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
Create a portrait without changing the facial features. A black and white artistic photograph of a man in a noir style. The man is sitting on a metal staircase or balcony with a cityscape in the background. He is wearing a dark shirt with an open collar, dark trousers, chunky sneakers, and sunglasses. Accessories are visible on his hands, including a bracelet. His pose is relaxed, with his gaze directed downward. The lighting is high contrast with deep shadows. The atmosphere reflects a 90s megacity, with strong film grain, street fashion aesthetics, and a grunge mood. High contrast lighting, film grain, 90s street style aesthetic, gritty noir atmosphere, grainy texture, 35mm film 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": "Create a portrait without changing the facial features. A black and white artistic photograph of a man in a noir style. The man is sitting on a metal staircase or balcony with a cityscape in the background. He is wearing a dark shirt with an open collar, dark trousers, chunky sneakers, and sunglasses. Accessories are visible on his hands, including a bracelet. His pose is relaxed, with his gaze directed downward. The lighting is high contrast with deep shadows. The atmosphere reflects a 90s megacity, with strong film grain, street fashion aesthetics, and a grunge mood. High contrast lighting, film grain, 90s street style aesthetic, gritty noir atmosphere, grainy texture, 35mm film look."
}
JSON
Create a hyper-realistic macro photograph of a miniature surreal scene. The environment is dominated by a giant, oversized <everyday object>, which has been repurposed as a bustling landscape. Tiny, highly detailed miniature human figures are interacting around and on the object. Shot on an 85mm macro lens with a shallow depth of field (f/1.8) to heavily blur the distant background. Lighting is soft, directional, and casts appropriate micro-shadows to emphasize the massive scale of the object relative to the figures. Intricate environmental details like dust particles and surface scratches are visible on the object. Cinematic, photorealistic, 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": "Create a hyper-realistic macro photograph of a miniature surreal scene. The environment is dominated by a giant, oversized <everyday object>, which has been repurposed as a bustling landscape. Tiny, highly detailed miniature human figures are interacting around and on the object. Shot on an 85mm macro lens with a shallow depth of field (f/1.8) to heavily blur the distant background. Lighting is soft, directional, and casts appropriate micro-shadows to emphasize the massive scale of the object relative to the figures. Intricate environmental details like dust particles and surface scratches are visible on the object. Cinematic, photorealistic, 4K."
}
JSON
You are a world-class director of industrial visualization and a futuristic interface designer specializing in advanced visual engineering diagnostic tools. Your task is to transform the downloaded product into a futuristic visualization of the technical scanning interface, similar to the product analyzed in a high-tech laboratory diagnostic system. input: uploaded product image style: • black background with a clear white grid of the drawing • the product is made in the form of a luminous translucent X-ray frame model • clear geometry of the technical grid • Ultra-sharp white lines and edges • Minimalistic HUD interface design in sci-fi style INTERFACE ELEMENTS: • thin white lettering-callouts with pointer lines describing the components of the product • Zoom analysis field, showing a product fragment in close-up • A colored layer of the heat map of the material (red/ orange/blue) is displayed inside the zoom field. • Scan indicators such as: "THE SCAN..." "MATERIAL ANALYSIS..." "98% DATA PROCESSING" • Small loading panels and user interface diagnostic modules • luminous markers in the form of angular frames around the image VISUAL LANGUAGE: • Advanced engineering drawing design • Futuristic laboratory scanning interface • Engineering visualization of the product at the Apple level • Ultra-pure composition • High-contrast black and white interface lighting: • subtle white glow around the frame • Volumetric light beam scanning • Technical sci-fi visualization composition: • in the center of the product • Grid-aligned interface layout • Scalable analysis panel in one corner • Minimalistic but highly technical exit: Futuristic product scanning interface , visualization of technical diagnostics , technical analysis screen , ultra clean, ultra clear, 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": "You are a world-class director of industrial visualization and a futuristic interface designer specializing in advanced visual engineering diagnostic tools. Your task is to transform the downloaded product into a futuristic visualization of the technical scanning interface, similar to the product analyzed in a high-tech laboratory diagnostic system. input: uploaded product image style: • black background with a clear white grid of the drawing • the product is made in the form of a luminous translucent X-ray frame model • clear geometry of the technical grid • Ultra-sharp white lines and edges • Minimalistic HUD interface design in sci-fi style INTERFACE ELEMENTS: • thin white lettering-callouts with pointer lines describing the components of the product • Zoom analysis field, showing a product fragment in close-up • A colored layer of the heat map of the material (red/ orange/blue) is displayed inside the zoom field. • Scan indicators such as: \"THE SCAN...\" \"MATERIAL ANALYSIS...\" \"98% DATA PROCESSING\" • Small loading panels and user interface diagnostic modules • luminous markers in the form of angular frames around the image VISUAL LANGUAGE: • Advanced engineering drawing design • Futuristic laboratory scanning interface • Engineering visualization of the product at the Apple level • Ultra-pure composition • High-contrast black and white interface lighting: • subtle white glow around the frame • Volumetric light beam scanning • Technical sci-fi visualization composition: • in the center of the product • Grid-aligned interface layout • Scalable analysis panel in one corner • Minimalistic but highly technical exit: Futuristic product scanning interface , visualization of technical diagnostics , technical analysis screen , ultra clean, ultra clear, 8K"
}
JSON
A Cinematic Night Photo On A Dimly Lit Urban Overpass With A View Of The City Skyline. In The Foreground, A Young Man Leaning Casually Against A Classic 1960s Ford Mustang Fast-back In A Sleek Black Finish. The Car's Muscu-lar Lines Are Accentuated By The Wet Asphalt Reflecting Neon Signs From Nearby Buildings. The Young Man Is Wearing A Black Trucker Jacket, A Simple Casual T-shirt, Loose Cargo Pants, And Converse Shoes. His Pose Is Re-laxed, One Hand In His Pocket, Looking Di-rectly At The Camera With A Cool, Confident Expression. The Shooting Style Uses A Fujifilm Camera With Soft Cinematic Color Tones, A Slight Fine Grain, And Deep Shadows. The Dominant Color Tone Is A Moody Blue-teal, With High-lights From Warm Streetlights Creating A Dramatic Contrast. The Depth Of Field Is Shal-low, With Sharp Focus On The Young Man And The Mustang, While The City Lights In The Background Blur Into Soft, Cinematic Bokeн, Evoking The Aesthetic Of A Modern Analog Film Snapshot.
curl -X POST https://runapi.ai/api/v1/nano_banana/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "nano-banana-2",
"prompt": "A Cinematic Night Photo On A Dimly Lit Urban Overpass With A View Of The City Skyline. In The Foreground, A Young Man Leaning Casually Against A Classic 1960s Ford Mustang Fast-back In A Sleek Black Finish. The Car's Muscu-lar Lines Are Accentuated By The Wet Asphalt Reflecting Neon Signs From Nearby Buildings. The Young Man Is Wearing A Black Trucker Jacket, A Simple Casual T-shirt, Loose Cargo Pants, And Converse Shoes. His Pose Is Re-laxed, One Hand In His Pocket, Looking Di-rectly At The Camera With A Cool, Confident Expression. The Shooting Style Uses A Fujifilm Camera With Soft Cinematic Color Tones, A Slight Fine Grain, And Deep Shadows. The Dominant Color Tone Is A Moody Blue-teal, With High-lights From Warm Streetlights Creating A Dramatic Contrast. The Depth Of Field Is Shal-low, With Sharp Focus On The Young Man And The Mustang, While The City Lights In The Background Blur Into Soft, Cinematic Bokeн, Evoking The Aesthetic Of A Modern Analog Film Snapshot."
}
JSON
[BRAND NAME]: A high-end, glossy concept art magazine editorial photograph of a unique, unexpected functional object conceptualized and designed by the brand. **1. The Concept & Object (AI Invention):** Based on the design philosophy, heritage, and material vocabulary of the specified brand, the AI must invent a novel utility product (NOT standard clothing, shoes, or bags). Examples could be home goods, tech accessories, tools, or sporting equipment, reinterpretated through the brand's lens. The object should feel sculptural yet functional. **2. Materials & Details (Hyper-Premium):** The object is constructed from ultra-premium, highly tactile materials characteristic of the brand (e.g., patinated exotic leathers, brushed aerospace-grade titanium, sculpted matte ceramics, molded carbon fiber, or technical high-fashion textiles). Every detail is hyper-realistic: visible stitching, microscopic material grain, precision engravings, and complex texture contrasts. **3. Photography & Lighting (Cinematic Studio):** Shot on a medium format Phase One camera with a 100mm macro lens. Extremely shallow depth of field, with sharp focus on the hero details of the object and a creamy, smooth bokeh background. The lighting is sophisticated studio softbox lighting: gentle, enveloping fill light with precise rim lighting to accentuate contours and material textures. **4. Environment:** A seamless, impeccably clean studio cyclorama background in a pure, ultra-light pastel tone (e.g., desaturated mint, pale blush, or off-white), free of shadows. **5. Layout & UI Elements (Strict Placement):** - **Bottom Right Corner:** A small, understated, monochrome gray logo of the brand. - **Bottom Left Corner:** Small, minimalist monochrome gray text describing the invented product. The font style looks like Manrope Regular with very tight tracking (kerning) and balanced line spacing. Example format: "CONCEPT STUDY: [AI inserts invented product name]. MATERIAL: [AI inserts main materials]. SS25.
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]: A high-end, glossy concept art magazine editorial photograph of a unique, unexpected functional object conceptualized and designed by the brand. **1. The Concept & Object (AI Invention):** Based on the design philosophy, heritage, and material vocabulary of the specified brand, the AI must invent a novel utility product (NOT standard clothing, shoes, or bags). Examples could be home goods, tech accessories, tools, or sporting equipment, reinterpretated through the brand's lens. The object should feel sculptural yet functional. **2. Materials & Details (Hyper-Premium):** The object is constructed from ultra-premium, highly tactile materials characteristic of the brand (e.g., patinated exotic leathers, brushed aerospace-grade titanium, sculpted matte ceramics, molded carbon fiber, or technical high-fashion textiles). Every detail is hyper-realistic: visible stitching, microscopic material grain, precision engravings, and complex texture contrasts. **3. Photography & Lighting (Cinematic Studio):** Shot on a medium format Phase One camera with a 100mm macro lens. Extremely shallow depth of field, with sharp focus on the hero details of the object and a creamy, smooth bokeh background. The lighting is sophisticated studio softbox lighting: gentle, enveloping fill light with precise rim lighting to accentuate contours and material textures. **4. Environment:** A seamless, impeccably clean studio cyclorama background in a pure, ultra-light pastel tone (e.g., desaturated mint, pale blush, or off-white), free of shadows. **5. Layout & UI Elements (Strict Placement):** - **Bottom Right Corner:** A small, understated, monochrome gray logo of the brand. - **Bottom Left Corner:** Small, minimalist monochrome gray text describing the invented product. The font style looks like Manrope Regular with very tight tracking (kerning) and balanced line spacing. Example format: \"CONCEPT STUDY: [AI inserts invented product name]. MATERIAL: [AI inserts main materials]. SS25."
}
JSON
Editorial fashion contact sheet of a modern woman with a sharp black bob haircut wearing white oval sunglasses, a beige tailored suit over a red sweater vest and white shirt, photographed in a minimalist studio with a neutral grey backdrop. Multiple frames arranged in a 3×3 grid showing varied angles—front, side, top-down, back view—while the subject repeatedly reaches her hand toward the camera lens, creating strong depth and perspective distortion. Clean high-fashion styling, bold color contrast, soft diffused studio lighting, crisp focus, contemporary magazine aesthetic, 35mm–50mm look, ultra-sharp, high resolution.
curl -X POST https://runapi.ai/api/v1/nano_banana/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "nano-banana-2",
"prompt": "Editorial fashion contact sheet of a modern woman with a sharp black bob haircut wearing white oval sunglasses, a beige tailored suit over a red sweater vest and white shirt, photographed in a minimalist studio with a neutral grey backdrop. Multiple frames arranged in a 3×3 grid showing varied angles—front, side, top-down, back view—while the subject repeatedly reaches her hand toward the camera lens, creating strong depth and perspective distortion. Clean high-fashion styling, bold color contrast, soft diffused studio lighting, crisp focus, contemporary magazine aesthetic, 35mm–50mm look, ultra-sharp, high resolution."
}
JSON
Un storyboard limpio en cuadrícula 3×3 con nueve paneles iguales en proporción [ratio], dentro de un formato total 4:5. Usa la imagen de referencia como base del producto. Mantén exactamente el mismo producto, diseño del packaging, branding, materiales, colores, proporciones e identidad general en los nueve paneles, tal como en la referencia. El producto debe ser claramente reconocible en cada frame. La etiqueta, el logo y las proporciones deben permanecer exactamente iguales. Este storyboard es una presentación mockup de alto nivel para un portfolio de branding. El enfoque está en la forma, la composición, la materialidad y el ritmo visual, más que en el realismo o una narrativa lifestyle. El resultado debe sentirse curado, editorial y orientado al diseño. FRAME 1: Plano frontal hero del producto en un entorno de estudio limpio. Fondo neutro, composición equilibrada, presentación calmada y segura del producto. FRAME 2: Primer plano con el enfoque centrado en la parte media del producto. Se destacan la textura de la superficie, los materiales y los detalles de impresión. FRAME 3: El producto de referencia colocado en un entorno que encaja naturalmente con la marca y la categoría del producto. Escenario de estudio inspirado en los elementos de diseño y colores del producto. FRAME 4: Producto mostrado en uso o en interacción sobre un fondo de estudio neutro. Las manos y los elementos de interacción son mínimos y discretos, manteniendo el estilo del packaging. FRAME 5: Composición isométrica que muestra varios productos organizados en un orden geométrico preciso desde un ángulo isométrico superior. Todos los productos están colocados con el mismo ángulo isométrico, espaciados de forma uniforme, limpios, estructurados y gráficos. FRAME 6: Producto levitando ligeramente, inclinado sobre un fondo neutro que coincida con la paleta de colores de la imagen de referencia. La posición flotante es intencional y natural en el espacio. FRAME 7: Primerísimo primer plano centrado en un detalle específico de la etiqueta, el borde, la textura o el comportamiento del material. FRAME 8: El producto en un entorno inesperado pero estéticamente potente, con un enfoque audaz, editorial y visualmente impactante. Escenario inesperado pero altamente estilizado, basado en estudio y dirigido por diseño. Composición fuerte que eleva la marca. FRAME 9: Composición amplia que muestra el producto en uso dentro de un setup de diseño refinado. Props limpios, estilismo controlado y coherente con el resto de la serie. CÁMARA Y ESTILO: Imágenes de estudio de ultra alta calidad con apariencia de cámara real. Diferentes ángulos y encuadres en cada frame. Profundidad de campo controlada, iluminación precisa, materiales y reflejos realistas. La lógica de iluminación, la paleta de colores, el mood y el lenguaje visual deben mantenerse consistentes en los nueve paneles como una sola serie cohesionada. OUTPUT: Una cuadrícula limpia 3×3 sin bordes, sin texto, sin captions y sin marcas de agua.
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": "Un storyboard limpio en cuadrícula 3×3 con nueve paneles iguales en proporción [ratio], dentro de un formato total 4:5. Usa la imagen de referencia como base del producto. Mantén exactamente el mismo producto, diseño del packaging, branding, materiales, colores, proporciones e identidad general en los nueve paneles, tal como en la referencia. El producto debe ser claramente reconocible en cada frame. La etiqueta, el logo y las proporciones deben permanecer exactamente iguales. Este storyboard es una presentación mockup de alto nivel para un portfolio de branding. El enfoque está en la forma, la composición, la materialidad y el ritmo visual, más que en el realismo o una narrativa lifestyle. El resultado debe sentirse curado, editorial y orientado al diseño. FRAME 1: Plano frontal hero del producto en un entorno de estudio limpio. Fondo neutro, composición equilibrada, presentación calmada y segura del producto. FRAME 2: Primer plano con el enfoque centrado en la parte media del producto. Se destacan la textura de la superficie, los materiales y los detalles de impresión. FRAME 3: El producto de referencia colocado en un entorno que encaja naturalmente con la marca y la categoría del producto. Escenario de estudio inspirado en los elementos de diseño y colores del producto. FRAME 4: Producto mostrado en uso o en interacción sobre un fondo de estudio neutro. Las manos y los elementos de interacción son mínimos y discretos, manteniendo el estilo del packaging. FRAME 5: Composición isométrica que muestra varios productos organizados en un orden geométrico preciso desde un ángulo isométrico superior. Todos los productos están colocados con el mismo ángulo isométrico, espaciados de forma uniforme, limpios, estructurados y gráficos. FRAME 6: Producto levitando ligeramente, inclinado sobre un fondo neutro que coincida con la paleta de colores de la imagen de referencia. La posición flotante es intencional y natural en el espacio. FRAME 7: Primerísimo primer plano centrado en un detalle específico de la etiqueta, el borde, la textura o el comportamiento del material. FRAME 8: El producto en un entorno inesperado pero estéticamente potente, con un enfoque audaz, editorial y visualmente impactante. Escenario inesperado pero altamente estilizado, basado en estudio y dirigido por diseño. Composición fuerte que eleva la marca. FRAME 9: Composición amplia que muestra el producto en uso dentro de un setup de diseño refinado. Props limpios, estilismo controlado y coherente con el resto de la serie. CÁMARA Y ESTILO: Imágenes de estudio de ultra alta calidad con apariencia de cámara real. Diferentes ángulos y encuadres en cada frame. Profundidad de campo controlada, iluminación precisa, materiales y reflejos realistas. La lógica de iluminación, la paleta de colores, el mood y el lenguaje visual deben mantenerse consistentes en los nueve paneles como una sola serie cohesionada. OUTPUT: Una cuadrícula limpia 3×3 sin bordes, sin texto, sin captions y sin marcas de agua."
}
JSON
A double exposure, long exposure editorial photograph of a man Use image for face reference in a brown hooded utility jacket with sharp facial features and curly blonde hair. Apply a digital glitch distortion effect with chromatic aberration (cyan and magenta color fringing), horizontal scan lines, and pixel sorting across the motion trails. Clean white backdrop, cinematic lighting, 35mm lens, high resolution, muted natural colors with tech-inspired digital artifacts."
curl -X POST https://runapi.ai/api/v1/nano_banana/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "nano-banana-2",
"prompt": "A double exposure, long exposure editorial photograph of a man Use image for face reference in a brown hooded utility jacket with sharp facial features and curly blonde hair. Apply a digital glitch distortion effect with chromatic aberration (cyan and magenta color fringing), horizontal scan lines, and pixel sorting across the motion trails. Clean white backdrop, cinematic lighting, 35mm lens, high resolution, muted natural colors with tech-inspired digital artifacts.\""
}
JSON
mobile phone photo, CCD camera aesthetic, on-camera flash photography, harsh direct flash with hard shadows cast on convenience store refrigerator glass behind them, soft film grain texture, aspect ratio 9:16, centered composition, upper body portrait bust shot of TWO women, low angle shot looking up, from chest up including shoulders and collarbones, TWO Korean women, Rosé and Lisa from BLACKPINK, gorgeous off-duty K-pop female idols, convenience store at 3AM, both caught by sudden camera flash, IMPORTANT — SKIN QUALITY FOR BOTH WOMEN: milky luminous flawless skin, creamy smooth porcelain complexion with subtle inner glow, perfectly even skin tone, zero visible pores zero blemishes, soft-focus skin surface like milk poured over glass, skin so smooth it almost glows under the flash, flash light bouncing off silky-smooth skin creating clean bright highlights with no texture interruption, baby-soft flawless dewy finish, WOMAN A (ROSÉ - front, facing camera, leaning back against refrigerator glass door): 23 years old, innocent-sexy pure-and-seductive type, slim oval face with delicate jawline, slightly hooded monolid eyes wide open with prominent sparkly aegyo-sal under-eye fat pads highlighted with subtle shimmer, light peach-brown eyeshadow clean and fresh, long natural curled lashes, signature pale strawberry blonde long straight hair one side tucked behind ear exposing full neck line, cold-toned milky white flawless skin with soft rosy flush on cheeks, wearing black satin spaghetti-strap camisole with low neckline fabric clinging to full bust with silky flash reflection, oversized black leather biker jacket slipped down to both elbows completely exposing both bare shoulders collarbones and thin straps, delicate silver chain necklace catching flash, head tilted slightly back and toward Lisa, cute playful expression — pouty lips and wide innocent eyes, WOMAN B (LISA - behind Rosé, pressed against her back, partially hidden): 21 years old, innocent-sexy type, distinct doll-like face with fuller cheeks, large round double-eyelid almond eyes with full aegyo-sal, cold direct unblinking stare into camera with subtle displeasure, lips closed and slightly pouting with faint pink lip gloss, jet black medium hair with her iconic thick flat air bangs clinging to forehead, several dark strands draped across Rosé's bare shoulder, warm-toned milky fair flawless skin, wearing white oversized thin t-shirt with stretched-out neckline slipping off one shoulder revealing black bralette strap, her chin resting directly on Rosé's bare shoulder skin-to-skin contact, one arm wrapped around Rosé's waist with fingers lightly gripping the hem of the satin camisole, half her face hidden behind Rosé's shoulder, faces less than 5cm apart but not touching, convenience store at 3AM, refrigerator glass door behind them glowing with cold white internal LED, blurred beer cans visible through glass, overhead fluorescent lights with greenish tint, on-camera flash hitting Rosé fully and Lisa partially, harsh flash shadow on refrigerator glass, CCD camera look with soft fine film grain, no full body, no legs, no extra people, no text, no watermark, no identical faces, no visible pores, no rough skin 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": "mobile phone photo, CCD camera aesthetic, on-camera flash photography, harsh direct flash with hard shadows cast on convenience store refrigerator glass behind them, soft film grain texture, aspect ratio 9:16, centered composition, upper body portrait bust shot of TWO women, low angle shot looking up, from chest up including shoulders and collarbones, TWO Korean women, Rosé and Lisa from BLACKPINK, gorgeous off-duty K-pop female idols, convenience store at 3AM, both caught by sudden camera flash, IMPORTANT — SKIN QUALITY FOR BOTH WOMEN: milky luminous flawless skin, creamy smooth porcelain complexion with subtle inner glow, perfectly even skin tone, zero visible pores zero blemishes, soft-focus skin surface like milk poured over glass, skin so smooth it almost glows under the flash, flash light bouncing off silky-smooth skin creating clean bright highlights with no texture interruption, baby-soft flawless dewy finish, WOMAN A (ROSÉ - front, facing camera, leaning back against refrigerator glass door): 23 years old, innocent-sexy pure-and-seductive type, slim oval face with delicate jawline, slightly hooded monolid eyes wide open with prominent sparkly aegyo-sal under-eye fat pads highlighted with subtle shimmer, light peach-brown eyeshadow clean and fresh, long natural curled lashes, signature pale strawberry blonde long straight hair one side tucked behind ear exposing full neck line, cold-toned milky white flawless skin with soft rosy flush on cheeks, wearing black satin spaghetti-strap camisole with low neckline fabric clinging to full bust with silky flash reflection, oversized black leather biker jacket slipped down to both elbows completely exposing both bare shoulders collarbones and thin straps, delicate silver chain necklace catching flash, head tilted slightly back and toward Lisa, cute playful expression — pouty lips and wide innocent eyes, WOMAN B (LISA - behind Rosé, pressed against her back, partially hidden): 21 years old, innocent-sexy type, distinct doll-like face with fuller cheeks, large round double-eyelid almond eyes with full aegyo-sal, cold direct unblinking stare into camera with subtle displeasure, lips closed and slightly pouting with faint pink lip gloss, jet black medium hair with her iconic thick flat air bangs clinging to forehead, several dark strands draped across Rosé's bare shoulder, warm-toned milky fair flawless skin, wearing white oversized thin t-shirt with stretched-out neckline slipping off one shoulder revealing black bralette strap, her chin resting directly on Rosé's bare shoulder skin-to-skin contact, one arm wrapped around Rosé's waist with fingers lightly gripping the hem of the satin camisole, half her face hidden behind Rosé's shoulder, faces less than 5cm apart but not touching, convenience store at 3AM, refrigerator glass door behind them glowing with cold white internal LED, blurred beer cans visible through glass, overhead fluorescent lights with greenish tint, on-camera flash hitting Rosé fully and Lisa partially, harsh flash shadow on refrigerator glass, CCD camera look with soft fine film grain, no full body, no legs, no extra people, no text, no watermark, no identical faces, no visible pores, no rough skin texture."
}
JSON
Create a high-impact editorial studio portrait using the person from the attached reference photo as the only identity source. Preserve the subject’s facial structure, skin tone, proportions, hairstyle, age, and overall likeness exactly as in the reference image. Do not modify, enhance, reshape, beautify, or reinterpret any facial features. Absolute identity accuracy is required. The subject is framed in a medium close-up (head and shoulders), photographed from a low-angle perspective looking slightly upward to create a powerful, dominant presence. The subject’s gaze is directed off-camera, upward into space, with a serious, focused, intense expression. Wardrobe: premium black pique polo shirt with visible cotton mesh texture. The fit is sharp and tailored, deep matte black fabric, structured and clean silhouette. Background: solid vibrant orange-red studio backdrop with smooth, seamless color gradients. No patterns or texture — only rich, intense color creating a heated, dramatic atmosphere. Lighting: bold, high-contrast studio lighting dominated by orange and deep red tones. Strong directional key light creates dramatic chiaroscuro shadows that emphasize facial structure and jawline. Add a powerful rim light or edge glow separating the shoulders and head from the background. Maintain depth and dimensionality. Mood: heroic, intense, commanding, cinematic studio aesthetic. Technical quality: ultra-photorealistic, highly detailed, sharp focus on the face, visible natural skin texture and pores, no smoothing. Background gradients smooth and clean. High resolution, studio-grade quality, professional editorial 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": "Create a high-impact editorial studio portrait using the person from the attached reference photo as the only identity source. Preserve the subject’s facial structure, skin tone, proportions, hairstyle, age, and overall likeness exactly as in the reference image. Do not modify, enhance, reshape, beautify, or reinterpret any facial features. Absolute identity accuracy is required. The subject is framed in a medium close-up (head and shoulders), photographed from a low-angle perspective looking slightly upward to create a powerful, dominant presence. The subject’s gaze is directed off-camera, upward into space, with a serious, focused, intense expression. Wardrobe: premium black pique polo shirt with visible cotton mesh texture. The fit is sharp and tailored, deep matte black fabric, structured and clean silhouette. Background: solid vibrant orange-red studio backdrop with smooth, seamless color gradients. No patterns or texture — only rich, intense color creating a heated, dramatic atmosphere. Lighting: bold, high-contrast studio lighting dominated by orange and deep red tones. Strong directional key light creates dramatic chiaroscuro shadows that emphasize facial structure and jawline. Add a powerful rim light or edge glow separating the shoulders and head from the background. Maintain depth and dimensionality. Mood: heroic, intense, commanding, cinematic studio aesthetic. Technical quality: ultra-photorealistic, highly detailed, sharp focus on the face, visible natural skin texture and pores, no smoothing. Background gradients smooth and clean. High resolution, studio-grade quality, professional editorial finish"
}
JSON
A hyper-realistic, cinematic close-up of a sizzling gourmet cheeseburger. The thick, juicy beef patty features a heavy, glossy char and is blanketed in vibrant orange cheddar cheese that melts and oozes down the sides in thick, viscous streams over a toasted brioche bun. The atmosphere is dramatic and smoky, with thick wisps of white and blue steam swirling upwards, surrounded by floating bright orange sparks, glowing embers, and frozen droplets of grease suspended in the air. The lighting is high-contrast and dramatic against a deep black background, emphasizing the glistening textures. Shot with a macro lens, shallow depth of field, and 8k resolution commercial food photography style.
curl -X POST https://runapi.ai/api/v1/nano_banana/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "nano-banana-2",
"prompt": "A hyper-realistic, cinematic close-up of a sizzling gourmet cheeseburger. The thick, juicy beef patty features a heavy, glossy char and is blanketed in vibrant orange cheddar cheese that melts and oozes down the sides in thick, viscous streams over a toasted brioche bun. The atmosphere is dramatic and smoky, with thick wisps of white and blue steam swirling upwards, surrounded by floating bright orange sparks, glowing embers, and frozen droplets of grease suspended in the air. The lighting is high-contrast and dramatic against a deep black background, emphasizing the glistening textures. Shot with a macro lens, shallow depth of field, and 8k resolution commercial food photography style."
}
JSON
{ "action": "image_generation", "action_input": { "prompt": "A high-detail, 8K close-up portrait of the same woman from the previous images with the same facial features and long blonde wavy hair. She is captured in a moment of genuine, joyful laughter with her head slightly tilted back and eyes closed. She is wearing a crisp white button-down social shirt with a small black lapel microphone attached. The background is a minimalist, smooth light gray studio wall. The lighting is soft and professional, highlighting the texture of the fabric and the natural details of her expression. Cinematic quality, realistic skin textures, 2:3 aspect ratio.", "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": "{ \"action\": \"image_generation\", \"action_input\": { \"prompt\": \"A high-detail, 8K close-up portrait of the same woman from the previous images with the same facial features and long blonde wavy hair. She is captured in a moment of genuine, joyful laughter with her head slightly tilted back and eyes closed. She is wearing a crisp white button-down social shirt with a small black lapel microphone attached. The background is a minimalist, smooth light gray studio wall. The lighting is soft and professional, highlighting the texture of the fabric and the natural details of her expression. Cinematic quality, realistic skin textures, 2:3 aspect ratio.\", \"aspect_ratio\": \"2:3\" } }"
}
JSON
{ "prompt": "Ultra-realistic high-end fashion editorial portrait of an adult man, 100% using the uploaded reference image for exact face, identity, facial structure, and expression (no changes or stylization). The subject is leaning casually against a tall white rectangular pedestal in a minimal studio environment. Pose must match the reference exactly: body angled sideways, left hip resting on the pedestal, one hand casually placed inside the trouser pocket, the other relaxed by the thigh. One leg straight on the ground, the other slightly bent at the knee, feet crossed naturally at the ankles.\n\nHe is wearing a tailored light grey textured suit with slim-fit trousers and a matching blazer, paired with a white button-down shirt worn casually open at the collar (no tie). Black leather loafers with a visible ankle gap, clean and elegant styling.\n\nFacial details preserved from the reference: sharp masculine jawline, light stubble beard, defined cheekbones, neatly styled dark hair swept back. Expression is serious and calm, eyes looking slightly off-camera to the side.\n\nLighting is dramatic with hard side lighting from a single direction, creating strong, sharp shadows and a clear silhouette shadow of the subject projected onto the wall behind him. High-contrast light-and-shadow geometry enhances the cinematic editorial mood.\n\nBackground consists of a smooth dark grey studio wall and floor, minimalist and distraction-free, with no props other than the pedestal. Luxury fashion magazine aesthetic, ultra-sharp focus, realistic skin texture, fine fabric details, cinematic contrast. DSLR photography look with an 85mm lens, shallow depth of field, muted neutral color grading. Vertical composition, premium editorial quality, 8K photorealism.", "aspect_ratio": "4:5", "resolution": "8K", "camera_lens": "85mm", "style": "luxury fashion editorial, cinematic", "lighting": "dramatic hard side lighting, high contrast", "quality": "ultra-realistic, premium", "reference_image": "strictly use uploaded image only" }
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 high-end fashion editorial portrait of an adult man, 100% using the uploaded reference image for exact face, identity, facial structure, and expression (no changes or stylization). The subject is leaning casually against a tall white rectangular pedestal in a minimal studio environment. Pose must match the reference exactly: body angled sideways, left hip resting on the pedestal, one hand casually placed inside the trouser pocket, the other relaxed by the thigh. One leg straight on the ground, the other slightly bent at the knee, feet crossed naturally at the ankles.\\n\\nHe is wearing a tailored light grey textured suit with slim-fit trousers and a matching blazer, paired with a white button-down shirt worn casually open at the collar (no tie). Black leather loafers with a visible ankle gap, clean and elegant styling.\\n\\nFacial details preserved from the reference: sharp masculine jawline, light stubble beard, defined cheekbones, neatly styled dark hair swept back. Expression is serious and calm, eyes looking slightly off-camera to the side.\\n\\nLighting is dramatic with hard side lighting from a single direction, creating strong, sharp shadows and a clear silhouette shadow of the subject projected onto the wall behind him. High-contrast light-and-shadow geometry enhances the cinematic editorial mood.\\n\\nBackground consists of a smooth dark grey studio wall and floor, minimalist and distraction-free, with no props other than the pedestal. Luxury fashion magazine aesthetic, ultra-sharp focus, realistic skin texture, fine fabric details, cinematic contrast. DSLR photography look with an 85mm lens, shallow depth of field, muted neutral color grading. Vertical composition, premium editorial quality, 8K photorealism.\", \"aspect_ratio\": \"4:5\", \"resolution\": \"8K\", \"camera_lens\": \"85mm\", \"style\": \"luxury fashion editorial, cinematic\", \"lighting\": \"dramatic hard side lighting, high contrast\", \"quality\": \"ultra-realistic, premium\", \"reference_image\": \"strictly use uploaded image only\" }"
}
JSON
8k Ultra-Realistic Promotional Create an exquisite miniature 3D cartoon-style scene of the user-specified company, viewed from a 45° top down perspective, with the company’s most iconic building or campus at the center, surrounded by proportionally scaled product icons, cartoon figures, vehicles, and playful elements representing everyday activities. Render in Cinema 4D with refined, smoothly rounded modeling, rich PBR textures, gentle lifelike lighting, and soft shadows for a warm, polished feel, using a clean solid-color background. Integrate accurate real-time stock market data for the specified date into a minimalistic layout, displaying the company name or stock ticker at the top center in large text, the date in extra-small text, and the stock price range in medium text with clear trend icons and charts, all in the user-specified language and without text backgrounds, subtly overlapping the scene if needed. Very important: verify stock data accuracy for the given company/ticker and date before generation; if unavailable, notify the user and stop. Parameters: aspect ratio (user input, default 1:1), date (user input/current), company/ticker (user input). Example: Company – Google, Date – 01/01/2026.
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": "8k Ultra-Realistic Promotional Create an exquisite miniature 3D cartoon-style scene of the user-specified company, viewed from a 45° top down perspective, with the company’s most iconic building or campus at the center, surrounded by proportionally scaled product icons, cartoon figures, vehicles, and playful elements representing everyday activities. Render in Cinema 4D with refined, smoothly rounded modeling, rich PBR textures, gentle lifelike lighting, and soft shadows for a warm, polished feel, using a clean solid-color background. Integrate accurate real-time stock market data for the specified date into a minimalistic layout, displaying the company name or stock ticker at the top center in large text, the date in extra-small text, and the stock price range in medium text with clear trend icons and charts, all in the user-specified language and without text backgrounds, subtly overlapping the scene if needed. Very important: verify stock data accuracy for the given company/ticker and date before generation; if unavailable, notify the user and stop. Parameters: aspect ratio (user input, default 1:1), date (user input/current), company/ticker (user input). Example: Company – Google, Date – 01/01/2026."
}
JSON
8k Ultra-Realistic Promotional Generate a whimsical miniature world featuring [KASHMIR SNOWFALL LAND MARK NAME] crafted entirely from colorful modeling clay. Every element buildings, trees, waterways, and urban features should appear hand sculpted with visible fingerprints and organic clay textures. Use a playful, childlike style with vibrant colors: bright azure sky, puffy cream clouds, emerald trees, and buildings in warm yellows, oranges, reds, and blues. The handmade quality should be evident in every surface and gentle curve. Capture from a wide perspective showcasing the entire miniature landscape in a harmonious, joyful composition. Include no text, words, or signage only sculptural clay elements that define the location through recognizable architectural features. 1080x1080 dimension.
curl -X POST https://runapi.ai/api/v1/nano_banana/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "nano-banana-2",
"prompt": "8k Ultra-Realistic Promotional Generate a whimsical miniature world featuring [KASHMIR SNOWFALL LAND MARK NAME] crafted entirely from colorful modeling clay. Every element buildings, trees, waterways, and urban features should appear hand sculpted with visible fingerprints and organic clay textures. Use a playful, childlike style with vibrant colors: bright azure sky, puffy cream clouds, emerald trees, and buildings in warm yellows, oranges, reds, and blues. The handmade quality should be evident in every surface and gentle curve. Capture from a wide perspective showcasing the entire miniature landscape in a harmonious, joyful composition. Include no text, words, or signage only sculptural clay elements that define the location through recognizable architectural features. 1080x1080 dimension."
}
JSON
Ultra-detailed stylized 3D portrait using the provided reference photo lebron james as the exact facial base. Preserve the person perfectly — identical face shape, bone structure, jawline, eyes, nose, lips, skin tone, marks, freckles, expression and proportions. DO NOT modify facial identity in any way. Convert ONLY into high-end stylized 3D realism. Head & elements: Floating head only (no neck, no shoulders, no body) Keep EXACTLY whatever the person has on their head in the reference image — same hairstyle, same hair length and texture, same hat, cap, sunglasses, glasses, headphones or any accessory. Do not remove or add anything. Skin refinement: Natural smooth skin (not plastic).Visible realistic micro-texture and pores. Subtle subsurface scattering for natural light diffusion. Soft highlights on cheekbones, nose bridge and tip.Balanced realistic shadows for depth Hair & accessories (if present in reference): Ultra-realistic volumetric strands.Natural shine and soft rim reflections. Perfectly preserved shape and position Lighting: Strong cinematic purple ambient background. Soft frontal key light evenly illuminating the face. Subtle rim light separating head from background. Gentle under-chin shadow for depth. Smooth light gradients, no harsh contrast Rendering style: Premium Pixar-quality stylized realism. Clean smooth shading. Global illumination. Soft bloom on highlights. Ultra sharp edgesNoise-free professional CGI Camera & quality: Centered portrait composition. Shallow depth of field illusion. Ultra high resolution. Cinematic look Rules: Respect reference face 100%.Respect all head accessories and hair exactly. Only convert to stylized 3D. No exaggeration. No cartoon distortion. No facial changes
curl -X POST https://runapi.ai/api/v1/nano_banana/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "nano-banana-2",
"prompt": "Ultra-detailed stylized 3D portrait using the provided reference photo lebron james as the exact facial base. Preserve the person perfectly — identical face shape, bone structure, jawline, eyes, nose, lips, skin tone, marks, freckles, expression and proportions. DO NOT modify facial identity in any way. Convert ONLY into high-end stylized 3D realism. Head & elements: Floating head only (no neck, no shoulders, no body) Keep EXACTLY whatever the person has on their head in the reference image — same hairstyle, same hair length and texture, same hat, cap, sunglasses, glasses, headphones or any accessory. Do not remove or add anything. Skin refinement: Natural smooth skin (not plastic).Visible realistic micro-texture and pores. Subtle subsurface scattering for natural light diffusion. Soft highlights on cheekbones, nose bridge and tip.Balanced realistic shadows for depth Hair & accessories (if present in reference): Ultra-realistic volumetric strands.Natural shine and soft rim reflections. Perfectly preserved shape and position Lighting: Strong cinematic purple ambient background. Soft frontal key light evenly illuminating the face. Subtle rim light separating head from background. Gentle under-chin shadow for depth. Smooth light gradients, no harsh contrast Rendering style: Premium Pixar-quality stylized realism. Clean smooth shading. Global illumination. Soft bloom on highlights. Ultra sharp edgesNoise-free professional CGI Camera & quality: Centered portrait composition. Shallow depth of field illusion. Ultra high resolution. Cinematic look Rules: Respect reference face 100%.Respect all head accessories and hair exactly. Only convert to stylized 3D. No exaggeration. No cartoon distortion. No facial changes"
}
JSON
%{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.