1. claude mcp add runapi -s user -- npx -y @runapi.ai/mcp
2. 重启 Claude Code
3. 粘贴这个 prompt：生成一张图像："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. 重启 Codex
3. 粘贴这个 prompt：生成一张图像："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. 重启 Cursor
3. 粘贴这个 prompt：生成一张图像："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. 重启 Windsurf
3. 粘贴这个 prompt：生成一张图像："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_image获取 API Key
[BRAND NAME] + [COLOR] Act as a Senior CGI Artist specializing in shrink wrap simulation and 3D material rendering. Your task: render [BRAND NAME]'s complete logo — icon mark AND wordmark if the brand uses one — completely wrapped under a single layer of tight stretched plastic film or shrink wrap. The logo forms are visible only as raised shapes beneath the material, never exposed directly. BRAND INTELLIGENCE SYSTEM Before executing, resolve: (1) LOGO GEOMETRY — identify [BRAND NAME]'s complete visual identity mark — this includes both the icon symbol AND the wordmark/logotype if the brand uses them together. Render both elements as they appear in the brand's official lockup. If the brand uses only an icon with no wordmark, render the icon only. If the brand uses a wordmark without an icon, render the wordmark only. Preserve the correct spatial relationship between icon and text as it appears in the real logo, (2) COLOR SYSTEM — based on [COLOR], determine one single monochromatic tone that covers everything in the scene without exception — the wrapped object, the background surface, the film material — pure tonal unity with variation only through light and shadow, (3) FILM CHARACTER — based on [COLOR] determine the stretch film behavior: bright saturated colors become tight latex or glossy shrink wrap with visible tension lines, neutrals become matte stretch film like packaging plastic, darks become semi-transparent vacuum seal film, light colors become frosted cling wrap. PHASE 1: SCENE & SURFACE The entire scene is monochromatic — one single color [COLOR] covers every element without exception. The background is the same film material pooling and wrinkling loosely around the central wrapped object — a continuous surface of the same material with natural stress lines, crinkles, and soft folds radiating outward from where the film is pulled tightest over the logo forms. No floor line. No walls. No horizon. Just continuous film material in every direction filling the entire frame. PHASE 2: THE WRAPPED LOGO — CRITICAL [BRAND NAME]'s complete logo — resolved in the brand intelligence system — exists as solid three-dimensional inflated forms. Each element of the logo — every letter, every curve of the icon, every geometric element — is volumetrically inflated like a balloon, giving each component roundness and depth. The complete logo lockup sits on the background surface and is covered by a single continuous layer of stretch plastic film pulled tightly from above. The film conforms precisely to every raised logo element — stretching tightly over the peaks of each inflated letter and icon form, creating visible tension stress lines in the film where it is pulled most taut, and releasing into loose crinkled pools of excess material in the gaps between letters, in the negative spaces of the icon, and around the outer perimeter of the logo where the film relaxes back onto the background surface. The entire logo must remain fully legible through the film — every letter readable, the icon identifiable — but no surface of the actual logo is ever directly visible or exposed. Only the film surface exists. The physical behavior of the film must be accurate: tight stretch over high points, stress lines radiating from tension peaks, loose crinkle pools in valleys, the film slightly lifting off the surface in the spaces between raised elements creating small shadow gaps underneath. PHASE 3: LIGHTING Large soft area light from upper-left — diffused and broad. The lighting reveals the film's topography: raised logo elements catch more light on their peaks, valleys and gaps between forms fall into progressively deeper shadow, background crinkled film shows its own shadow landscape of stress lines and folds. For glossy or latex film [COLOR]: add subtle specular highlights running along the highest tension points of the film — a tight line of brighter light along the film's most stretched areas. For matte film [COLOR]: no specular, pure diffuse light only. Global illumination on — ambient light fills shadow areas enough to retain detail in the deepest folds without flattening the overall relief. TECH SPECS The entire image is one color — [COLOR] — applied to every surface with variation only through light and shadow. No other colors anywhere. No exposed logo surfaces. No additional text beyond what is part of [BRAND NAME]'s actual logo lockup. Film simulation must be physically accurate — real stretch film behavior, real tension dynamics, real crinkle patterns. No fabric look. No cloth drape. This is plastic film — it has different tension behavior than textile: tighter, more stressed, more geometric stress lines, less organic drape. Film grain: ISO 400 equivalent. Mood: a product sealed for shipping, a reveal imminent, the form known but not yet touched.
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] + [COLOR] Act as a Senior CGI Artist specializing in shrink wrap simulation and 3D material rendering. Your task: render [BRAND NAME]'s complete logo — icon mark AND wordmark if the brand uses one — completely wrapped under a single layer of tight stretched plastic film or shrink wrap. The logo forms are visible only as raised shapes beneath the material, never exposed directly. BRAND INTELLIGENCE SYSTEM Before executing, resolve: (1) LOGO GEOMETRY — identify [BRAND NAME]'s complete visual identity mark — this includes both the icon symbol AND the wordmark/logotype if the brand uses them together. Render both elements as they appear in the brand's official lockup. If the brand uses only an icon with no wordmark, render the icon only. If the brand uses a wordmark without an icon, render the wordmark only. Preserve the correct spatial relationship between icon and text as it appears in the real logo, (2) COLOR SYSTEM — based on [COLOR], determine one single monochromatic tone that covers everything in the scene without exception — the wrapped object, the background surface, the film material — pure tonal unity with variation only through light and shadow, (3) FILM CHARACTER — based on [COLOR] determine the stretch film behavior: bright saturated colors become tight latex or glossy shrink wrap with visible tension lines, neutrals become matte stretch film like packaging plastic, darks become semi-transparent vacuum seal film, light colors become frosted cling wrap. PHASE 1: SCENE & SURFACE The entire scene is monochromatic — one single color [COLOR] covers every element without exception. The background is the same film material pooling and wrinkling loosely around the central wrapped object — a continuous surface of the same material with natural stress lines, crinkles, and soft folds radiating outward from where the film is pulled tightest over the logo forms. No floor line. No walls. No horizon. Just continuous film material in every direction filling the entire frame. PHASE 2: THE WRAPPED LOGO — CRITICAL [BRAND NAME]'s complete logo — resolved in the brand intelligence system — exists as solid three-dimensional inflated forms. Each element of the logo — every letter, every curve of the icon, every geometric element — is volumetrically inflated like a balloon, giving each component roundness and depth. The complete logo lockup sits on the background surface and is covered by a single continuous layer of stretch plastic film pulled tightly from above. The film conforms precisely to every raised logo element — stretching tightly over the peaks of each inflated letter and icon form, creating visible tension stress lines in the film where it is pulled most taut, and releasing into loose crinkled pools of excess material in the gaps between letters, in the negative spaces of the icon, and around the outer perimeter of the logo where the film relaxes back onto the background surface. The entire logo must remain fully legible through the film — every letter readable, the icon identifiable — but no surface of the actual logo is ever directly visible or exposed. Only the film surface exists. The physical behavior of the film must be accurate: tight stretch over high points, stress lines radiating from tension peaks, loose crinkle pools in valleys, the film slightly lifting off the surface in the spaces between raised elements creating small shadow gaps underneath. PHASE 3: LIGHTING Large soft area light from upper-left — diffused and broad. The lighting reveals the film's topography: raised logo elements catch more light on their peaks, valleys and gaps between forms fall into progressively deeper shadow, background crinkled film shows its own shadow landscape of stress lines and folds. For glossy or latex film [COLOR]: add subtle specular highlights running along the highest tension points of the film — a tight line of brighter light along the film's most stretched areas. For matte film [COLOR]: no specular, pure diffuse light only. Global illumination on — ambient light fills shadow areas enough to retain detail in the deepest folds without flattening the overall relief. TECH SPECS The entire image is one color — [COLOR] — applied to every surface with variation only through light and shadow. No other colors anywhere. No exposed logo surfaces. No additional text beyond what is part of [BRAND NAME]'s actual logo lockup. Film simulation must be physically accurate — real stretch film behavior, real tension dynamics, real crinkle patterns. No fabric look. No cloth drape. This is plastic film — it has different tension behavior than textile: tighter, more stressed, more geometric stress lines, less organic drape. Film grain: ISO 400 equivalent. Mood: a product sealed for shipping, a reveal imminent, the form known but not yet touched."
}
JSON
A mini chibi version of the character in the uploaded image, with a big head and small body, sitting on an open left palm for realistic scale. A right hand gently pressing its cheek with an index finger. The character looks annoyed and pouty — puffed cheeks, slightly frowning, squinting eyes. Ultra-detailed chibi style, soft pastel colors, smooth texture, clean lighting, shallow depth of field, strong focus on facial expression and hand interaction, vertical composition 4:5 ratio.
curl -X POST https://runapi.ai/api/v1/nano_banana/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "nano-banana-2",
"prompt": "A mini chibi version of the character in the uploaded image, with a big head and small body, sitting on an open left palm for realistic scale. A right hand gently pressing its cheek with an index finger. The character looks annoyed and pouty — puffed cheeks, slightly frowning, squinting eyes. Ultra-detailed chibi style, soft pastel colors, smooth texture, clean lighting, shallow depth of field, strong focus on facial expression and hand interaction, vertical composition 4:5 ratio."
}
JSON
minimal studio shot on pure white background, real [Food Name] emerging from a paper packaging, the visible part outside the packaging is fully photorealistic, the continuation of the same food is drawn as a clean black line illustration printed directly on the surface of the packaging, perfectly aligned with the real food shape, the illustration stays strictly on the packaging material, not floating, not extending into the background, seamless transition between real and printed illustration, modern minimal branding, top-down composition, soft shadows
curl -X POST https://runapi.ai/api/v1/nano_banana/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "nano-banana-2",
"prompt": "minimal studio shot on pure white background, real [Food Name] emerging from a paper packaging, the visible part outside the packaging is fully photorealistic, the continuation of the same food is drawn as a clean black line illustration printed directly on the surface of the packaging, perfectly aligned with the real food shape, the illustration stays strictly on the packaging material, not floating, not extending into the background, seamless transition between real and printed illustration, modern minimal branding, top-down composition, soft shadows"
}
JSON
Hyper-realistic cinematic product photograph of a luxury sports car front three-quarter view, glossy paint reflecting sharp highlights. Water mist and rain droplets explode around the car in frozen motion, light streaks emphasizing speed. Dramatic studio lighting with strong rim light and soft fill, shallow depth of field, ultra-sharp focus, dark minimal background, premium automotive advertising realism.
curl -X POST https://runapi.ai/api/v1/nano_banana/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "nano-banana-2",
"prompt": "Hyper-realistic cinematic product photograph of a luxury sports car front three-quarter view, glossy paint reflecting sharp highlights. Water mist and rain droplets explode around the car in frozen motion, light streaks emphasizing speed. Dramatic studio lighting with strong rim light and soft fill, shallow depth of field, ultra-sharp focus, dark minimal background, premium automotive advertising realism."
}
JSON
A first-person point-of-view (POV) shot inside a modern supermarket aisle. The viewer's hands are holding a mixed fruit jam jar with colorful branding, showing a blend of strawberry, blueberry, and orange flavors. Floating around the jar are sleek, semi-transparent Augmented Reality (AR) digital interfaces and holographic HUDs. The overlays display "Flavor Mix" with fruit icons, "Nutrition Info," and a glowing "Freshness Meter" reading 9/10. A digital shopping list with checkmarks for bread and butter appears beside the jar, along with small recipe suggestions like breakfast toast, pancakes, and desserts. The background shelves are slightly blurred with other products and shoppers, creating realistic depth of field. Bright, clean lighting with a futuristic retail atmosphere, ultra-realistic, cinematic look, high-tech AR glasses perspective, vertical composition.
curl -X POST https://runapi.ai/api/v1/nano_banana/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "nano-banana-2",
"prompt": "A first-person point-of-view (POV) shot inside a modern supermarket aisle. The viewer's hands are holding a mixed fruit jam jar with colorful branding, showing a blend of strawberry, blueberry, and orange flavors. Floating around the jar are sleek, semi-transparent Augmented Reality (AR) digital interfaces and holographic HUDs. The overlays display \"Flavor Mix\" with fruit icons, \"Nutrition Info,\" and a glowing \"Freshness Meter\" reading 9/10. A digital shopping list with checkmarks for bread and butter appears beside the jar, along with small recipe suggestions like breakfast toast, pancakes, and desserts. The background shelves are slightly blurred with other products and shoppers, creating realistic depth of field. Bright, clean lighting with a futuristic retail atmosphere, ultra-realistic, cinematic look, high-tech AR glasses perspective, vertical composition."
}
JSON
A young blonde Hollywood actress, similar to Sydney Sweeney, appears inside a bathtub filled with foam up to the brim. Her blonde hair is styled in a high, voluminous, slightly messy bun, with a few loose strands softly framing her face. She looks directly at the camera with a neutral, subtly seductive expression, her lips slightly parted. She wears light, natural makeup, a delicate silver chain necklace with a small circular pendant, and small, discreet stud earrings. Her upper body faces forward, visible above the foam. She holds a large open printed newspaper with both hands at chest height, as if reading it. The newspaper is partially covered with dense white soap foam, which also gathers around her in thick, fluffy bubbles filling the bathtub. Beneath the foam and the newspaper, she is wearing a green beach top that remains completely hidden. The scene takes place inside a tiled bathtub. In the background, there is a vibrant wall completely covered with small, bright yellow square mosaic tiles. In the left corner of the composition, a slightly out-of-focus white door frame is visible, with a silver metallic doorknob. The lighting is soft, diffused, and even indoor lighting, coming from the front and slightly from above. It creates soft, flattering highlights on her face, shoulders, and hair, with very few harsh shadows. The image conveys an eccentric, artistic, editorial atmosphere that feels slightly surreal, yet calm and visually striking. The color palette highlights the bright yellow tiles, the white foam, the blonde hair, and the gray tones of the newspaper. The photograph is a modern, photorealistic editorial portrait with cinematic framing. The composition is a medium shot from the upper bust upward, at eye level, with a shallow depth of field that keeps the actress and the newspaper in sharp focus while slightly blurring the door handle in the foreground. The image is highly detailed, with crisp focus, professional lighting, vibrant high-contrast colors, and extremely high quality in 8K resolution, in a 4:5 aspect ratio.
curl -X POST https://runapi.ai/api/v1/nano_banana/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "nano-banana-2",
"prompt": "A young blonde Hollywood actress, similar to Sydney Sweeney, appears inside a bathtub filled with foam up to the brim. Her blonde hair is styled in a high, voluminous, slightly messy bun, with a few loose strands softly framing her face. She looks directly at the camera with a neutral, subtly seductive expression, her lips slightly parted. She wears light, natural makeup, a delicate silver chain necklace with a small circular pendant, and small, discreet stud earrings. Her upper body faces forward, visible above the foam. She holds a large open printed newspaper with both hands at chest height, as if reading it. The newspaper is partially covered with dense white soap foam, which also gathers around her in thick, fluffy bubbles filling the bathtub. Beneath the foam and the newspaper, she is wearing a green beach top that remains completely hidden. The scene takes place inside a tiled bathtub. In the background, there is a vibrant wall completely covered with small, bright yellow square mosaic tiles. In the left corner of the composition, a slightly out-of-focus white door frame is visible, with a silver metallic doorknob. The lighting is soft, diffused, and even indoor lighting, coming from the front and slightly from above. It creates soft, flattering highlights on her face, shoulders, and hair, with very few harsh shadows. The image conveys an eccentric, artistic, editorial atmosphere that feels slightly surreal, yet calm and visually striking. The color palette highlights the bright yellow tiles, the white foam, the blonde hair, and the gray tones of the newspaper. The photograph is a modern, photorealistic editorial portrait with cinematic framing. The composition is a medium shot from the upper bust upward, at eye level, with a shallow depth of field that keeps the actress and the newspaper in sharp focus while slightly blurring the door handle in the foreground. The image is highly detailed, with crisp focus, professional lighting, vibrant high-contrast colors, and extremely high quality in 8K resolution, in a 4:5 aspect ratio."
}
JSON
[PERSONE]. Act as a Senior Art Director. PHASE 1: PHOTOGRAPHIC COMPOSITION. - Layered Effect: Double exposure photographic collage. High-definition action shot in the foreground; massive monumental silhouette in the background. - Overlap: The subject must seamlessly integrate with the background graphics. PHASE 2: CONTEXTUAL VIBE SIMULATION. - Identity Analysis: Autonomously identify the core industry of [PERSONE] (Sport, Music, Cinema, or Business). - Pose & Props: PHASE 3: DYNAMIC COLOR & BRAND SIMULATION (VARIABLE COLORS). - Primary Color (Atmosphere): Identify the MOST ICONIC color associated with [PERSONE] or their team/brand. Use this for the background, halftone textures, and smoke. - Accent Color (Impact): Identify a secondary high-contrast VIBRANT hue (e.g., neon, gold, or electric white). Use this for the "Radial Burst" rays. - Visual Texture: Apply heavy film grain and halftone dots (screen printing effect) to the shadows of the high-res photos. PHASE 4: GRAPHIC ACCENTS. - Geometry: Bold radial rays bursting from the center. Fluid, wave-like organic shapes at the base. - Birds: Minimalist black bird silhouettes for scale and depth. PHASE 5: BRANDING & TEXT. - Tagline: Generate a powerful, one-word or two-word slogan tailored to [PERSONE]'s legacy. - Logo: Place a minimalist, industry-appropriate logo in the bottom corner. - Typography: Bold, high-impact Sans-Serif. TECHNICAL FINISH: - Quality: 8k resolution, authentic commercial photography style (NOT an illustration). - Lighting: Extreme studio rim-lighting (contour highlights) to separate the photographic subjects from the graphic layers.
curl -X POST https://runapi.ai/api/v1/nano_banana/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "nano-banana-2",
"prompt": "[PERSONE]. Act as a Senior Art Director. PHASE 1: PHOTOGRAPHIC COMPOSITION. - Layered Effect: Double exposure photographic collage. High-definition action shot in the foreground; massive monumental silhouette in the background. - Overlap: The subject must seamlessly integrate with the background graphics. PHASE 2: CONTEXTUAL VIBE SIMULATION. - Identity Analysis: Autonomously identify the core industry of [PERSONE] (Sport, Music, Cinema, or Business). - Pose & Props: PHASE 3: DYNAMIC COLOR & BRAND SIMULATION (VARIABLE COLORS). - Primary Color (Atmosphere): Identify the MOST ICONIC color associated with [PERSONE] or their team/brand. Use this for the background, halftone textures, and smoke. - Accent Color (Impact): Identify a secondary high-contrast VIBRANT hue (e.g., neon, gold, or electric white). Use this for the \"Radial Burst\" rays. - Visual Texture: Apply heavy film grain and halftone dots (screen printing effect) to the shadows of the high-res photos. PHASE 4: GRAPHIC ACCENTS. - Geometry: Bold radial rays bursting from the center. Fluid, wave-like organic shapes at the base. - Birds: Minimalist black bird silhouettes for scale and depth. PHASE 5: BRANDING & TEXT. - Tagline: Generate a powerful, one-word or two-word slogan tailored to [PERSONE]'s legacy. - Logo: Place a minimalist, industry-appropriate logo in the bottom corner. - Typography: Bold, high-impact Sans-Serif. TECHNICAL FINISH: - Quality: 8k resolution, authentic commercial photography style (NOT an illustration). - Lighting: Extreme studio rim-lighting (contour highlights) to separate the photographic subjects from the graphic layers."
}
JSON
Transform this image [Upload Your Image] into a 64K DSLR shot resolution of A stylish urban fashion collage composed of multiple candid street-style shots arranged in a vertical split layout. The setting is a European-style city street with stone-paved sidewalks, historic architecture, and muted neutral tones. The overall atmosphere feels modern, artsy, and lifestyle-driven, blending fashion photography with everyday urban moments. The main subject is a fashion-forward young woman (same face as the uploaded image) with long black hair, wearing a coordinated vintage-inspired outfit. She has a confident, playful, slightly rebellious attitude expressed through her body language and facial expressions. Her outfit consists of a brown plaid blazer, a white button-up shirt, and a pale yellow tie, paired with loose dark trousers and two-tone leather shoes. She accessories with a brown fitted cap, large amber-tinted aviator sunglasses, silver hoop earrings, and a small shoulder bag. White wireless earbuds are visible in some frames, reinforcing a casual, modern lifestyle aesthetic. Left panel: A reflective mirror shot taken through a glass surface, showing the subject (same face as the uploaded image) holding a smartphone up to her face while taking a photo. The reflection slightly distorts the scene, creating layered depth with urban elements like street markings and building facades blending into the glass. Top-right panel: A high-angle shot looking down at the subject (same face as the uploaded image) as she leans forward toward the camera, lips pursed in a playful pout, emphasizing her expressive personality and bold eyewear. Bottom-right panel: A close-up selfie angle where she looks directly into the camera while holding an iced coffee in a clear plastic cup, earbuds in, with sunlight softly illuminating her face and sunglasses. Overlayed across the center of the collage is a minimalist music player UI, semi-transparent, displaying a paused or playing track with progress bar and controls, adding a digital, lifestyle-tech aesthetic. The interface floats above the imagery, blending seamlessly with the collage and reinforcing a "day-in-the-life" mood. Lighting is natural daylight with soft shadows. The color palette is muted and earthy browns, greys, yellows-enhanced with subtle film grain and a slightly desaturated, editorial color grade. The overall mood is effortlessly cool, candid, and contemporary, mixing street fashion, music culture, and casual city exploration. Style & Quality Tags: Street-style fashion photography, lifestyle editorial, urban aesthetic, candid moments, vintage-inspired outfit, natural light, muted color grading, subtle film grain, modern collage layout, high-resolution, Instagram editorial style. Octane render & Unreal Engine 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": "Transform this image [Upload Your Image] into a 64K DSLR shot resolution of A stylish urban fashion collage composed of multiple candid street-style shots arranged in a vertical split layout. The setting is a European-style city street with stone-paved sidewalks, historic architecture, and muted neutral tones. The overall atmosphere feels modern, artsy, and lifestyle-driven, blending fashion photography with everyday urban moments. The main subject is a fashion-forward young woman (same face as the uploaded image) with long black hair, wearing a coordinated vintage-inspired outfit. She has a confident, playful, slightly rebellious attitude expressed through her body language and facial expressions. Her outfit consists of a brown plaid blazer, a white button-up shirt, and a pale yellow tie, paired with loose dark trousers and two-tone leather shoes. She accessories with a brown fitted cap, large amber-tinted aviator sunglasses, silver hoop earrings, and a small shoulder bag. White wireless earbuds are visible in some frames, reinforcing a casual, modern lifestyle aesthetic. Left panel: A reflective mirror shot taken through a glass surface, showing the subject (same face as the uploaded image) holding a smartphone up to her face while taking a photo. The reflection slightly distorts the scene, creating layered depth with urban elements like street markings and building facades blending into the glass. Top-right panel: A high-angle shot looking down at the subject (same face as the uploaded image) as she leans forward toward the camera, lips pursed in a playful pout, emphasizing her expressive personality and bold eyewear. Bottom-right panel: A close-up selfie angle where she looks directly into the camera while holding an iced coffee in a clear plastic cup, earbuds in, with sunlight softly illuminating her face and sunglasses. Overlayed across the center of the collage is a minimalist music player UI, semi-transparent, displaying a paused or playing track with progress bar and controls, adding a digital, lifestyle-tech aesthetic. The interface floats above the imagery, blending seamlessly with the collage and reinforcing a \"day-in-the-life\" mood. Lighting is natural daylight with soft shadows. The color palette is muted and earthy browns, greys, yellows-enhanced with subtle film grain and a slightly desaturated, editorial color grade. The overall mood is effortlessly cool, candid, and contemporary, mixing street fashion, music culture, and casual city exploration. Style & Quality Tags: Street-style fashion photography, lifestyle editorial, urban aesthetic, candid moments, vintage-inspired outfit, natural light, muted color grading, subtle film grain, modern collage layout, high-resolution, Instagram editorial style. Octane render & Unreal Engine 5."
}
JSON
Create an ultra-photorealistic studio portrait using the uploaded image as the ONLY identity reference. The subject must retain exact facial identity — same facial structure, proportions, skin tone, hairstyle, and natural features. Do not alter or beautify the face. The subject is wearing a sharply tailored,
curl -X POST https://runapi.ai/api/v1/nano_banana/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "nano-banana-2",
"prompt": "Create an ultra-photorealistic studio portrait using the uploaded image as the ONLY identity reference. The subject must retain exact facial identity — same facial structure, proportions, skin tone, hairstyle, and natural features. Do not alter or beautify the face. The subject is wearing a sharply tailored,"
}
JSON
[PERSONE]. Act as a Senior Editorial Designer and Graphic Artist. Goal: Generate a complex, multi-layered Swiss-style collage poster for [PERSONE]. PHASE 1: SEMANTIC INTELLIGENCE (AUTONOMOUS) [INSTRUCTIONS]: Analyze "[PERSONE]". Determine their primary field (e.g., Elite Sports, Cyber-Engineering, Cinema, History). Select an "Iconic Accent Color" based on their identity (e.g., Racing Orange for a driver, Neon Cyan for a hacker, Crimson for a hero). Generate 3 key statistics or milestones (e.g., "7 TITLES", "98% ACCURACY") and a short professional title. PHASE 2: COMPOSITIONAL STRUCTURE (THE GRID) The image is a single vertical composition with overlapping geometric frames and segments: - MAIN SUBJECT (Top Left): A large, high-grain grayscale or color portrait of [PERSONE], smiling or looking confident. - DETAIL SHOT (Center Right): A zoomed-in, cropped rectangle showing only the eyes or a specific detail of [PERSONE]. - FULL BODY SHOT (Bottom Center): [PERSONE] sitting on a geometric box or podium in a relaxed but powerful pose. - BACKGROUND: Light gray with a heavy, tactile film grain/noise texture. PHASE 3: GRAPHIC ELEMENTS & TYPOGRAPHY - Initials: Large, outlined capital letters of the first and last name placed in opposite corners. - Vertical Ribbon: A solid color strip with the text "WORLD CHAMPIONSHIP LEADER" or a relevant title running vertically through the center. - Data Blocks: - A specific number (ID or rank) in a bold sans-serif block. - A "Statistics" block in the bottom-left corner with 3 lines of text (e.g., "TWO POLES / FOUR WINS / FIVE PODIUMS"). - Accents: Scatter orange and black squares, dotted circles, and small asterisks throughout the grid for visual complexity. PHASE 4: LIGHTING & TEXTURE - Texture: High-contrast, gritty, and grainy. The overall image should look like a printed high-end magazine or a vintage poster. - Lighting: Professional studio lighting on the subjects, but processed with a "risograph" or "halftone" feel. PHASE 5: TECH SPECS 8K Resolution. Swiss Modernism aesthetic. Flat vector shapes combined with hyper-realistic photography.
curl -X POST https://runapi.ai/api/v1/nano_banana/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "nano-banana-2",
"prompt": "[PERSONE]. Act as a Senior Editorial Designer and Graphic Artist. Goal: Generate a complex, multi-layered Swiss-style collage poster for [PERSONE]. PHASE 1: SEMANTIC INTELLIGENCE (AUTONOMOUS) [INSTRUCTIONS]: Analyze \"[PERSONE]\". Determine their primary field (e.g., Elite Sports, Cyber-Engineering, Cinema, History). Select an \"Iconic Accent Color\" based on their identity (e.g., Racing Orange for a driver, Neon Cyan for a hacker, Crimson for a hero). Generate 3 key statistics or milestones (e.g., \"7 TITLES\", \"98% ACCURACY\") and a short professional title. PHASE 2: COMPOSITIONAL STRUCTURE (THE GRID) The image is a single vertical composition with overlapping geometric frames and segments: - MAIN SUBJECT (Top Left): A large, high-grain grayscale or color portrait of [PERSONE], smiling or looking confident. - DETAIL SHOT (Center Right): A zoomed-in, cropped rectangle showing only the eyes or a specific detail of [PERSONE]. - FULL BODY SHOT (Bottom Center): [PERSONE] sitting on a geometric box or podium in a relaxed but powerful pose. - BACKGROUND: Light gray with a heavy, tactile film grain/noise texture. PHASE 3: GRAPHIC ELEMENTS & TYPOGRAPHY - Initials: Large, outlined capital letters of the first and last name placed in opposite corners. - Vertical Ribbon: A solid color strip with the text \"WORLD CHAMPIONSHIP LEADER\" or a relevant title running vertically through the center. - Data Blocks: - A specific number (ID or rank) in a bold sans-serif block. - A \"Statistics\" block in the bottom-left corner with 3 lines of text (e.g., \"TWO POLES / FOUR WINS / FIVE PODIUMS\"). - Accents: Scatter orange and black squares, dotted circles, and small asterisks throughout the grid for visual complexity. PHASE 4: LIGHTING & TEXTURE - Texture: High-contrast, gritty, and grainy. The overall image should look like a printed high-end magazine or a vintage poster. - Lighting: Professional studio lighting on the subjects, but processed with a \"risograph\" or \"halftone\" feel. PHASE 5: TECH SPECS 8K Resolution. Swiss Modernism aesthetic. Flat vector shapes combined with hyper-realistic photography."
}
JSON
playstation 1 game case with a movie tie-in game that seems like a real game you may have played back in the day. Pick a period appropriate movie that never got a video game version because that would have been a really bad idea. Worst possible choice for a movie tie-in game.
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": "playstation 1 game case with a movie tie-in game that seems like a real game you may have played back in the day. Pick a period appropriate movie that never got a video game version because that would have been a really bad idea. Worst possible choice for a movie tie-in game."
}
JSON
Create a collection of icons representing [ROUTINE / PROCESS / HABITS], with each icon depicting one specific routine step and clearly labeled by name. They belong together as a single cohesive theme. The background is pure white. Place the title “[ROUTINE NAME]” at the top center of the image, aligned symmetrically above the grid, using a clean, minimal typography style that complements the icon design without overpowering it. Icons are rendered in a friendly, modern 3D style, featuring smooth gradients and soft shadows. Maintain consistent proportions, color harmony, materials, and typography across all icons and labels so the set feels unified and easy to read.
curl -X POST https://runapi.ai/api/v1/nano_banana/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "nano-banana-2",
"prompt": "Create a collection of icons representing [ROUTINE / PROCESS / HABITS], with each icon depicting one specific routine step and clearly labeled by name. They belong together as a single cohesive theme. The background is pure white. Place the title “[ROUTINE NAME]” at the top center of the image, aligned symmetrically above the grid, using a clean, minimal typography style that complements the icon design without overpowering it. Icons are rendered in a friendly, modern 3D style, featuring smooth gradients and soft shadows. Maintain consistent proportions, color harmony, materials, and typography across all icons and labels so the set feels unified and easy to read."
}
JSON
Use this photo attached to create a striking outdoor fashion portrait set in a vibrant flower field during daylight, captured with a digital camera using a harsh flash. The camera angle is low and slightly tilted upward, intensifying the scene's energy and drama. The subject has long, loose, dark brown wavy hair cascading over a voluminous, soft, shaggy lavender faux fur coat that drapes naturally over the body. Surrounding the subject are large, colorful poppies in yellow, pink, and orange, some in the foreground and others in the background, creating an immersive field-of-flowers effect. The sky is clear and blue, providing a crisp, contrasting backdrop. The mood is bold, editorial, and whimsical, making the vibrant colors of the outfit and flowers pop starkly against the serene sky. The overall composition should evoke a playful yet high-fashion atmosphere with a hint of surrealism, emphasizing texture and color through the use of direct flash photography.
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 this photo attached to create a striking outdoor fashion portrait set in a vibrant flower field during daylight, captured with a digital camera using a harsh flash. The camera angle is low and slightly tilted upward, intensifying the scene's energy and drama. The subject has long, loose, dark brown wavy hair cascading over a voluminous, soft, shaggy lavender faux fur coat that drapes naturally over the body. Surrounding the subject are large, colorful poppies in yellow, pink, and orange, some in the foreground and others in the background, creating an immersive field-of-flowers effect. The sky is clear and blue, providing a crisp, contrasting backdrop. The mood is bold, editorial, and whimsical, making the vibrant colors of the outfit and flowers pop starkly against the serene sky. The overall composition should evoke a playful yet high-fashion atmosphere with a hint of surrealism, emphasizing texture and color through the use of direct flash photography."
}
JSON
Create an ultra-realistic cinematic 8K portrait, use face reference exactly (100% identical, no changes) - preserve original facial features, proportions, skin texture, hair, and expressions. A man wearing black sunglasses, a black t-shirt, black leather jacket, dark denim pants, and black Converse-style sneakers sits casually on a concrete ledge. One leg is bent while the other hangs freely. His posture is relaxed, projecting calm confidence. A massive airplane flies extremely low overhead, dominating the sky. Powerful wind ripples his jacket and clothing. Captured with a wide-angle lens from a low perspective, creating dramatic scale. Motion blur appears in clouds, debris, and air turbulence, enhancing speed and intensity. Lighting is natural and cinematic with strong contrast. The atmosphere feels surreal yet realistic, emphasizing depth, movement, and cinematic tension.
curl -X POST https://runapi.ai/api/v1/nano_banana/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "nano-banana-2",
"prompt": "Create an ultra-realistic cinematic 8K portrait, use face reference exactly (100% identical, no changes) - preserve original facial features, proportions, skin texture, hair, and expressions. A man wearing black sunglasses, a black t-shirt, black leather jacket, dark denim pants, and black Converse-style sneakers sits casually on a concrete ledge. One leg is bent while the other hangs freely. His posture is relaxed, projecting calm confidence. A massive airplane flies extremely low overhead, dominating the sky. Powerful wind ripples his jacket and clothing. Captured with a wide-angle lens from a low perspective, creating dramatic scale. Motion blur appears in clouds, debris, and air turbulence, enhancing speed and intensity. Lighting is natural and cinematic with strong contrast. The atmosphere feels surreal yet realistic, emphasizing depth, movement, and cinematic tension."
}
JSON
Split composition image, left and right halves clearly divided in 16:9 widescreen format. Left Half: Highly detailed architectural floor plan and cross-section illustration of [LANDMARK] in a modern minimalist style. Top-down view showing main structural layout, internal divisions, circulation paths, key chambers or spaces with labels. Material callouts, structural support systems, and architectural details clearly marked. Neutral beige and warm gray color palette, clean linework, soft shadows, subtle textures. Professional architectural-presentation style. Include detailed cross-sectional diagram showing vertical layers and internal structure. Blueprint aesthetic with technical accuracy and labeled sections. Right Half: Ultra-realistic aerial exterior photograph of [LANDMARK] captured from above and to the side (elevated isometric perspective, not straight overhead). Shows the complete structure with authentic weathered textures, aged materials, surrounding landscape, dramatic golden-hour sunlight creating sharp shadows, atmospheric haze suggesting historical significance. The perspective reveals both external grandeur and internal scale simultaneously. Warm golden-light lighting, realistic patina and wear patterns, authentic architectural proportions. Feels like an aerial photograph capturing the monument’s true majesty and scale. Both halves align visually, clearly showing architectural engineering blueprint vs. the actual monumental structure in its archaeological or historical reality. Style & Mood: •Architectural blueprint visualization meets historical aerial photography •Engineering precision and historical significance •Educational, museum-exhibit presentation •Engineering schematic-to-reality comparison •Grandeur emphasizing scale and architectural sophistication Lighting & Color: •Left: Flat, even lighting, neutral blueprint tones, technical aesthetic •Right: Golden-hour natural light, dramatic shadows, warm tones, atmospheric depth •Consistent warm palette between both halves Camera & Technical Details: •Left: Top-down orthographic + detailed cross-sectional architectural view with labeled sections •Right: Elevated aerial perspective (45-degree isometric angle), capturing full structure from above-and-to-the-side •High resolution, sharp architectural details on left; photorealistic weathered textures on right Negative Prompt: Cartoon style, low detail, cluttered composition, modern elements, unrealistic proportions, harsh lighting, exaggerated colors, text overlays, watermarks, CGI look, sterile rendering, straight-down overhead view, no atmospheric quality, overly pristine condition
Ultra-realistic commercial product photography of a pastel peach-colored soda can labeled “OLIPOP – Peaches & Cream” placed upright in the center, surrounded tightly by fresh whole peaches at the bottom and large transparent ice cubes stacked around and partially covering the top of the can, heavy condensation droplets covering the can and fruit, tiny carbonation bubbles visible on the peaches, crushed ice texture with sharp edges and frosty highlights, soft diffused studio lighting.
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 commercial product photography of a pastel peach-colored soda can labeled “OLIPOP – Peaches & Cream” placed upright in the center, surrounded tightly by fresh whole peaches at the bottom and large transparent ice cubes stacked around and partially covering the top of the can, heavy condensation droplets covering the can and fruit, tiny carbonation bubbles visible on the peaches, crushed ice texture with sharp edges and frosty highlights, soft diffused studio lighting."
}
JSON
{ "objective": "Create a side-by-side comparison image featuring a technical sketch and real photograph of the Burj Khalifa", "image_specifications": { "style": "Mixed media (Technical drawing + Real photograph)", "layout": "Horizontal split - Left side: Sketch with measurements, Right side: Real photo", "aspect_ratio": "3:2" }, "left_side": { "content_type": "Technical sketch of the Burj Khalifa", "features": [ "Detailed architectural lines showing tiered setbacks", "Numerical height and width measurements", "Elevation labels for different tower sections", "Side and front elevation views (top-down projection if space allows)" ], "text_annotations": { "units": "Metric (meters)", "language": "English", "font_style": "Blueprint or engineering-style typography" }, "positioning": "Take up the left half of the image" }, "right_side": { "content_type": "High-resolution real photo of the Burj Khalifa", "features": [ "Full view of the tower from base to spire", "Natural daylight with clear sky", "Color image with Dubai skyline or Downtown Dubai context" ], "positioning": "Take up the right half of the image" }, "visual_elements": { "border_division": "Vertical line or subtle transition between left (sketch) and right (photo)", "color_palette": { "left": "Monochrome or blueprint blue for sketch", "right": "Natural realistic colors" } }, "output_format": { "type": "Image", "use_case": ["Educational poster", "Architectural comparison", "Engineering visualization", "Tourism visual aid"], "high_resolution": true } }
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": "{ \"objective\": \"Create a side-by-side comparison image featuring a technical sketch and real photograph of the Burj Khalifa\", \"image_specifications\": { \"style\": \"Mixed media (Technical drawing + Real photograph)\", \"layout\": \"Horizontal split - Left side: Sketch with measurements, Right side: Real photo\", \"aspect_ratio\": \"3:2\" }, \"left_side\": { \"content_type\": \"Technical sketch of the Burj Khalifa\", \"features\": [ \"Detailed architectural lines showing tiered setbacks\", \"Numerical height and width measurements\", \"Elevation labels for different tower sections\", \"Side and front elevation views (top-down projection if space allows)\" ], \"text_annotations\": { \"units\": \"Metric (meters)\", \"language\": \"English\", \"font_style\": \"Blueprint or engineering-style typography\" }, \"positioning\": \"Take up the left half of the image\" }, \"right_side\": { \"content_type\": \"High-resolution real photo of the Burj Khalifa\", \"features\": [ \"Full view of the tower from base to spire\", \"Natural daylight with clear sky\", \"Color image with Dubai skyline or Downtown Dubai context\" ], \"positioning\": \"Take up the right half of the image\" }, \"visual_elements\": { \"border_division\": \"Vertical line or subtle transition between left (sketch) and right (photo)\", \"color_palette\": { \"left\": \"Monochrome or blueprint blue for sketch\", \"right\": \"Natural realistic colors\" } }, \"output_format\": { \"type\": \"Image\", \"use_case\": [\"Educational poster\", \"Architectural comparison\", \"Engineering visualization\", \"Tourism visual aid\"], \"high_resolution\": true } }"
}
JSON
Use the same face from the reference image without changing facial features Vertical (4:5 or 9:16) surreal 3D scene featuring a photorealistic character generated strictly from the attached reference image (accurate facial likeness, skin texture, age, proportions). Front-facing view, camera slightly above eye level, the character riding her own scooter/motorbike directly on top of the blue GPS route line itself, moving forward toward a red destination pin. The character wears culturally accurate clothing inspired by [west], with realistic fabric behavior and riding posture. Below, a stylized GPS-style city map of [United Kingdom] fills the scene. A chaos zone at [Greenwich ] shows dense miniature cars, people, buildings, trees, and urban clutter concentrated near the destination. Natural daylight, cinematic shadows, sharp focus on the character, and subtle depth of field on the map. High-end concept-art quality combining photoreal human + stylized miniature city.
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 the same face from the reference image without changing facial features Vertical (4:5 or 9:16) surreal 3D scene featuring a photorealistic character generated strictly from the attached reference image (accurate facial likeness, skin texture, age, proportions). Front-facing view, camera slightly above eye level, the character riding her own scooter/motorbike directly on top of the blue GPS route line itself, moving forward toward a red destination pin. The character wears culturally accurate clothing inspired by [west], with realistic fabric behavior and riding posture. Below, a stylized GPS-style city map of [United Kingdom] fills the scene. A chaos zone at [Greenwich ] shows dense miniature cars, people, buildings, trees, and urban clutter concentrated near the destination. Natural daylight, cinematic shadows, sharp focus on the character, and subtle depth of field on the map. High-end concept-art quality combining photoreal human + stylized miniature city."
}
JSON
A majestic, ancient gnarled tree with thick, twisting roots sits at the center of a lush, mystical landscape, its roots anchoring into a vibrant, foaming stream flowing over moss-covered rocks. Suspended within the dense, dark green canopy of the tree is a radiant, glowing golden orb containing a detailed, ethereal silhouette of a tree of life. In the background, a massive, towering waterfall cascades down a rugged, misty cliffside into the river below. The scene is illuminated by the soft, warm light emanating from the golden orb, contrasting with the moody, overcast sky and the deep, rich greens of the surrounding forest. Photorealistic, cinematic lighting, high fantasy art style, intricate textures on the bark and water, 8k 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": "A majestic, ancient gnarled tree with thick, twisting roots sits at the center of a lush, mystical landscape, its roots anchoring into a vibrant, foaming stream flowing over moss-covered rocks. Suspended within the dense, dark green canopy of the tree is a radiant, glowing golden orb containing a detailed, ethereal silhouette of a tree of life. In the background, a massive, towering waterfall cascades down a rugged, misty cliffside into the river below. The scene is illuminated by the soft, warm light emanating from the golden orb, contrasting with the moody, overcast sky and the deep, rich greens of the surrounding forest. Photorealistic, cinematic lighting, high fantasy art style, intricate textures on the bark and water, 8k resolution."
}
JSON