, 4x3 grid layout, professional portrait photograph
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-quality photo collage featuring the same person with identical facial features and expression, shown in multiple frames with different hairstyles. Each panel displays a unique hairstyle such as long straight hair, high ponytail, messy bun, pixie cut, braided crown, soft waves, short bob with bangs, low bun, side braid, and loose curls. Consistent neutral outfit and makeup across all images, soft studio lighting, warm blurred background, realistic skin texture, symmetrical face consistency, ultra-detailed, editorial beauty look, 4x3 grid layout, professional portrait photograph"
}
JSON
A high-end commercial food photograph of the same two tacos from the reference image, preserving their exact structure, fillings, proportions, and arrangement. The camera angle is slightly adjusted to a more flattering three-quarter close-up, enhancing depth and appetite appeal without altering the tacos themselves. Soft cinematic lighting highlights the textures of the tortillas and fillings, with subtle steam and natural sheen to emphasize freshness. The background is replaced with a clean, modern, out-of-focus setting in warm complementary tones that enhance the food without distracting from it. Shallow depth of field, crisp focus on the tacos, rich contrast, natural colors, and premium restaurant advertising quality. No added or removed ingredients, refined composition, lighting, and environment. Image 2: Exploded-view commercial visualization of the taco from the image, presented as premium recipe-style breakdown. The taco is deconstructed into four visible ingredients, matching the original taco precisely in composition, color, and texture. No additional ingredients. The ingredients are separated and arranged in a clean vertical stack, evenly spaced from bottom to top, floating in place with precise alignment and symmetry. Ingredient order (bottom → top): Soft wheat taco tortilla Shredded red cabbage Grilled chicken pieces Sauce with garnish (topped with a small mixed garnish of diced onion, tomato, and parsley, approximately 5–6 small cubes total, lightly mixed, placed naturally on top) Each ingredient is visually distinct and clearly readable in shape and texture. Annotation design requirements: – Large, bold sans-serif font, high legibility at feed scale – Each annotation placed inside a solid or softly rounded rectangular color block – Background color of each block corresponds subtly to the ingredient color (tomato red, lettuce green, meat warm brown, sauce white/cream, pita beige) – High contrast text (dark on light, light on dark) – Thick, clean connector lines pointing clearly to each ingredient – No transparency that reduces readability – Annotations must visually dominate over background without covering ingredients Background is soft, neutral, and atmospheric, with subtle depth and gentle gradients, inspired by premium food advertising. Overall style is clean, modern, and appetizing, commercial-ready without technical or schematic feel. No extra elements, no substitutions, no reinterpretation of ingredients.
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-end commercial food photograph of the same two tacos from the reference image, preserving their exact structure, fillings, proportions, and arrangement. The camera angle is slightly adjusted to a more flattering three-quarter close-up, enhancing depth and appetite appeal without altering the tacos themselves. Soft cinematic lighting highlights the textures of the tortillas and fillings, with subtle steam and natural sheen to emphasize freshness. The background is replaced with a clean, modern, out-of-focus setting in warm complementary tones that enhance the food without distracting from it. Shallow depth of field, crisp focus on the tacos, rich contrast, natural colors, and premium restaurant advertising quality. No added or removed ingredients, refined composition, lighting, and environment. Image 2: Exploded-view commercial visualization of the taco from the image, presented as premium recipe-style breakdown. The taco is deconstructed into four visible ingredients, matching the original taco precisely in composition, color, and texture. No additional ingredients. The ingredients are separated and arranged in a clean vertical stack, evenly spaced from bottom to top, floating in place with precise alignment and symmetry. Ingredient order (bottom → top): Soft wheat taco tortilla Shredded red cabbage Grilled chicken pieces Sauce with garnish (topped with a small mixed garnish of diced onion, tomato, and parsley, approximately 5–6 small cubes total, lightly mixed, placed naturally on top) Each ingredient is visually distinct and clearly readable in shape and texture. Annotation design requirements: – Large, bold sans-serif font, high legibility at feed scale – Each annotation placed inside a solid or softly rounded rectangular color block – Background color of each block corresponds subtly to the ingredient color (tomato red, lettuce green, meat warm brown, sauce white/cream, pita beige) – High contrast text (dark on light, light on dark) – Thick, clean connector lines pointing clearly to each ingredient – No transparency that reduces readability – Annotations must visually dominate over background without covering ingredients Background is soft, neutral, and atmospheric, with subtle depth and gentle gradients, inspired by premium food advertising. Overall style is clean, modern, and appetizing, commercial-ready without technical or schematic feel. No extra elements, no substitutions, no reinterpretation of ingredients."
}
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.