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.
Create an ultra-HD, hyper-realistic digital poster of a floating miniature island shaped like [Country], resting on white clouds in the sky. Blend iconic landmarks, natural landscapes (like [landmark 1], [landscape 2], or [landscape 3]), and cultural elements unique to [Country]. Carve "[Country]" into the terrain using large white 3D letters. Add artistic details like [wildlife], cinematic lighting, vivid colors, aerial perspective, and sun reflections to enhance realism
curl -X POST https://runapi.ai/api/v1/gpt_image_2/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "gpt-image-2",
"prompt": "Create an ultra-HD, hyper-realistic digital poster of a floating miniature island shaped like [Country], resting on white clouds in the sky. Blend iconic landmarks, natural landscapes (like [landmark 1], [landscape 2], or [landscape 3]), and cultural elements unique to [Country]. Carve \"[Country]\" into the terrain using large white 3D letters. Add artistic details like [wildlife], cinematic lighting, vivid colors, aerial perspective, and sun reflections to enhance realism"
}
JSON
Surreal comedic scene inside a modern kitchen: a young man bends backward in an extreme dodge pose, acrobatic and exaggerated, with a kettle mid-air above him splashing hot tea in a dramatic frozen moment. A woman in the background extends her arm as if she accidentally threw the kettle, expression shocked and energetic.Dynamic action freeze-frame, dramatic liquid splash, wide-angle lens distortion, sharp details, realistic lighting, cinematic color grading, humorous storytelling, high-resolution digital art.
curl -X POST https://runapi.ai/api/v1/gpt_image_2/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "gpt-image-2",
"prompt": "Surreal comedic scene inside a modern kitchen: a young man bends backward in an extreme dodge pose, acrobatic and exaggerated, with a kettle mid-air above him splashing hot tea in a dramatic frozen moment. A woman in the background extends her arm as if she accidentally threw the kettle, expression shocked and energetic.Dynamic action freeze-frame, dramatic liquid splash, wide-angle lens distortion, sharp details, realistic lighting, cinematic color grading, humorous storytelling, high-resolution digital art."
}
JSON
Minimalist food photograph, [1080x1080] – a single [FOOD] rests on a light, matte surface and is captured mid-transformation into a 3D pixelized form: one half remains intact while the other organically fragments into large, floating cubes that drift outward, each cube revealing the object’s texture, ingredients, and colors. Studio lighting with soft, realistic shadows, shallow depth of field, tasteful perspective and composition, hyperrealistic detail, stylish geometric abstraction, subtle motion blur on the cubes, high resolution, cinematic close-up.
curl -X POST https://runapi.ai/api/v1/gpt_image_2/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "gpt-image-2",
"prompt": "Minimalist food photograph, [1080x1080] – a single [FOOD] rests on a light, matte surface and is captured mid-transformation into a 3D pixelized form: one half remains intact while the other organically fragments into large, floating cubes that drift outward, each cube revealing the object’s texture, ingredients, and colors. Studio lighting with soft, realistic shadows, shallow depth of field, tasteful perspective and composition, hyperrealistic detail, stylish geometric abstraction, subtle motion blur on the cubes, high resolution, cinematic close-up."
}
JSON
Create an Ultra-realistic photo composite of uploaded person breaking out of an Instagram post frame. Standing pose, both hands holding frame edges, upper body outside frame with real shadows. High top-down view, strong 10mm fisheye effect on person only (big head, smaller body), frame straight. Confident upward gaze, purple graffiti puffer jacket, black tee, gold chain, white sneakers, sunglasses, black cap, yellow floor, clean Instagram UI (simeon-sanai) overlay, photorealistic.
curl -X POST https://runapi.ai/api/v1/gpt_image_2/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "gpt-image-2",
"prompt": "Create an Ultra-realistic photo composite of uploaded person breaking out of an Instagram post frame. Standing pose, both hands holding frame edges, upper body outside frame with real shadows. High top-down view, strong 10mm fisheye effect on person only (big head, smaller body), frame straight. Confident upward gaze, purple graffiti puffer jacket, black tee, gold chain, white sneakers, sunglasses, black cap, yellow floor, clean Instagram UI (simeon-sanai) overlay, photorealistic."
}
JSON
curl -X POST https://runapi.ai/api/v1/gpt_image_2/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "gpt-image-2",
"prompt": "Make a wheatpaste poster setup on a brick wall in sf featuring posters from various AI labs"
}
JSON
A stylish man wearing a tan suit and sunglasses is featured in a creative split image, framed by two ornate gold frames. In the top frame, he is pouring Coca-Cola from a bottle. The cola streams downward, passing through the gap between the frames. In the bottom frame, the same man, also in a tan suit and sunglasses, is shown with a joyful expression as the stream of cola splashes into a glass mug he is holding, creating a dynamic splash.The background behind the frames is a softly blurred night cityscape with tall buildings and lights, suggesting.
curl -X POST https://runapi.ai/api/v1/gpt_image_2/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "gpt-image-2",
"prompt": "A stylish man wearing a tan suit and sunglasses is featured in a creative split image, framed by two ornate gold frames. In the top frame, he is pouring Coca-Cola from a bottle. The cola streams downward, passing through the gap between the frames. In the bottom frame, the same man, also in a tan suit and sunglasses, is shown with a joyful expression as the stream of cola splashes into a glass mug he is holding, creating a dynamic splash.The background behind the frames is a softly blurred night cityscape with tall buildings and lights, suggesting."
}
JSON
Ultra-realistic 8K full body portrait of [PERSON’S FULL NAME], wearing a clean and pressed white social shirt with folded collar and a small lapel microphone, dark navy-blue dress pants and polished brown social shoes. Casually and unpretentiously leaning against a smooth light gray studio wall; hands are in pockets and one leg is crossed over the other, with relaxed and confident body language. Add to the wall next to them a prominent vector portrait in black and white of their face and bust - with sharp lines and angles, overlapping polygonal shapes and a minimalist modern graphic style, right below the information: “[PERSON’S FULL NAME]”, and below the name: “[PROFESSION]”
curl -X POST https://runapi.ai/api/v1/nano_banana/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "nano-banana-2",
"prompt": "Ultra-realistic 8K full body portrait of [PERSON’S FULL NAME], wearing a clean and pressed white social shirt with folded collar and a small lapel microphone, dark navy-blue dress pants and polished brown social shoes. Casually and unpretentiously leaning against a smooth light gray studio wall; hands are in pockets and one leg is crossed over the other, with relaxed and confident body language. Add to the wall next to them a prominent vector portrait in black and white of their face and bust - with sharp lines and angles, overlapping polygonal shapes and a minimalist modern graphic style, right below the information: “[PERSON’S FULL NAME]”, and below the name: “[PROFESSION]”"
}
JSON
Hyper-realistic cinematic 8k photograph, low-angle wide perspective. A massive Monster Energy can standing vertically like an arctic monument, partially frozen inside thick blue ice and snow. Frost covering the textured surface, icicles forming along the logo and rim, snow filling the pull-tab opening. Snowcat vehicle and scientists in red parkas emphasize scale. Overcast arctic daylight, HDR, ultra-detailed frozen textures, cinematic realism --ar 2:3
curl -X POST https://runapi.ai/api/v1/gpt_image_2/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "gpt-image-2",
"prompt": "Hyper-realistic cinematic 8k photograph, low-angle wide perspective. A massive Monster Energy can standing vertically like an arctic monument, partially frozen inside thick blue ice and snow. Frost covering the textured surface, icicles forming along the logo and rim, snow filling the pull-tab opening. Snowcat vehicle and scientists in red parkas emphasize scale. Overcast arctic daylight, HDR, ultra-detailed frozen textures, cinematic realism --ar 2:3"
}
JSON
A hyper-realistic travel advertisement in square format (1080x1080), featuring a hand holding a sleek, ultra-thin smartphone or tablet in portrait orientation, tilted slightly sideways to create a striking 3D portal effect. The screen displays a high-resolution image of an iconic landmark from [COUNTRY], which continues into the real background, blending seamlessly. The landmark appears to emerge from the screen. Birds fly nearby and a commercial airplane passes through a bright blue sky with soft white clouds. Bold, clean sans-serif text reading [CITY] is placed prominently above. The lighting is warm and natural, casting soft shadows across the landscape. The surroundings reflect the region’s natural environment (like meadows, coastlines, or city skylines). The device is glossy and minimal-bezel, enhancing realism and depth.
curl -X POST https://runapi.ai/api/v1/gpt_image_2/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "gpt-image-2",
"prompt": "A hyper-realistic travel advertisement in square format (1080x1080), featuring a hand holding a sleek, ultra-thin smartphone or tablet in portrait orientation, tilted slightly sideways to create a striking 3D portal effect. The screen displays a high-resolution image of an iconic landmark from [COUNTRY], which continues into the real background, blending seamlessly. The landmark appears to emerge from the screen. Birds fly nearby and a commercial airplane passes through a bright blue sky with soft white clouds. Bold, clean sans-serif text reading [CITY] is placed prominently above. The lighting is warm and natural, casting soft shadows across the landscape. The surroundings reflect the region’s natural environment (like meadows, coastlines, or city skylines). The device is glossy and minimal-bezel, enhancing realism and depth."
}
JSON
Present a clear, 45° top-down isometric miniature 3D cartoon diorama of the [BRAND], with soft refined textures, realistic PBR materials, and gentle lifelike lighting. Create a small raised diorama-style base that includes the most recognizable elements of the store, along with tiny stylized characters if needed (no facial details). Use a clean solid [BACKGROUND COLOR] background. At the top-center, display [BRAND] in large bold text, and place the official logo associated with [BRAND] below the subtext. All text must automatically match the background contrast (white or black). Composition: perfectly centered layout, square 1080x1080, ultra-clean, high-clarity diorama aesthetic.
curl -X POST https://runapi.ai/api/v1/gpt_image_2/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "gpt-image-2",
"prompt": "Present a clear, 45° top-down isometric miniature 3D cartoon diorama of the [BRAND], with soft refined textures, realistic PBR materials, and gentle lifelike lighting. Create a small raised diorama-style base that includes the most recognizable elements of the store, along with tiny stylized characters if needed (no facial details). Use a clean solid [BACKGROUND COLOR] background. At the top-center, display [BRAND] in large bold text, and place the official logo associated with [BRAND] below the subtext. All text must automatically match the background contrast (white or black). Composition: perfectly centered layout, square 1080x1080, ultra-clean, high-clarity diorama aesthetic."
}
JSON
Avant-garde sports fashion advertisement, oversized tennis racket positioned like monumental sculpture, female athlete seated casually on the strings as if a suspended lounge, giant word “PRECISION” in bold typography behind, crisp white studio backdrop, reflective court-like floor, luxury sportswear editorial aesthetic, cinematic lighting, ultra-clean composition, 1:1
Convert uploaded photo into ultra-wide 10mm fisheye portrait from dramatic high top-down angle with strong perspective distortion (larger head, compressed body). Add black oversized sunglasses and plain white cap, right hand adjusting cap, confident upward gaze. Color-block puffer jacket (burnt orange/cream/brown), white tee, white sneakers. Bold terracotta studio background, smooth gradient, high contrast, sharp editorial lighting, 8k.
Top-down flat lay on a rustic wooden table, cozy aesthetic, soft natural light. A glass of iced tea with lemon slices and ice cubes, a glazed donut, a small succulent plant in a white pot, a vintage book, and eyeglasses. A sleeping tabby cat curled on a blanket at the edge. White hand-drawn doodle outlines and arrows around each object with playful handwritten labels like “refreshing iced tea,” “sweet treat,” “little green friend,” “afternoon read,” and “cutest thing in the world – cat.” Warm tones, minimal shadows, lifestyle photography, high detail, Instagram aesthetic.
curl -X POST https://runapi.ai/api/v1/gpt_image_2/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "gpt-image-2",
"prompt": "Top-down flat lay on a rustic wooden table, cozy aesthetic, soft natural light. A glass of iced tea with lemon slices and ice cubes, a glazed donut, a small succulent plant in a white pot, a vintage book, and eyeglasses. A sleeping tabby cat curled on a blanket at the edge. White hand-drawn doodle outlines and arrows around each object with playful handwritten labels like “refreshing iced tea,” “sweet treat,” “little green friend,” “afternoon read,” and “cutest thing in the world – cat.” Warm tones, minimal shadows, lifestyle photography, high detail, Instagram aesthetic."
}
JSON
curl -X POST https://runapi.ai/api/v1/gpt_image_2/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "gpt-image-2",
"prompt": "Conceptual transformation, bird nest construction techniques shaping a sculptural lounge chair, sequence from nest-building photography to weaving diagrams to organic structural abstraction to final product, interwoven frame forming seat and backrest, natural fibers with soft cushioning, earthy tones with refined finish, sustainable luxury aesthetic, presentation layout, sketches above, render below, warm natural lighting. AR – 4:3"
}
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.