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.
A refined fashion editorial image with a 3:4 aspect ratio, split into two clear sections. Right side: A fashionable, confident, sensual woman standing and walking casually in a modern architectural space with red luxurious walls and soft natural light. She wears a top with a deep V neckline, a 90-60-90 figure, tucked into a high-waisted blue tailored short skirt, On her feet are sleek black stiletto heels, elegant and minimal. She carries a small structured red handbag in one hand and she is wearing a luxurious diamond necklace with a blue diamond on it. Her hair is open emphasizing her facial structure. She wears subtle statement earrings. The look is refined, modern, and effortlessly chic. Natural daylight, soft shadows, realistic skin texture. Casual fashion photography style with an editorial, high-end feel. alive color palette, warm tones, shallow depth of field, cinematic realism. Style & Mood: Modern elegance, quiet luxury, confident, minimal, editorial casual. Photography Details: Eye-level angle, candid stance, 35mm lens, natural lighting, high detail, photorealistic. Left side: A clean, minimalist product breakdown layout on a neutral background. The individual fashion items worn by the woman are displayed separately, neatly arranged with subtle shadows. Each item includes a small, elegant price label in refined sans-serif typography: – white deep V-neck knit top — $180 – blue high-waisted tailored mini skirt — $220 – Black pointed-toe stiletto heels — $350 – Small structured red handbag — $480 – a diamond necklace with a big blue diamond — $160000 The left side feels like a luxury fashion catalog or e-commerce lookbook, with a red carpet, luxurious walls, art pieces on wall Overall Style & Mood: Quiet luxury, modern elegance, editorial fashion, high-end retail aesthetic. Lighting & Quality: Soft natural light, studio-clean clarity on product side, photorealistic, ultra-high resolution, professional fashion photography. Negative Prompt: Cluttered layout, oversized text, flashy logos, mannequins, people on left side, harsh lighting, low resolution, cartoon style.
curl -X POST https://runapi.ai/api/v1/nano_banana/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "nano-banana-2",
"prompt": "A refined fashion editorial image with a 3:4 aspect ratio, split into two clear sections. Right side: A fashionable, confident, sensual woman standing and walking casually in a modern architectural space with red luxurious walls and soft natural light. She wears a top with a deep V neckline, a 90-60-90 figure, tucked into a high-waisted blue tailored short skirt, On her feet are sleek black stiletto heels, elegant and minimal. She carries a small structured red handbag in one hand and she is wearing a luxurious diamond necklace with a blue diamond on it. Her hair is open emphasizing her facial structure. She wears subtle statement earrings. The look is refined, modern, and effortlessly chic. Natural daylight, soft shadows, realistic skin texture. Casual fashion photography style with an editorial, high-end feel. alive color palette, warm tones, shallow depth of field, cinematic realism. Style & Mood: Modern elegance, quiet luxury, confident, minimal, editorial casual. Photography Details: Eye-level angle, candid stance, 35mm lens, natural lighting, high detail, photorealistic. Left side: A clean, minimalist product breakdown layout on a neutral background. The individual fashion items worn by the woman are displayed separately, neatly arranged with subtle shadows. Each item includes a small, elegant price label in refined sans-serif typography: – white deep V-neck knit top — $180 – blue high-waisted tailored mini skirt — $220 – Black pointed-toe stiletto heels — $350 – Small structured red handbag — $480 – a diamond necklace with a big blue diamond — $160000 The left side feels like a luxury fashion catalog or e-commerce lookbook, with a red carpet, luxurious walls, art pieces on wall Overall Style & Mood: Quiet luxury, modern elegance, editorial fashion, high-end retail aesthetic. Lighting & Quality: Soft natural light, studio-clean clarity on product side, photorealistic, ultra-high resolution, professional fashion photography. Negative Prompt: Cluttered layout, oversized text, flashy logos, mannequins, people on left side, harsh lighting, low resolution, cartoon style."
}
JSON
A minimalist cinematic colored poster featuring a [Character Name]’s portrait from shoulders to the top of the head. The face is reconstructed using a small number of large, square-cut paper fragments arranged in a simple grid [around 4x5 or 5x6 pieces]. Each paper fragment contains a disjointed part of the face which together reconstruct the portrait. The internal paper fragments constituting the face are not perfectly flat; many have slightly curled edges and lifted corners, casting tiny, realistic shadows that give them a three-dimensional, tacked-down appearance. 4 of these squares have subtle black handwritten [text1, text2, text3, text4] directly on the skin/image. Scattered irregularly around the outer perimeter of this central grid in various randomly placed positions (not confined to the corners), several [Sticky Note Color] sticky notes are attached to the [Color] wall, containing handwritten [External Text Content, e.g., iconic quotes]. The overall layout is slightly irregular with visible gaps between the pieces showing [Color] concrete wall background. Realistic paper texture throughout, high-end studio lighting emphasizing the lifted edges, sharp focus on ink and paper grain.
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 minimalist cinematic colored poster featuring a [Character Name]’s portrait from shoulders to the top of the head. The face is reconstructed using a small number of large, square-cut paper fragments arranged in a simple grid [around 4x5 or 5x6 pieces]. Each paper fragment contains a disjointed part of the face which together reconstruct the portrait. The internal paper fragments constituting the face are not perfectly flat; many have slightly curled edges and lifted corners, casting tiny, realistic shadows that give them a three-dimensional, tacked-down appearance. 4 of these squares have subtle black handwritten [text1, text2, text3, text4] directly on the skin/image. Scattered irregularly around the outer perimeter of this central grid in various randomly placed positions (not confined to the corners), several [Sticky Note Color] sticky notes are attached to the [Color] wall, containing handwritten [External Text Content, e.g., iconic quotes]. The overall layout is slightly irregular with visible gaps between the pieces showing [Color] concrete wall background. Realistic paper texture throughout, high-end studio lighting emphasizing the lifted edges, sharp focus on ink and paper grain."
}
JSON
A photorealistic fashion upper body shot of [Character Description and expression] wearing [Detailed Outfit Description]. The subject is framed inside a central white Instagram-style post border. Composition & Spacing: The white frame is perfectly centered in the middle of the image, leaving balanced empty [Soft Background Color matching the outfit] space above and below the frame to match the theme. Frame Details: The top, left, and right white borders are very thin. The bottom white section is thicker to include UI elements. The bottom section features a red heart icon, comment bubble, share icon, and bookmark icon. Text Details: Clearly visible text on the bottom panel: "[Number] likes", username "[Username]", caption "[Caption text]... more", and below that, "View all comments". 3D Pop-Out Effect & Hand Pose: [CHOOSE ONE OF THE FOLLOWING ACTIONS OR DESCRIBE YOUR OWN ACTION:] 1. (Grip): head and arms are physically popping out OVER the top and side thin borders. hands are realistically gripping the outer edges of the thin side borders, appearing to hold the frame firmly. 2. (Kiss): Her body is leaning forward towards the camera, creating a strong sense of depth. Her head remains securely framed WITHIN the top thin white border. Only her right hand, raised near her mouth in a blowing-kiss gesture, physically extends forward and breaks OUT of the thin side frame boundary. Her left hand realistically grips the side edge. 3. (Resting): She is looking directly at the camera with a gentle smile. Her head and shoulders physically pop out OVER the top thin white border. Crucially, her hands are realistically resting comfortably on top of the thicker bottom white UI panel, appearing to lean casually on the frame edge. 4. (Dynamic Frame): Her upper body and head remain secure WITHIN the boundaries of the white frame. However, both of her arms are fully extended outward dynamically, breaking past the thin borders up to her elbows, reaching straight toward the camera lens. She forms a distinct “L” shape with both hands, as if framing a scene. Due to perspective, her hands are positioned significantly closer to the camera than her face, showing strong spatial depth. Subject Dimensionality & Texture: The subject must look like a solid, three-dimensional figure, not flat. Emphasize the detailed texture of the [Specific Fabric Name from outfit description], the contours of the face, and realistic hair details. She should have distinct depth separating her from the flat [Background Color] background. Lighting & Shadows: Professional studio lighting creating soft, realistic drop shadows cast by the physical frame and, crucially, by the [popping-out elements, e.g., hands/head/arms] onto the solid flat [Background Color] background, enhancing the dramatic depth and illusion. High definition, commercial 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": "A photorealistic fashion upper body shot of [Character Description and expression] wearing [Detailed Outfit Description]. The subject is framed inside a central white Instagram-style post border. Composition & Spacing: The white frame is perfectly centered in the middle of the image, leaving balanced empty [Soft Background Color matching the outfit] space above and below the frame to match the theme. Frame Details: The top, left, and right white borders are very thin. The bottom white section is thicker to include UI elements. The bottom section features a red heart icon, comment bubble, share icon, and bookmark icon. Text Details: Clearly visible text on the bottom panel: \"[Number] likes\", username \"[Username]\", caption \"[Caption text]... more\", and below that, \"View all comments\". 3D Pop-Out Effect & Hand Pose: [CHOOSE ONE OF THE FOLLOWING ACTIONS OR DESCRIBE YOUR OWN ACTION:] 1. (Grip): head and arms are physically popping out OVER the top and side thin borders. hands are realistically gripping the outer edges of the thin side borders, appearing to hold the frame firmly. 2. (Kiss): Her body is leaning forward towards the camera, creating a strong sense of depth. Her head remains securely framed WITHIN the top thin white border. Only her right hand, raised near her mouth in a blowing-kiss gesture, physically extends forward and breaks OUT of the thin side frame boundary. Her left hand realistically grips the side edge. 3. (Resting): She is looking directly at the camera with a gentle smile. Her head and shoulders physically pop out OVER the top thin white border. Crucially, her hands are realistically resting comfortably on top of the thicker bottom white UI panel, appearing to lean casually on the frame edge. 4. (Dynamic Frame): Her upper body and head remain secure WITHIN the boundaries of the white frame. However, both of her arms are fully extended outward dynamically, breaking past the thin borders up to her elbows, reaching straight toward the camera lens. She forms a distinct “L” shape with both hands, as if framing a scene. Due to perspective, her hands are positioned significantly closer to the camera than her face, showing strong spatial depth. Subject Dimensionality & Texture: The subject must look like a solid, three-dimensional figure, not flat. Emphasize the detailed texture of the [Specific Fabric Name from outfit description], the contours of the face, and realistic hair details. She should have distinct depth separating her from the flat [Background Color] background. Lighting & Shadows: Professional studio lighting creating soft, realistic drop shadows cast by the physical frame and, crucially, by the [popping-out elements, e.g., hands/head/arms] onto the solid flat [Background Color] background, enhancing the dramatic depth and illusion. High definition, commercial photography."
}
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 👇
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
A photorealistic, highly detailed commercial product photograph of a standard aluminum [Type of Soda Can] centered against a minimal, textured [Background Color] paper background, with subtle fibers visible. A single, continuous horizontal paper-tear strip runs across the entire width of the frame, seamless from the far-right edge to the far-left edge. The torn channel cuts through the metal body of the can and continues across the background on both sides with a barely perceptible and minimal diagonal slope towards the upper-left. The tear channel is significantly broader, revealing a dense, glistening, and vibrant layer of [Description of Fruit Segments/Sacs/Berries] tightly packed inside. Near the extreme far-left end of this tear, the paper is neatly rolled into a tight, realistic coil that occupies almost the entire left margin. The can features a newly designed, minimalist branding: the upper portion has a stylized, abstract line-art illustration of [Fruit Branch/Plant] in a contrasting [Ink Color], set against a subtle matte geometric [Pattern Type] pattern on the can surface. Below this, the brand name "[Brand Name]" is printed in an elegant, modern dark typography, with smaller technical text "330ml - NATURAL EXTRACT" and a small "Recyclable" logo. A small, detailed graphic of the fruit is located below the torn path. The lighting is soft and cinematic, casting delicate drop shadows beneath the torn paper edges and the large left coil. 8k resolution, macro details on fibrous paper and glossy fruit texture.
curl -X POST https://runapi.ai/api/v1/nano_banana/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "nano-banana-2",
"prompt": "A photorealistic, highly detailed commercial product photograph of a standard aluminum [Type of Soda Can] centered against a minimal, textured [Background Color] paper background, with subtle fibers visible. A single, continuous horizontal paper-tear strip runs across the entire width of the frame, seamless from the far-right edge to the far-left edge. The torn channel cuts through the metal body of the can and continues across the background on both sides with a barely perceptible and minimal diagonal slope towards the upper-left. The tear channel is significantly broader, revealing a dense, glistening, and vibrant layer of [Description of Fruit Segments/Sacs/Berries] tightly packed inside. Near the extreme far-left end of this tear, the paper is neatly rolled into a tight, realistic coil that occupies almost the entire left margin. The can features a newly designed, minimalist branding: the upper portion has a stylized, abstract line-art illustration of [Fruit Branch/Plant] in a contrasting [Ink Color], set against a subtle matte geometric [Pattern Type] pattern on the can surface. Below this, the brand name \"[Brand Name]\" is printed in an elegant, modern dark typography, with smaller technical text \"330ml - NATURAL EXTRACT\" and a small \"Recyclable\" logo. A small, detailed graphic of the fruit is located below the torn path. The lighting is soft and cinematic, casting delicate drop shadows beneath the torn paper edges and the large left coil. 8k resolution, macro details on fibrous paper and glossy fruit texture."
}
JSON
[BRAND NAME] | [SLOGAN]. Act as a Professional Editorial Art Director. PHASE 1: PHYSICS & GROUNDING (THE "STABILITY" RULE). - Analyze [BRAND NAME] category: * CATEGORY A (Active/Sports/Fashion): The subject (person) is in a high-intensity leap, detached from the ground, silhouette against the sky. * CATEGORY B (Automotive/Heavy Goods): The subject (vehicle) must be HEROICALLY GROUNDED. Place the car firmly on a solid surface (asphalt, concrete, or rock). * Perspective: Use an extreme low-angle (worm's-eye view). The car must look massive and dominant, anchored to the bottom of the frame, towering over the viewer. NO floating or flying for vehicles. PHASE 2: DYNAMIC PHOTOGRAPHY & LIGHTING. - Environment: A vast, clear blue sky with minimal soft clouds. - Lighting: Natural, direct sunlight. High-contrast shadows on the subject to emphasize form and texture. - Style: High-end 8k commercial photography. Sharp focus. PHASE 3: TYPOGRAPHY & LAYOUT (MATTE FINISH). - Layout: Use the text from "[SLOGAN]" as massive, ultra-condensed bold sans-serif characters. - Execution: Split "[SLOGAN]" into two parts: one on the far left, one on the far right. - Depth: A part of the subject (e.g., a bumper, a mirror, or a person's limb) must overlap the letters to create a 3D effect. PHASE 4: COLOR STRATEGY (MATTE & REALISTIC). - Graphic Color: NO NEON. Use a solid, matte brand color for the text (e.g., flat Navy for BMW, flat Red for Red Bull). The color must be opaque and non-glowing, resembling high-quality print ink. - Photo Color: Maintain authentic, rich photographic colors for the subject and the sky. The contrast comes from "Flat Graphic vs. Realistic Photo". PHASE 5: FINAL BRANDING. - Logo: Small minimalist [BRAND NAME] logo in the upper corner. - Metadata: Tiny secondary text in a clean sans-serif font at the bottom for a technical/editorial look.
curl -X POST https://runapi.ai/api/v1/nano_banana/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "nano-banana-2",
"prompt": "[BRAND NAME] | [SLOGAN]. Act as a Professional Editorial Art Director. PHASE 1: PHYSICS & GROUNDING (THE \"STABILITY\" RULE). - Analyze [BRAND NAME] category: * CATEGORY A (Active/Sports/Fashion): The subject (person) is in a high-intensity leap, detached from the ground, silhouette against the sky. * CATEGORY B (Automotive/Heavy Goods): The subject (vehicle) must be HEROICALLY GROUNDED. Place the car firmly on a solid surface (asphalt, concrete, or rock). * Perspective: Use an extreme low-angle (worm's-eye view). The car must look massive and dominant, anchored to the bottom of the frame, towering over the viewer. NO floating or flying for vehicles. PHASE 2: DYNAMIC PHOTOGRAPHY & LIGHTING. - Environment: A vast, clear blue sky with minimal soft clouds. - Lighting: Natural, direct sunlight. High-contrast shadows on the subject to emphasize form and texture. - Style: High-end 8k commercial photography. Sharp focus. PHASE 3: TYPOGRAPHY & LAYOUT (MATTE FINISH). - Layout: Use the text from \"[SLOGAN]\" as massive, ultra-condensed bold sans-serif characters. - Execution: Split \"[SLOGAN]\" into two parts: one on the far left, one on the far right. - Depth: A part of the subject (e.g., a bumper, a mirror, or a person's limb) must overlap the letters to create a 3D effect. PHASE 4: COLOR STRATEGY (MATTE & REALISTIC). - Graphic Color: NO NEON. Use a solid, matte brand color for the text (e.g., flat Navy for BMW, flat Red for Red Bull). The color must be opaque and non-glowing, resembling high-quality print ink. - Photo Color: Maintain authentic, rich photographic colors for the subject and the sky. The contrast comes from \"Flat Graphic vs. Realistic Photo\". PHASE 5: FINAL BRANDING. - Logo: Small minimalist [BRAND NAME] logo in the upper corner. - Metadata: Tiny secondary text in a clean sans-serif font at the bottom for a technical/editorial look."
}
JSON
A hyper-realistic studio photograph of a male athlete mid-air as if running or jumping, wearing a pastel pink sweatshirt and light pink jogger pants, with soft blue sneakers. Pink powder smoke is exploding and swirling around his body, especially behind him and around his legs, creating a dynamic motion effect. Clean minimal background with a soft gradient from light gray to pale pink. Cinematic lighting, ultra-sharp focus, shallow depth of field, fashion advertising style, high detail, 8k, soft shadows, professional studio 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": "A hyper-realistic studio photograph of a male athlete mid-air as if running or jumping, wearing a pastel pink sweatshirt and light pink jogger pants, with soft blue sneakers. Pink powder smoke is exploding and swirling around his body, especially behind him and around his legs, creating a dynamic motion effect. Clean minimal background with a soft gradient from light gray to pale pink. Cinematic lighting, ultra-sharp focus, shallow depth of field, fashion advertising style, high detail, 8k, soft shadows, professional studio photography."
}
JSON
Style & Composition: High-fashion editorial typography poster with a strict 1:2 composition split. Layout & Ratio: The frame is divided so that the right two-thirds show the full subject and background, while the left one-third is reserved for the typography masking section. Typography Masking: A massive, ultra-bold, vertical word "[WORD]" is placed on the left third. The text is strictly full-bleed, stretching perfectly and touching the absolute top and absolute bottom edges of the frame with zero vertical padding, gaps, or margins. This typography acts as a stencil mask: the letters reveal the underlying character, while the space to the far left of the letters is a solid, clean white. Subject Details & Positioning: An upper-body shot of [CHARACTER DESCRIPTION]. The model is positioned so that only her left-most side is visible through the letters, while the rest of her body is fully visible and contained on the right side against a solid [COLOR] background, ensuring no part of the subject is cropped by the right edge of the frame. Pose: [POSE DESCRIPTION], ensuring the silhouette remains within the center of the right two-thirds area. Secondary Text: In the top right corner, add the text: "[TEXT]". Use a small, sophisticated, white "Helvetica Condensed" style font with wide letter spacing (kerning) for a premium, minimalist look. Color Palette: A strict monochromatic [COLOR] theme, sharply contrasted by the crisp white negative space on the left. 8k resolution, photorealistic textures, sharp studio lighting, high contrast, clean graphic design 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": "Style & Composition: High-fashion editorial typography poster with a strict 1:2 composition split. Layout & Ratio: The frame is divided so that the right two-thirds show the full subject and background, while the left one-third is reserved for the typography masking section. Typography Masking: A massive, ultra-bold, vertical word \"[WORD]\" is placed on the left third. The text is strictly full-bleed, stretching perfectly and touching the absolute top and absolute bottom edges of the frame with zero vertical padding, gaps, or margins. This typography acts as a stencil mask: the letters reveal the underlying character, while the space to the far left of the letters is a solid, clean white. Subject Details & Positioning: An upper-body shot of [CHARACTER DESCRIPTION]. The model is positioned so that only her left-most side is visible through the letters, while the rest of her body is fully visible and contained on the right side against a solid [COLOR] background, ensuring no part of the subject is cropped by the right edge of the frame. Pose: [POSE DESCRIPTION], ensuring the silhouette remains within the center of the right two-thirds area. Secondary Text: In the top right corner, add the text: \"[TEXT]\". Use a small, sophisticated, white \"Helvetica Condensed\" style font with wide letter spacing (kerning) for a premium, minimalist look. Color Palette: A strict monochromatic [COLOR] theme, sharply contrasted by the crisp white negative space on the left. 8k resolution, photorealistic textures, sharp studio lighting, high contrast, clean graphic design aesthetic."
}
JSON
Minimalist fashion studio photoshoot featuring stylish people sitting confidently on a modern chair, monochromatic aesthetic, subjects wearing bold cobalt-blue outfits (tailored suit or modern streetwear set) with white sneakers and clear glasses, relaxed powerful pose with legs apart and hands resting naturally, clean blue studio background with a large geometric letter “A” behind them, soft professional studio lighting, fashion editorial composition, modern luxury brand campaign style, ultra-realistic, sharp focus, high detail, 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": "Minimalist fashion studio photoshoot featuring stylish people sitting confidently on a modern chair, monochromatic aesthetic, subjects wearing bold cobalt-blue outfits (tailored suit or modern streetwear set) with white sneakers and clear glasses, relaxed powerful pose with legs apart and hands resting naturally, clean blue studio background with a large geometric letter “A” behind them, soft professional studio lighting, fashion editorial composition, modern luxury brand campaign style, ultra-realistic, sharp focus, high detail, 8K."
}
JSON
A dynamic fashion advertisement for Nike showing a hyper-realistic model mid-twist jump, light trails following her limbs. Background: prism-shifting gradient (hot magenta to sapphire) with refracted lens flares. The model wears iridescent Nike runner tights and a cropped tech hoodie in holographic white. Bold serif "NIKE" and motion-glitched "LUMINA" in layered text behind. High-energy, futuristic aesthetic with fashion gloss
curl -X POST https://runapi.ai/api/v1/nano_banana/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "nano-banana-2",
"prompt": "A dynamic fashion advertisement for Nike showing a hyper-realistic model mid-twist jump, light trails following her limbs. Background: prism-shifting gradient (hot magenta to sapphire) with refracted lens flares. The model wears iridescent Nike runner tights and a cropped tech hoodie in holographic white. Bold serif \"NIKE\" and motion-glitched \"LUMINA\" in layered text behind. High-energy, futuristic aesthetic with fashion gloss"
}
JSON
[PERSON NAME]. Act as a graphic designer creating a minimalist, avant-garde streetwear poster. COMPOSITION (THE FUSION): The image is a creative fusion of a massive typographic name and a monochrome portrait of [PERSON NAME]. The Subject: A high-contrast, black-and-white full-body or 3/4 cut-out photograph of [PERSON NAME]. The subject stands centrally, looking cool and detached. The Typography: The person's name is written horizontally across the entire width of the image. The text interacts with the body: the person stands through the letters, creating a "woven" depth effect (some limbs in front of text, some behind), or the portrait creates a silhouette mask for the text. TYPOGRAPHY STYLE (MIXED SCRIPTS): Mimic the specific "Street Editorial" font pairing: The First Letter: The initial letter of the name is rendered in a large, sweeping, expressive Calligraphic Script or Brush font (dynamic and loose). The Rest of the Name: The remaining letters are rendered in an Ultra-Heavy, Geometric Sans-Serif font (like Impact or Helvetica Black). Color: The text is solid Dark Grey or Black. AESTHETICS & ATMOSPHERE: Palette: Strictly Monochrome (Black, White, and Greyscale). Background: Pure, vast White Minimalist background. Extensive negative space. Vibe: Raw, "Zine" aesthetic, cut-and-paste collage feel, high-fashion streetwear poster. LAYOUT DETAILS: Add very small, microscopic functional text in the extreme corners (e.g., "poster design", "2025", "fig 01") to enhance the Swiss Design poster feel.
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": "[PERSON NAME]. Act as a graphic designer creating a minimalist, avant-garde streetwear poster. COMPOSITION (THE FUSION): The image is a creative fusion of a massive typographic name and a monochrome portrait of [PERSON NAME]. The Subject: A high-contrast, black-and-white full-body or 3/4 cut-out photograph of [PERSON NAME]. The subject stands centrally, looking cool and detached. The Typography: The person's name is written horizontally across the entire width of the image. The text interacts with the body: the person stands through the letters, creating a \"woven\" depth effect (some limbs in front of text, some behind), or the portrait creates a silhouette mask for the text. TYPOGRAPHY STYLE (MIXED SCRIPTS): Mimic the specific \"Street Editorial\" font pairing: The First Letter: The initial letter of the name is rendered in a large, sweeping, expressive Calligraphic Script or Brush font (dynamic and loose). The Rest of the Name: The remaining letters are rendered in an Ultra-Heavy, Geometric Sans-Serif font (like Impact or Helvetica Black). Color: The text is solid Dark Grey or Black. AESTHETICS & ATMOSPHERE: Palette: Strictly Monochrome (Black, White, and Greyscale). Background: Pure, vast White Minimalist background. Extensive negative space. Vibe: Raw, \"Zine\" aesthetic, cut-and-paste collage feel, high-fashion streetwear poster. LAYOUT DETAILS: Add very small, microscopic functional text in the extreme corners (e.g., \"poster design\", \"2025\", \"fig 01\") to enhance the Swiss Design poster feel."
}
JSON
Create a digital modern maximalism style sports collage of [TEAm Name] [Player name] visuals with grainy textures, abstract geometric shapes, dynamic grid layout, minimal background, contemporary editorial composition, inspired by [BRAND NAME ex Nike...] campaigns and modern sports graphic design, strong visual rhythm, bold and emotional atmosphere. Post-process film grain, and specially cinematic color-graded tones for serious intensity.
Pixar 3D CGI animated movie poster style, ensemble cast featuring the most iconic and recognizable characters from [MOVIE/SHOW], all rendered as Pixar-style 3D animated characters with exaggerated expressive faces, smooth stylized skin, big eyes, chunky proportions. Characters automatically selected as the most famous heroes and villains from [MOVIE/SHOW]. Dramatic layered composition: central hero front and center, others fanned behind in dynamic action poses. Background color automatically chosen to match the iconic tone and palette of [MOVIE/SHOW]. Bold title text at bottom: [MOVIE/SHOW] in the original film's iconic font style. Cinematic lighting, rim light on characters, deep shadows. 3:4 vertical aspect ratio. High detail, polished Pixar feature film 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": "Pixar 3D CGI animated movie poster style, ensemble cast featuring the most iconic and recognizable characters from [MOVIE/SHOW], all rendered as Pixar-style 3D animated characters with exaggerated expressive faces, smooth stylized skin, big eyes, chunky proportions. Characters automatically selected as the most famous heroes and villains from [MOVIE/SHOW]. Dramatic layered composition: central hero front and center, others fanned behind in dynamic action poses. Background color automatically chosen to match the iconic tone and palette of [MOVIE/SHOW]. Bold title text at bottom: [MOVIE/SHOW] in the original film's iconic font style. Cinematic lighting, rim light on characters, deep shadows. 3:4 vertical aspect ratio. High detail, polished Pixar feature film aesthetic."
}
JSON
[upload luxury product photo] BRAND NAME: [Put the brand name here] Create ONE luxury editorial poster. Keep the product EXACT and unchanged. Use the BRAND NAME to infer identity and place the REAL official logo (correct proportions) in the most brand-appropriate position with subtle print texture. Add a perfectly matched attractive model wearing the product naturally. Rich deep colors, HDR, premium studio lighting, clean background, strong negative space, ultra-sharp 8K. No extra text, 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": "[upload luxury product photo] BRAND NAME: [Put the brand name here] Create ONE luxury editorial poster. Keep the product EXACT and unchanged. Use the BRAND NAME to infer identity and place the REAL official logo (correct proportions) in the most brand-appropriate position with subtle print texture. Add a perfectly matched attractive model wearing the product naturally. Rich deep colors, HDR, premium studio lighting, clean background, strong negative space, ultra-sharp 8K. No extra text, no watermark."
}
JSON
A hyper-realistic macro shot of a paintbrush creating a thick textured paint stroke on a clean white background. The paint forms the shape and colors of the [COUNTRY FLAG], flowing dynamically like a wave. Inside the paint stroke, a highly detailed miniature cityscape of [COUNTRY NAME] emerges, including iconic landmarks such as [LANDMARK 1], [LANDMARK 2], [LANDMARK 3]. The paint has visible brush textures, glossy acrylic finish, rich vibrant colors.
curl -X POST https://runapi.ai/api/v1/nano_banana/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "nano-banana-2",
"prompt": "A hyper-realistic macro shot of a paintbrush creating a thick textured paint stroke on a clean white background. The paint forms the shape and colors of the [COUNTRY FLAG], flowing dynamically like a wave. Inside the paint stroke, a highly detailed miniature cityscape of [COUNTRY NAME] emerges, including iconic landmarks such as [LANDMARK 1], [LANDMARK 2], [LANDMARK 3]. The paint has visible brush textures, glossy acrylic finish, rich vibrant colors."
}
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
Masterpiece, best quality, high resolution, 8k, (Photorealistic:1.4), (Vibrant natural colors:1.2), (Full body shot:1.6), minimalist fashion scrapbook page. Subject: A full body fashion photo of [Character Description] standing in a [Pose]. The subject is wearing [Detailed Outfit]. The subject is a sharp, high-detail photographic cutout with sticker borders. The sticker has a die-cut white paper edge with visible paper-fiber texture on the cut-line. This white border has a subtle 3D thickness (beveled edge) that catches the light, creating a realistic micro-shadow. Composition: Professional top-down flat-lay view. A thin stack of 3-4 clean-cut premium white paper sheets (smooth edges) placed on a seamless Soft [Color] background. Medium camera distance for a clear full-body view. A single, (prominent oversized silver metal trombone paperclip:1.5) at the top left corner, showing realistic metallic reflections and micro-scratches. 5 delicate hand-drawn black ink arrows pointing to specific fashion details: "[Feature 1]" (pointing to [Detail]). "[Feature 2]" (pointing to [Detail]). "[Feature 3]" (pointing to [Detail]). "[Feature 4]" (pointing to [Detail]). All annotations are in refined, elegant handwritten cursive. Ray-traced ambient occlusion around the sticker's white border to emphasize physical elevation and depth. Ray-traced soft shadows between the paper layers. High-end editorial studio lighting. Visible tactile paper micro-texture throughout the character's edges, clean and modern high-fashion aesthetic. No grayscale, full color photography, no illustration.
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": "Masterpiece, best quality, high resolution, 8k, (Photorealistic:1.4), (Vibrant natural colors:1.2), (Full body shot:1.6), minimalist fashion scrapbook page. Subject: A full body fashion photo of [Character Description] standing in a [Pose]. The subject is wearing [Detailed Outfit]. The subject is a sharp, high-detail photographic cutout with sticker borders. The sticker has a die-cut white paper edge with visible paper-fiber texture on the cut-line. This white border has a subtle 3D thickness (beveled edge) that catches the light, creating a realistic micro-shadow. Composition: Professional top-down flat-lay view. A thin stack of 3-4 clean-cut premium white paper sheets (smooth edges) placed on a seamless Soft [Color] background. Medium camera distance for a clear full-body view. A single, (prominent oversized silver metal trombone paperclip:1.5) at the top left corner, showing realistic metallic reflections and micro-scratches. 5 delicate hand-drawn black ink arrows pointing to specific fashion details: \"[Feature 1]\" (pointing to [Detail]). \"[Feature 2]\" (pointing to [Detail]). \"[Feature 3]\" (pointing to [Detail]). \"[Feature 4]\" (pointing to [Detail]). All annotations are in refined, elegant handwritten cursive. Ray-traced ambient occlusion around the sticker's white border to emphasize physical elevation and depth. Ray-traced soft shadows between the paper layers. High-end editorial studio lighting. Visible tactile paper micro-texture throughout the character's edges, clean and modern high-fashion aesthetic. No grayscale, full color photography, no illustration."
}
JSON
[BRAND NAME] [PRODUCT TYPE] (Clothing / Food / Automotive / Tech). Goal: Generate a professional "scrapbook" style collage poster for [BRAND NAME] centered around a [PRODUCT TYPE]. 1. HERO PRODUCT (BOTTOM FOCUS) - Object: A high-definition, realistic 3D render of a [PRODUCT TYPE] by [BRAND NAME] at the bottom center. - Placement: Slightly angled to show depth, with soft realistic contact shadows on a plain off-white floor. 2. THE MULTI-LAYERED COLLAGE STACK - Photos: A vertical stack of overlapping photos with RAGGED, TORN paper edges rising above the product. - Content: Photos should show [PRODUCT TYPE] in use, lifestyle shots related to [BRAND NAME], and close-ups of specific details. - Materials: Physical swatches of textures related to [PRODUCT TYPE] (e.g., leather/fabric for clothing, metal/carbon for cars, organic ingredients for food). Include visible raw edges and stitching. - Fasteners: Use strips of semi-transparent masking tape and black duct tape with the "[BRAND NAME]" logo printed in white to "hold" the pieces together. 3. GRAPHIC OVERLAYS & STAMPS - Stamp: A black, distressed ink stamp or seal near the hero product with text: "AUTHENTIC QUALITY // SUSTAINABLE CHOICE". - Typography: Small, clean sans-serif and typewriter-style text blocks describing the heritage of [BRAND NAME] placed at the bottom. - Logo: The primary "[BRAND NAME]" logo centered at the very bottom in a minimalist font. 4. STYLE & ATMOSPHERE - Aesthetic: Industrial DIY, workshop moodboard, high-end editorial collage. - Lighting: Bright, studio high-key lighting with soft, multi-layered shadows between the paper scraps and textures. - Quality: 8K resolution, macro detail on paper grain, fabric fibers, and tape adhesive.
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] [PRODUCT TYPE] (Clothing / Food / Automotive / Tech). Goal: Generate a professional \"scrapbook\" style collage poster for [BRAND NAME] centered around a [PRODUCT TYPE]. 1. HERO PRODUCT (BOTTOM FOCUS) - Object: A high-definition, realistic 3D render of a [PRODUCT TYPE] by [BRAND NAME] at the bottom center. - Placement: Slightly angled to show depth, with soft realistic contact shadows on a plain off-white floor. 2. THE MULTI-LAYERED COLLAGE STACK - Photos: A vertical stack of overlapping photos with RAGGED, TORN paper edges rising above the product. - Content: Photos should show [PRODUCT TYPE] in use, lifestyle shots related to [BRAND NAME], and close-ups of specific details. - Materials: Physical swatches of textures related to [PRODUCT TYPE] (e.g., leather/fabric for clothing, metal/carbon for cars, organic ingredients for food). Include visible raw edges and stitching. - Fasteners: Use strips of semi-transparent masking tape and black duct tape with the \"[BRAND NAME]\" logo printed in white to \"hold\" the pieces together. 3. GRAPHIC OVERLAYS & STAMPS - Stamp: A black, distressed ink stamp or seal near the hero product with text: \"AUTHENTIC QUALITY // SUSTAINABLE CHOICE\". - Typography: Small, clean sans-serif and typewriter-style text blocks describing the heritage of [BRAND NAME] placed at the bottom. - Logo: The primary \"[BRAND NAME]\" logo centered at the very bottom in a minimalist font. 4. STYLE & ATMOSPHERE - Aesthetic: Industrial DIY, workshop moodboard, high-end editorial collage. - Lighting: Bright, studio high-key lighting with soft, multi-layered shadows between the paper scraps and textures. - Quality: 8K resolution, macro detail on paper grain, fabric fibers, and tape adhesive."
}
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.