Browse 1632+ curated prompts for image, video, music, and audio generation. Copy a prompt into Claude Code, Codex, Cursor, Windsurf, or use the API code directly.
Using the attached image, create an illustration sheet of professional industrial design packaging for the package (PACKAGE TYPE). A centered heroic 3D rendering with realistic materials, soft studio lighting and commercial quality finishes. Surrounded by technical views: front, side, top, bottom, oblique perspective and flat position. Include sketches of the frame structure, crease lines, seam details, and size arrows in millimeters. Show materials and finishes (matte, glossy print, plastic, paper, glass, etc.) in handwritten annotations. Add color swatches, realistic product illustrations, and subtle shadows. Clean sketchbook background, realistic rendering + pencil sketch style, modern design design, ultra-detailed, portfolio ready.
curl -X POST https://runapi.ai/api/v1/nano_banana/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "nano-banana-2",
"prompt": "Using the attached image, create an illustration sheet of professional industrial design packaging for the package (PACKAGE TYPE). A centered heroic 3D rendering with realistic materials, soft studio lighting and commercial quality finishes. Surrounded by technical views: front, side, top, bottom, oblique perspective and flat position. Include sketches of the frame structure, crease lines, seam details, and size arrows in millimeters. Show materials and finishes (matte, glossy print, plastic, paper, glass, etc.) in handwritten annotations. Add color swatches, realistic product illustrations, and subtle shadows. Clean sketchbook background, realistic rendering + pencil sketch style, modern design design, ultra-detailed, portfolio ready."
}
JSON
A realistic, highly detailed geographic map viewed from above, accurately representing the region where [COUNTRY] is located. Rising from the map is a miniature 3D diorama of [CITY], precisely positioned at its real geographic location. The diorama features iconic architecture, natural landmarks, and cultural elements seamlessly emerging from the map surface. Ultra-realistic materials, fine textures, and depth of field. Soft studio lighting with subtle shadows, cinematic composition, premium macro photography style. Square 1:1 format, high detail, realistic scale.
curl -X POST https://runapi.ai/api/v1/nano_banana/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "nano-banana-2",
"prompt": "A realistic, highly detailed geographic map viewed from above, accurately representing the region where [COUNTRY] is located. Rising from the map is a miniature 3D diorama of [CITY], precisely positioned at its real geographic location. The diorama features iconic architecture, natural landmarks, and cultural elements seamlessly emerging from the map surface. Ultra-realistic materials, fine textures, and depth of field. Soft studio lighting with subtle shadows, cinematic composition, premium macro photography style. Square 1:1 format, high detail, realistic scale."
}
JSON
Create a collection of icons representing [a theme], they belong together as a single theme. Put them in a 2x2 grid (no lines). The background is pure white. Make the icons as risograph prints. No text. No color distortion. Vibrant and not faded. Stochastic stippling and sand-like noise pattern within color fills. Each icon has a thick black outline.
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 [a theme], they belong together as a single theme. Put them in a 2x2 grid (no lines). The background is pure white. Make the icons as risograph prints. No text. No color distortion. Vibrant and not faded. Stochastic stippling and sand-like noise pattern within color fills. Each icon has a thick black outline."
}
JSON
[product], centered top down flat lay, surrounded by [ingredients], fresh slices and whole pieces, glossy wet look, water splash frozen mid motion around the product, dewy droplets on label and surface, warm beige seamless background, soft directional sunlight, crisp realistic shadow, high end skincare advertising, ultra realistic macro product photography, 100mm lens look, f/8 sharp focus, clean composition, no extra text, 8k, 1:1
Create a clear, 45° top-down isometric miniature 3D educational diorama explaining [PROCESS / CONCEPT]. Use soft refined textures, realistic PBR materials, and gentle lifelike lighting. Build a stepped or layered diorama base showing each stage of the process with subtle arrows or paths. Include tiny stylized figures interacting with each stage (no facial details). Use a clean solid [BACKGROUND COLOR] background. At the top-center, display [PROCESS NAME] in large bold text, directly beneath it show a short explanation subtitle, and place a minimal symbolic icon below. All text must automatically match the background contrast (white or black).
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 clear, 45° top-down isometric miniature 3D educational diorama explaining [PROCESS / CONCEPT]. Use soft refined textures, realistic PBR materials, and gentle lifelike lighting. Build a stepped or layered diorama base showing each stage of the process with subtle arrows or paths. Include tiny stylized figures interacting with each stage (no facial details). Use a clean solid [BACKGROUND COLOR] background. At the top-center, display [PROCESS NAME] in large bold text, directly beneath it show a short explanation subtitle, and place a minimal symbolic icon below. All text must automatically match the background contrast (white or black)."
}
JSON
A high-end editorial photo of a [PRODUCT] placed flat on a [TEXTURED SURFACE], captured from a direct top-down view. The surface is gently disturbed to suggest recent motion or interaction. The front of the product is fully visible and properly oriented upright. The area around the product is intentionally left open to optionally place [COMPLEMENTARY OBJECTS] that visually enhance the scene. Natural sunlight from the upper left casts warm, realistic shadows. 3D realism, luxury product photography, shallow depth of field, 1:1 format.
curl -X POST https://runapi.ai/api/v1/nano_banana/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "nano-banana-2",
"prompt": "A high-end editorial photo of a [PRODUCT] placed flat on a [TEXTURED SURFACE], captured from a direct top-down view. The surface is gently disturbed to suggest recent motion or interaction. The front of the product is fully visible and properly oriented upright. The area around the product is intentionally left open to optionally place [COMPLEMENTARY OBJECTS] that visually enhance the scene. Natural sunlight from the upper left casts warm, realistic shadows. 3D realism, luxury product photography, shallow depth of field, 1:1 format."
}
JSON
A professional high-end graphic design advertisement composition on a pure solid white canvas. Centered is a perfectly symmetrical, large solid rounded square (not a hollow frame). The entire interior of this square is filled with a smooth, vibrant color gradient fading from [Top-Left Color/Hex] to [Bottom-Right Color/Hex]. A [Description of Character] is positioned such that the bottom of their torso is perfectly flush and aligned with the very bottom edge of the square, leaving no thick colored border visible beneath them. Crucially, the person and their clothing maintain natural, realistic colors and textures, illuminated by professional studio lighting that is independent of the background gradient (preventing any color cast on their skin or clothes). They are firmly and realistically gripping [Product Description]. Crucially, the top of their head and hair break the top boundary of the square, partially overlapping the white background. Their hands and the [Product Name] also break the side boundaries for a powerful 3D breakout effect, extending onto the white canvas. Typography Layout: At the top, in the white space distinctly above the square with a clear gap, is the [Font Style] brand text '[Brand Name]' in [Top Text Color]. In the bottom-right corner, layered directly on top of the gradient inside the square, is a block of small, thin, clean [Bottom Text Color] descriptive text: '[Slogan/Tagline]'. The lighting is [Lighting Type: e.g., Sharp/Soft], crisp, and commercial, emphasizing the textures of both the subject and the product."
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 professional high-end graphic design advertisement composition on a pure solid white canvas. Centered is a perfectly symmetrical, large solid rounded square (not a hollow frame). The entire interior of this square is filled with a smooth, vibrant color gradient fading from [Top-Left Color/Hex] to [Bottom-Right Color/Hex]. A [Description of Character] is positioned such that the bottom of their torso is perfectly flush and aligned with the very bottom edge of the square, leaving no thick colored border visible beneath them. Crucially, the person and their clothing maintain natural, realistic colors and textures, illuminated by professional studio lighting that is independent of the background gradient (preventing any color cast on their skin or clothes). They are firmly and realistically gripping [Product Description]. Crucially, the top of their head and hair break the top boundary of the square, partially overlapping the white background. Their hands and the [Product Name] also break the side boundaries for a powerful 3D breakout effect, extending onto the white canvas. Typography Layout: At the top, in the white space distinctly above the square with a clear gap, is the [Font Style] brand text '[Brand Name]' in [Top Text Color]. In the bottom-right corner, layered directly on top of the gradient inside the square, is a block of small, thin, clean [Bottom Text Color] descriptive text: '[Slogan/Tagline]'. The lighting is [Lighting Type: e.g., Sharp/Soft], crisp, and commercial, emphasizing the textures of both the subject and the product.\""
}
JSON
Graphic design smart prompt Generate ad posters in Nano Banana This prompt generates: • POV low-angle photo (pointing at viewer) • Oversized text + brand tagline • Serial numbers, copyright lines, technical callouts • Brand-appropriate color blocking and texture Use case: • social media posting, • influencer collab visuals, • pitch decks. Prompt 👇
- A high-fidelity, wide-angle interior shot captures a surreal, mixed-media composition within a modern living room. It features a man resembling the face in the reference photo—using an uploaded face as a reference—wearing a bright yellow hoodie and black pants, sitting centrally on a plush light gray sofa. The scene seamlessly blends photorealistic 3D environments with cel-shaded 2D anime and cartoon characters interacting directly with the physical space. On the right side of the subject on the sofa, Nobita sits casually waving his hand, while on the left side, Doraemon leans casually on a pillow. Behind the sofa, two framed posters hang on the white wall—one featuring Son Goku and Vegeta, and the other featuring Trunks in a dynamic anime style. In the foreground, Shinchan lies relaxed on a textured gray carpet near a plate of dorayaki, while a chibi version of Son Goku stands triumphantly on a cream-colored knit pouf. On the left side of the room, Vegeta stands tall on a grooved wooden side table in a confident pose, while a miniature version of Trunks is near the wooden coffee table in the center, as if observing the scene with a curious expression. Soft natural light streams in from the left side through sheer curtains, creating subtle volumetric lighting that accentuates the texture of the blanket, the wood grain of the tiered table, and the leaves of the snake plant in the corner of the room. The entire scene is rendered in 8K resolution with sharp focus, vivid colors, and a dreamy, cinematic, and playful aesthetic blending between the real world and the anime world, with no AI visible.
curl -X POST https://runapi.ai/api/v1/nano_banana/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "nano-banana-2",
"prompt": "- A high-fidelity, wide-angle interior shot captures a surreal, mixed-media composition within a modern living room. It features a man resembling the face in the reference photo—using an uploaded face as a reference—wearing a bright yellow hoodie and black pants, sitting centrally on a plush light gray sofa. The scene seamlessly blends photorealistic 3D environments with cel-shaded 2D anime and cartoon characters interacting directly with the physical space. On the right side of the subject on the sofa, Nobita sits casually waving his hand, while on the left side, Doraemon leans casually on a pillow. Behind the sofa, two framed posters hang on the white wall—one featuring Son Goku and Vegeta, and the other featuring Trunks in a dynamic anime style. In the foreground, Shinchan lies relaxed on a textured gray carpet near a plate of dorayaki, while a chibi version of Son Goku stands triumphantly on a cream-colored knit pouf. On the left side of the room, Vegeta stands tall on a grooved wooden side table in a confident pose, while a miniature version of Trunks is near the wooden coffee table in the center, as if observing the scene with a curious expression. Soft natural light streams in from the left side through sheer curtains, creating subtle volumetric lighting that accentuates the texture of the blanket, the wood grain of the tiered table, and the leaves of the snake plant in the corner of the room. The entire scene is rendered in 8K resolution with sharp focus, vivid colors, and a dreamy, cinematic, and playful aesthetic blending between the real world and the anime world, with no AI visible."
}
JSON
A colossal hand gripping an enormous vintage fountain pen, captured in vertical portrait format (9:16), writing on endless textured paper that fills the frame. Where the ink flows, the story of [BOOK_NAME] bursts into vivid life — [iconic characters, key objects, and signature scenes from [BOOK_NAME] emerging as tiny miniature figures on the paper, each no larger than a fingernail, ultra-miniature scale]. The miniature world cascades downward across the page as the pen moves, characters frozen mid-story, ink still wet at the edges where they emerge. Extreme close-up of the enormous pen nib touching paper, ink bleeding into fiber, fingertips with visible skin texture. Warm amber and soft golden light raking across the paper surface, deep shadows, cinematic depth of field, magical realism, hyper-detailed, photorealistic, 8K, --ar 9:16
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 colossal hand gripping an enormous vintage fountain pen, captured in vertical portrait format (9:16), writing on endless textured paper that fills the frame. Where the ink flows, the story of [BOOK_NAME] bursts into vivid life — [iconic characters, key objects, and signature scenes from [BOOK_NAME] emerging as tiny miniature figures on the paper, each no larger than a fingernail, ultra-miniature scale]. The miniature world cascades downward across the page as the pen moves, characters frozen mid-story, ink still wet at the edges where they emerge. Extreme close-up of the enormous pen nib touching paper, ink bleeding into fiber, fingertips with visible skin texture. Warm amber and soft golden light raking across the paper surface, deep shadows, cinematic depth of field, magical realism, hyper-detailed, photorealistic, 8K, --ar 9:16"
}
JSON
[BRAND NAME]. Act as a Master of Material Science and World-Class 3D Visualizer. PHASE 1: DYNAMIC ELEMENTAL RECONSTRUCTION. The central subject is the iconic logo of [BRAND NAME], physically constructed from ANY raw natural element. CRITICAL: This includes, but is not limited to, botanical elements (flowers, rose petals, thorns, gnarled wood, moss, leaves) and geological/elemental materials (obsidian, crystals, flowing water, ice, volcanic rock). The logo must be medium-sized, levitating, and rotated at a dynamic 3D angle (3/4 view) to showcase its volume. PHASE 2: HYPER-TACTILE TEXTURE & REALISM. The goal is "Sensory Realism" — the viewer should feel they can touch the object. - If BOTANICAL: Render microscopic cellular structures on petals, dew droplets with refraction, and the velvety fuzz on stems. - If MINERAL: Render micro-pores, crystalline inclusions, and razor-sharp edges. Include subtle "imperfections" like dust particles or organic irregularities to break the CG look and achieve 100% photorealism. PHASE 3: COMPOSITION, LIGHTING & BRANDING. - ENVIRONMENT: A pure, clinical, solid white background for a High-Key commercial look. - TYPOGRAPHY: At the top of the frame, place a very small, minimalist [BRAND NAME] text logo in black. - LIGHTING: Precise studio setup with sharp specular highlights (glints) and a soft, realistic contact shadow on the white floor below to ground the levitating object. TECH SPECS: Extreme Macro photography, 100mm lens, f/8, Ray Tracing (Path Tracing), Subsurface Scattering for light depth, 8k resolution, Unreal Engine 5.4 / Octane Render aesthetic.
curl -X POST https://runapi.ai/api/v1/nano_banana/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "nano-banana-2",
"prompt": "[BRAND NAME]. Act as a Master of Material Science and World-Class 3D Visualizer. PHASE 1: DYNAMIC ELEMENTAL RECONSTRUCTION. The central subject is the iconic logo of [BRAND NAME], physically constructed from ANY raw natural element. CRITICAL: This includes, but is not limited to, botanical elements (flowers, rose petals, thorns, gnarled wood, moss, leaves) and geological/elemental materials (obsidian, crystals, flowing water, ice, volcanic rock). The logo must be medium-sized, levitating, and rotated at a dynamic 3D angle (3/4 view) to showcase its volume. PHASE 2: HYPER-TACTILE TEXTURE & REALISM. The goal is \"Sensory Realism\" — the viewer should feel they can touch the object. - If BOTANICAL: Render microscopic cellular structures on petals, dew droplets with refraction, and the velvety fuzz on stems. - If MINERAL: Render micro-pores, crystalline inclusions, and razor-sharp edges. Include subtle \"imperfections\" like dust particles or organic irregularities to break the CG look and achieve 100% photorealism. PHASE 3: COMPOSITION, LIGHTING & BRANDING. - ENVIRONMENT: A pure, clinical, solid white background for a High-Key commercial look. - TYPOGRAPHY: At the top of the frame, place a very small, minimalist [BRAND NAME] text logo in black. - LIGHTING: Precise studio setup with sharp specular highlights (glints) and a soft, realistic contact shadow on the white floor below to ground the levitating object. TECH SPECS: Extreme Macro photography, 100mm lens, f/8, Ray Tracing (Path Tracing), Subsurface Scattering for light depth, 8k resolution, Unreal Engine 5.4 / Octane Render aesthetic."
}
JSON
Editorial portrait from the attached reference photo, photorealistic. Use uploaded selfie as ONLY face reference. Identity lock: exact likeness, facial geometry/proportions, natural skin texture. No beautification. Keep clothing style, color, material, and fit identical to the reference. Medium close-up (face and shoulders), low angle looking up (heroic/dominant perspective), sharp focus on face/eyes.Serious, intense, focused expression, gaze directed upward and away from camera (beyond the frame). Dramatic saturated studio lighting, high-contrast chiaroscuro with deep shadows, vibrant oranges and deep reds palette, strong rim light creating a halo separation. Solid studio backdrop, rich orange-red smooth gradient, pattern-free, hot radiant atmosphere. High skin texture fidelity (pores visible), 8k, portrait aspect ratio, cinematic lighting, 4:5.
curl -X POST https://runapi.ai/api/v1/nano_banana/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "nano-banana-2",
"prompt": "Editorial portrait from the attached reference photo, photorealistic. Use uploaded selfie as ONLY face reference. Identity lock: exact likeness, facial geometry/proportions, natural skin texture. No beautification. Keep clothing style, color, material, and fit identical to the reference. Medium close-up (face and shoulders), low angle looking up (heroic/dominant perspective), sharp focus on face/eyes.Serious, intense, focused expression, gaze directed upward and away from camera (beyond the frame). Dramatic saturated studio lighting, high-contrast chiaroscuro with deep shadows, vibrant oranges and deep reds palette, strong rim light creating a halo separation. Solid studio backdrop, rich orange-red smooth gradient, pattern-free, hot radiant atmosphere. High skin texture fidelity (pores visible), 8k, portrait aspect ratio, cinematic lighting, 4:5."
}
JSON
Make a photo of a cute ball-shaped version of a [animal], with big adorable over-sized eyes, it has no head, instead its face is part of the ball, its head and body are one. They are in their usual habitat. Must be almost spherical and cartoonishly cute. Its eyes are looking up in the most adorable cheeky fashion.
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": "Make a photo of a cute ball-shaped version of a [animal], with big adorable over-sized eyes, it has no head, instead its face is part of the ball, its head and body are one. They are in their usual habitat. Must be almost spherical and cartoonishly cute. Its eyes are looking up in the most adorable cheeky fashion."
}
JSON
Using the uploaded selfie as the ONLY and exclusive face reference, generate a Pixar-style 3D character sticker set. The character must be clearly recognizable as the person from the selfie. Create a neat 3×3 grid collage (nine stickers total). Final aspect ratio is strictly 4:5. Each cell shows a distinct pose and facial expression. Style and tone: Pixar-style 3D animation with a meme-oriented feel. Exaggerated, slightly absurd emotions, playful overacting. Highly readable expressions at small sizes, with expressive eyes, eyebrows, and mouth. Subtle hand gestures where appropriate. Background and output: Fully transparent background (PNG). No backdrop, no background shadows. No text, captions, logos, or UI elements. Stickers must be ready for direct use in messengers. Consistency: Same hairstyle, clothing, colors, and character proportions across all nine stickers. Only facial expression and pose change. Clean, polished 3D sticker look. Emotions (one per sticker, 3×3 grid): Surprised, Annoyed, Confused, Frustrated, Thoughtful, Sarcastic, Worried, Bored, Curious.
curl -X POST https://runapi.ai/api/v1/nano_banana/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "nano-banana-2",
"prompt": "Using the uploaded selfie as the ONLY and exclusive face reference, generate a Pixar-style 3D character sticker set. The character must be clearly recognizable as the person from the selfie. Create a neat 3×3 grid collage (nine stickers total). Final aspect ratio is strictly 4:5. Each cell shows a distinct pose and facial expression. Style and tone: Pixar-style 3D animation with a meme-oriented feel. Exaggerated, slightly absurd emotions, playful overacting. Highly readable expressions at small sizes, with expressive eyes, eyebrows, and mouth. Subtle hand gestures where appropriate. Background and output: Fully transparent background (PNG). No backdrop, no background shadows. No text, captions, logos, or UI elements. Stickers must be ready for direct use in messengers. Consistency: Same hairstyle, clothing, colors, and character proportions across all nine stickers. Only facial expression and pose change. Clean, polished 3D sticker look. Emotions (one per sticker, 3×3 grid): Surprised, Annoyed, Confused, Frustrated, Thoughtful, Sarcastic, Worried, Bored, Curious."
}
JSON
{ "objective": "Create a split architectural visualization where the top is a detailed dark-themed blueprint and the bottom is a photorealistic house that matches the blueprint EXACTLY", "aspect_ratio": "3:4", "composition": { "layout": "vertical split", "top_section": "blueprint", "bottom_section": "realistic render", "alignment": "perfect structural correspondence between both sections" }, "top_section": { "type": "architectural blueprint", "style": "dark luxury blueprint (similar to reference image 2)", "visual_style": { "background": "deep navy / charcoal blue", "lines": "thin glowing beige/gold lines", "walls": "slightly extruded 3D effect", "labels": "clean modern sans-serif", "lighting": "soft ambient glow" }, "content": { "rooms": [ "3 bedrooms (left, right, bottom-right)", "central living room", "kitchen + dining (top center)", "2 bathrooms", "garage (left side connected)", "front porch", "backyard pool with deck" ], "details": [ "furniture outlines (beds, sofa, dining table)", "door swings and openings", "window placements", "circulation paths", "exact proportions and spacing" ] } }, "bottom_section": { "type": "photorealistic house render", "constraint": "MUST MATCH THE BLUEPRINT EXACTLY — no added, removed, or shifted rooms", "architecture": { "style": "modern single-story house", "roof": "flat layered roof", "materials": [ "smooth concrete walls", "wood panel accents", "large glass windows" ] }, "layout_mapping_rules": [ "garage must be on the left side exactly as blueprint", "main entrance aligned with living room", "pool positioned in backyard matching blueprint dimensions", "window placements correspond to each room location", "bedroom volumes visible externally in correct positions" ], "environment": { "setting": "suburban neighborhood", "elements": [ "green lawn", "minimal landscaping", "clean driveway leading to garage", "pool deck matching blueprint footprint" ] }, "lighting": { "time": "golden hour", "style": "soft natural light with realistic shadows" }, "camera": { "angle": "slightly elevated front perspective", "lens": "35mm architectural view" } }, "consistency_rules": [ "room positions must be identical between blueprint and render", "no extra structures added in render", "all doors and windows must align logically", "pool size and placement must match exactly", "garage placement must match blueprint" ], "style": { "top": "architectural visualization (dark premium)", "bottom": "photorealistic modern house", "overall": "clean, high-end architectural presentation" }, "negative_constraints": [ "no mismatch between blueprint and render", "no extra rooms", "no fantasy elements", "no unrealistic proportions", "no cluttered environment" ] }
{ "image_description": { "title": "Surveillance Feed: Defiant Subject in Retail Shop", "aspect_ratio": "4:5", "mood": "Raw, gritty, confrontational, authentic" }, "visual_elements": { "subject": { "framing": "Centered from mid-torso upward", "pose": "Head tilted back looking up at camera, relaxed yet defiant posture", "action": "Hand raised with middle finger extended (silhouette, ghosted by motion)", "facial_features": "Largely obscured by blur, mouth open with tongue faintly visible", "apparel": "Dark oversized sunglasses reflecting ambient light" }, "environment": { "location": "Cramped retail shop interior", "foreground": "Cluttered checkout counter, papers, white shopping bag with red rope handles", "background": "Densely packed shelves with small items, souvenirs, and figurines (abstracted by low resolution)" } }, "technical_specifications": { "camera_perspective": "High-mounted, steep downward angle, top-down CCTV view", "lens_distortion": "Subtle fisheye warping at frame edges", "lighting": "Harsh flat fluorescent, blown highlights, dull shadows", "color_grading": "Cool green-blue cast, uneven color reproduction, visible banding, reduced dynamic range" }, "image_fidelity": { "quality": "Intentionally degraded, low-fidelity", "artifacts": [ "Strong motion blur", "Digital smearing", "Compression artifacts", "Heavy noise", "Scan lines" ], "sharpness": "Low perceived sharpness, distinct details stretched and indistinct" }, "full_prompt_text": "A heavily distorted, low-fidelity surveillance-style image depicts the Subject standing behind a cramped retail checkout counter inside a cluttered shop, captured from a high-mounted camera angled steeply downward in a top-down CCTV perspective. The image quality is intentionally degraded, with strong motion blur, digital smearing, compression artifacts, heavy noise, scan lines, and subtle fisheye distortion warping the frame edges, making fine details indistinct and stretched. The Subject is centered from mid-torso upward, looking up toward the camera with the head tilted back; facial features are largely obscured by blur and artifacts, though dark oversized sunglasses dominate the face, reflecting ambient light, and the mouth appears open with the tongue faintly visible. One hand is raised toward the camera with the middle finger extended, clearly readable in silhouette but softened and ghosted by motion and low clarity, conveying a relaxed yet defiant posture. The foreground checkout counter is cluttered with papers and a white shopping bag with red rope handles, while the background shelves are densely packed with small items, souvenirs, and figurines that blend into abstract shapes due to low resolution and noise. Harsh, flat fluorescent lighting produces blown highlights, dull shadows, uneven color reproduction, and a cool green-blue color cast with visible banding and reduced dynamic range. Despite an effectively deep depth of field, perceived sharpness remains low, reinforcing a raw, gritty, confrontational mood that emphasizes the authenticity of an unpolished, unenhanced surveillance feed in a vertical 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": "{ \"image_description\": { \"title\": \"Surveillance Feed: Defiant Subject in Retail Shop\", \"aspect_ratio\": \"4:5\", \"mood\": \"Raw, gritty, confrontational, authentic\" }, \"visual_elements\": { \"subject\": { \"framing\": \"Centered from mid-torso upward\", \"pose\": \"Head tilted back looking up at camera, relaxed yet defiant posture\", \"action\": \"Hand raised with middle finger extended (silhouette, ghosted by motion)\", \"facial_features\": \"Largely obscured by blur, mouth open with tongue faintly visible\", \"apparel\": \"Dark oversized sunglasses reflecting ambient light\" }, \"environment\": { \"location\": \"Cramped retail shop interior\", \"foreground\": \"Cluttered checkout counter, papers, white shopping bag with red rope handles\", \"background\": \"Densely packed shelves with small items, souvenirs, and figurines (abstracted by low resolution)\" } }, \"technical_specifications\": { \"camera_perspective\": \"High-mounted, steep downward angle, top-down CCTV view\", \"lens_distortion\": \"Subtle fisheye warping at frame edges\", \"lighting\": \"Harsh flat fluorescent, blown highlights, dull shadows\", \"color_grading\": \"Cool green-blue cast, uneven color reproduction, visible banding, reduced dynamic range\" }, \"image_fidelity\": { \"quality\": \"Intentionally degraded, low-fidelity\", \"artifacts\": [ \"Strong motion blur\", \"Digital smearing\", \"Compression artifacts\", \"Heavy noise\", \"Scan lines\" ], \"sharpness\": \"Low perceived sharpness, distinct details stretched and indistinct\" }, \"full_prompt_text\": \"A heavily distorted, low-fidelity surveillance-style image depicts the Subject standing behind a cramped retail checkout counter inside a cluttered shop, captured from a high-mounted camera angled steeply downward in a top-down CCTV perspective. The image quality is intentionally degraded, with strong motion blur, digital smearing, compression artifacts, heavy noise, scan lines, and subtle fisheye distortion warping the frame edges, making fine details indistinct and stretched. The Subject is centered from mid-torso upward, looking up toward the camera with the head tilted back; facial features are largely obscured by blur and artifacts, though dark oversized sunglasses dominate the face, reflecting ambient light, and the mouth appears open with the tongue faintly visible. One hand is raised toward the camera with the middle finger extended, clearly readable in silhouette but softened and ghosted by motion and low clarity, conveying a relaxed yet defiant posture. The foreground checkout counter is cluttered with papers and a white shopping bag with red rope handles, while the background shelves are densely packed with small items, souvenirs, and figurines that blend into abstract shapes due to low resolution and noise. Harsh, flat fluorescent lighting produces blown highlights, dull shadows, uneven color reproduction, and a cool green-blue color cast with visible banding and reduced dynamic range. Despite an effectively deep depth of field, perceived sharpness remains low, reinforcing a raw, gritty, confrontational mood that emphasizes the authenticity of an unpolished, unenhanced surveillance feed in a vertical 4:5 aspect ratio\" }"
}
JSON
Cinematic studio portrait of a young man with messy textured hair, wearing a black turtleneck, centered composition, dark minimal background, dramatic low-key lighting, a horizontal red neon light strip cutting across his eyes, strong contrast shadows covering lower face, intense gaze, moody atmosphere, cyberpunk aesthetic, ultra-realistic, sharp focus, 85mm lens, shallow depth of field, high detail, editorial photography style.
Ultra-realistic cinematic street portrait of a young woman in a bright blue puffer jacket standing still in the middle of a busy city crowd, intense eye contact with camera, shallow depth of field, motion-blurred pedestrians rushing around her, urban background with traffic lights and tall buildings, cool color grading, natural skin tones, soft overcast lighting, 85mm lens, f/1.8, high detail, sharp focus on subject, dynamic motion blur, editorial photography, 8k.
curl -X POST https://runapi.ai/api/v1/nano_banana/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "nano-banana-2",
"prompt": "Ultra-realistic cinematic street portrait of a young woman in a bright blue puffer jacket standing still in the middle of a busy city crowd, intense eye contact with camera, shallow depth of field, motion-blurred pedestrians rushing around her, urban background with traffic lights and tall buildings, cool color grading, natural skin tones, soft overcast lighting, 85mm lens, f/1.8, high detail, sharp focus on subject, dynamic motion blur, editorial photography, 8k."
}
JSON
High-quality stylized 3D CGI Pixar-style render, vertical 3:4 composition, the most iconic characters from [SHOW/MOVIE] captured as a chaotic and joyful bathroom mirror selfie; the most recognizable character holds a large vintage camera up toward the mirror, the remaining characters squeezed tightly into the frame around them, each showing their most signature expression or pose; everyone wearing their most iconic costumes and outfits faithful to the source material; all crammed together creating classic crowded selfie energy; facial proportions gently stylized in Disney/Pixar animation style with expressive eyes while faithfully preserving each character's most recognizable traits, hairstyles and costumes from [SHOW/MOVIE]; the bathroom mirror has realistic toothpaste splatters and subtle smudges; the reflection shows bold black Pixar-style lettering reading "[SHOW/MOVIE]❤️"; the bathroom background is styled to match the world of [SHOW/MOVIE] with thematic props and easter eggs relevant to [SHOW/MOVIE] placed naturally around the scene; lighting combines soft ambient bathroom lighting with a bright camera flash reflecting in the mirror creating gentle specular highlights; warm Pixar-style color grading faithful to the visual tone of [SHOW/MOVIE], smooth highlight rolloff, refined Disney/Pixar cinematic character shading, ultra-detailed 4K render, no watermark
curl -X POST https://runapi.ai/api/v1/nano_banana/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "nano-banana-2",
"prompt": "High-quality stylized 3D CGI Pixar-style render, vertical 3:4 composition, the most iconic characters from [SHOW/MOVIE] captured as a chaotic and joyful bathroom mirror selfie; the most recognizable character holds a large vintage camera up toward the mirror, the remaining characters squeezed tightly into the frame around them, each showing their most signature expression or pose; everyone wearing their most iconic costumes and outfits faithful to the source material; all crammed together creating classic crowded selfie energy; facial proportions gently stylized in Disney/Pixar animation style with expressive eyes while faithfully preserving each character's most recognizable traits, hairstyles and costumes from [SHOW/MOVIE]; the bathroom mirror has realistic toothpaste splatters and subtle smudges; the reflection shows bold black Pixar-style lettering reading \"[SHOW/MOVIE]❤️\"; the bathroom background is styled to match the world of [SHOW/MOVIE] with thematic props and easter eggs relevant to [SHOW/MOVIE] placed naturally around the scene; lighting combines soft ambient bathroom lighting with a bright camera flash reflecting in the mirror creating gentle specular highlights; warm Pixar-style color grading faithful to the visual tone of [SHOW/MOVIE], smooth highlight rolloff, refined Disney/Pixar cinematic character shading, ultra-detailed 4K render, no watermark"
}
JSON
{ "type": "image_generation_prompt", "style": "photorealistic, lifestyle photography", "sexualization": "none", "description": { "subject": "A young woman standing casually in a home kitchen, seen in side profile", "pose": "Relaxed posture, one hand resting on her hip while the other holds a small drink carton with a straw", "expression": "Neutral, thoughtful, slightly distant gaze looking forward", "appearance": { "hair": "Dark hair tied in a loose low bun with natural strands framing the face", "clothing": "Oversized white t-shirt worn casually, simple underwear partially visible due to the relaxed fit of the shirt", "tattoos": "Small, minimal black-ink tattoos on the forearm, subtle and understated" } }, "environment": { "location": "A modest, lived-in home kitchen", "details": "Wooden cabinets, countertop appliances, a refrigerator covered with colorful magnets and souvenirs", "lighting": "Soft natural daylight coming from a window, warm and slightly muted", "atmosphere": "Quiet, everyday domestic moment" }, "camera": { "angle": "Side profile view", "framing": "Medium shot capturing the subject from mid-thigh to head", "lens": "35mm lifestyle lens", "depth_of_field": "Moderate, background softly in focus to preserve environmental context" }, "image_quality": { "realism": "High", "texture_detail": "Natural fabric folds, skin texture, and kitchen surface details visible", "grain": "Light natural film grain for an authentic look" }, "mood": "Calm, intimate, documentary-style", "constraints": [ "Non-sexualized, everyday realism", "Focus on natural lifestyle and atmosphere", "No exaggerated poses or expressions", "Candid, slice-of-life aesthetic" ] }
curl -X POST https://runapi.ai/api/v1/nano_banana/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "nano-banana-2",
"prompt": "{ \"type\": \"image_generation_prompt\", \"style\": \"photorealistic, lifestyle photography\", \"sexualization\": \"none\", \"description\": { \"subject\": \"A young woman standing casually in a home kitchen, seen in side profile\", \"pose\": \"Relaxed posture, one hand resting on her hip while the other holds a small drink carton with a straw\", \"expression\": \"Neutral, thoughtful, slightly distant gaze looking forward\", \"appearance\": { \"hair\": \"Dark hair tied in a loose low bun with natural strands framing the face\", \"clothing\": \"Oversized white t-shirt worn casually, simple underwear partially visible due to the relaxed fit of the shirt\", \"tattoos\": \"Small, minimal black-ink tattoos on the forearm, subtle and understated\" } }, \"environment\": { \"location\": \"A modest, lived-in home kitchen\", \"details\": \"Wooden cabinets, countertop appliances, a refrigerator covered with colorful magnets and souvenirs\", \"lighting\": \"Soft natural daylight coming from a window, warm and slightly muted\", \"atmosphere\": \"Quiet, everyday domestic moment\" }, \"camera\": { \"angle\": \"Side profile view\", \"framing\": \"Medium shot capturing the subject from mid-thigh to head\", \"lens\": \"35mm lifestyle lens\", \"depth_of_field\": \"Moderate, background softly in focus to preserve environmental context\" }, \"image_quality\": { \"realism\": \"High\", \"texture_detail\": \"Natural fabric folds, skin texture, and kitchen surface details visible\", \"grain\": \"Light natural film grain for an authentic look\" }, \"mood\": \"Calm, intimate, documentary-style\", \"constraints\": [ \"Non-sexualized, everyday realism\", \"Focus on natural lifestyle and atmosphere\", \"No exaggerated poses or expressions\", \"Candid, slice-of-life aesthetic\" ] }"
}
JSON
Ultra-wide-angle hyper-realistic shooting in top-down mode. A group of 4 real people sitting at a square dining table. The camera is pushed far back, creating a significant negative space (empty floor area) around the people and the table, which provides a clear, minimalistic composition. Scene [ATMOSPHERE AND CLOTHING]: Four people are dressed in [STYLE OF CLOTHING]. Their interaction is specific: [DESCRIBE EACH PERSON'S ACTIONS]. The table is a custom-made physical prop, designed as an Instagram post: it has a solid white stripe ONLY along the top and bottom edges (no white frames on the left or right). - The upper white stripe shows a drawn profile photo with [LOGO DESCRIPTION], the username "[USERNAME]", followed by a small blue icon with a confirmed check mark, and "..." on the right. - Red hearts, comment and share icons are painted on the bottom white stripe on the left, and a Bookmarks icon on the right. The center of the table is filled in [THE EXACT COLOR OF THE CENTER and the hexadecimal CODE]. The table shows [FOOD ITEMS/ITEM DESCRIPTIONS]. important: ALL food, beverages, objects, and hands that interact with them must be located strictly within this central area, colored in [COLOR]. NOTHING should go beyond the white stripes or beyond the table. The background of the floor is made in [THE COLOR OF THE FLOOR] to create a visual separation. Professional studio lighting with clear shadows. 8k, clear focus.
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-wide-angle hyper-realistic shooting in top-down mode. A group of 4 real people sitting at a square dining table. The camera is pushed far back, creating a significant negative space (empty floor area) around the people and the table, which provides a clear, minimalistic composition. Scene [ATMOSPHERE AND CLOTHING]: Four people are dressed in [STYLE OF CLOTHING]. Their interaction is specific: [DESCRIBE EACH PERSON'S ACTIONS]. The table is a custom-made physical prop, designed as an Instagram post: it has a solid white stripe ONLY along the top and bottom edges (no white frames on the left or right). - The upper white stripe shows a drawn profile photo with [LOGO DESCRIPTION], the username \"[USERNAME]\", followed by a small blue icon with a confirmed check mark, and \"...\" on the right. - Red hearts, comment and share icons are painted on the bottom white stripe on the left, and a Bookmarks icon on the right. The center of the table is filled in [THE EXACT COLOR OF THE CENTER and the hexadecimal CODE]. The table shows [FOOD ITEMS/ITEM DESCRIPTIONS]. important: ALL food, beverages, objects, and hands that interact with them must be located strictly within this central area, colored in [COLOR]. NOTHING should go beyond the white stripes or beyond the table. The background of the floor is made in [THE COLOR OF THE FLOOR] to create a visual separation. Professional studio lighting with clear shadows. 8k, clear focus."
}
JSON
FAQ
Finding and using RunAPI prompts
What are RunAPI prompts?
RunAPI prompts are curated input examples for image, video, music, and audio models. Each prompt is paired with the model slug and endpoint path so developers can copy the text into an agent or reuse it in backend calls.
Can I filter prompts by model or category?
Yes. Use the modality and category links to narrow the library, then open a model page for examples tied to one specific model slug. Each model page keeps the prompt cards, install steps, and API examples together.
Do I need an API key to browse prompts?
No. Browsing, filtering, and copying prompt text is public. You only need a RunAPI key when you ask an agent or your application to call a model and create a generation task.
How should agents use these prompts?
Install the RunAPI MCP Server in Claude Code, Codex, Cursor, or Windsurf, then paste the prompt instruction shown on the page. The agent can choose the matching RunAPI tool and send the prompt with the listed model.