Examples for using gpt-image-2 through RunAPI from agent tools or API calls. Copy a prompt, then use it in Claude Code, Codex, Cursor, Windsurf, or your backend.
{ "type": "image_generation_prompt", "style": "photorealistic cinematic street photography, documentary aesthetic", "resolution": "ultra-high resolution", "identity_preservation": { "use_reference_image": true, "alter_face": false, "strict_identity_lock": true, "notes": "Use the uploaded reference image as the compositional base. Replace the central character with the woman from the reference image, preserving exact facial structure, skin texture, lighting direction, shadows, depth of field, angle, and emotional expression. No distortions, no artifacts, no skin tone mismatch." }, "subject": { "gender": "female", "appearance": { "hair": "bald (as in the original composition)", "age": "adult", "expression": "calm, introspective, emotionally neutral", "skin": "realistic texture with natural pores and tones" }, "pose": { "position": "standing still in the center of a busy urban crosswalk", "action": "gently smelling a flower held near the face", "posture": "upright, relaxed, perfectly static" }, "wardrobe": { "outerwear": "dark minimalist blazer", "top": "black shirt" } }, "environment": { "location": "busy urban pedestrian crosswalk", "atmosphere": "metropolitan street scene", "crowd": { "behavior": "people moving rapidly around the subject", "effect": "motion blur from long exposure" } }, "lighting": { "type": "natural daylight", "conditions": "overcast sky", "quality": "soft, diffused light", "effects": [ "realistic skin tones", "no artificial highlights", "natural shadows" ] }, "cinematic_effects": { "long_exposure": true, "subject_clarity": "central subject perfectly sharp", "surroundings": "crowd blurred with motion", "mood": "isolation and stillness amid chaos" }, "color_grading": { "palette": [ "cool grays", "muted browns", "soft blacks" ], "saturation": "desaturated", "style": "professional cinematic grading" }, "camera": { "lens_look": "85mm", "depth_of_field": "shallow", "grain": "realistic film grain", "perspective": "identical to original reference image" }, "quality_constraints": [ "no facial deformation", "no AI artifacts", "no artificial lighting effects", "perfect facial integration", "consistent shadows and perspective" ], "output_goal": "Create a photorealistic, cinematic street photograph featuring a woman standing still in a busy crosswalk, smelling a flower, with long-exposure motion blur around her, preserving the exact realism, lighting, depth, and emotional tone of the original reference image." }
Create the most realistic front page design of a vintage newspaper featuring the main character. The layout should be made in the style of a real printed newspaper with a cinematic black-and-white aesthetic. The main photo should be prominently placed in the center, framed, like the image in the title of the article. The subject in the photo should remain unchanged and clearly distinguishable in natural light and slightly increased contrast in order to match the spectacular editorial style. Create a bold, attention-grabbing headline at the top (create a unique title that matches the spirit of the photo - it can be romantic, mysterious, funny, or dramatic). Add a smaller subtitle under it, which will look like a real newspaper caption. Add realistic newspaper elements: Columns of small text (in the style of lorem ipsum, but framed like real news) At the top is the fictitious name of the publication (for example, “The Daily Prompts”, “AI Times” or similar - think creatively, according to the picture) Date, issue number and location Decorative lines, dividers, and vintage typography Small additional articles or captions to the main image Optional stamps, doodles, or editorial notes to add personality. Style: Black and white or slightly faded monochrome paper Fine paper texture, grain, and ink defects Small shadows and creases that mimic real printed paper The aesthetics of a clean but slightly worn vintage newspaper Mood: Give the design personality, expressiveness and plot, as if the plot is part of the main article. Aspect ratio: 4:5 or 1:1 High-detail, ultra-realistic hybrid of editorial photography and print design.
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 the most realistic front page design of a vintage newspaper featuring the main character. The layout should be made in the style of a real printed newspaper with a cinematic black-and-white aesthetic. The main photo should be prominently placed in the center, framed, like the image in the title of the article. The subject in the photo should remain unchanged and clearly distinguishable in natural light and slightly increased contrast in order to match the spectacular editorial style. Create a bold, attention-grabbing headline at the top (create a unique title that matches the spirit of the photo - it can be romantic, mysterious, funny, or dramatic). Add a smaller subtitle under it, which will look like a real newspaper caption. Add realistic newspaper elements: Columns of small text (in the style of lorem ipsum, but framed like real news) At the top is the fictitious name of the publication (for example, “The Daily Prompts”, “AI Times” or similar - think creatively, according to the picture) Date, issue number and location Decorative lines, dividers, and vintage typography Small additional articles or captions to the main image Optional stamps, doodles, or editorial notes to add personality. Style: Black and white or slightly faded monochrome paper Fine paper texture, grain, and ink defects Small shadows and creases that mimic real printed paper The aesthetics of a clean but slightly worn vintage newspaper Mood: Give the design personality, expressiveness and plot, as if the plot is part of the main article. Aspect ratio: 4:5 or 1:1 High-detail, ultra-realistic hybrid of editorial photography and print design."
}
JSON
A hyperrealistic Nike sneaker advertisement shot in a dark, moody editorial style. A male leg wearing crisp white athletic crew socks with subtle Nike logo detail is suspended mid-air against a near-black charcoal background, angled diagonally toward the camera at a bold 45-degree perspective. The sneaker — a Nike low-top silhouette featuring a clean two-tone colorway of glacier teal suede panels and off-white tumbled leather, with an iridescent chrome Swoosh catching ambient light — dominates the lower two-thirds of the frame. The composition uses shallow depth of field with sharp focus on the shoe and soft blur on the upper leg. The background is layered with subtle urban texture - faint graffiti strokes in electric yellow and muted olive, barely visible through a heavy dark vignette. Multiple rows of ultra-small all-caps typographic text orbit the sneaker at different angles, reading phrases like "THE ONLY LIMITS ARE THE ONES YOU SET FOR YOURSELF" - evoking motion, speed, and energy. Some text runs vertically, some at 30-degree angles, giving the composition a chaotic yet intentional graphic design feeling. At the upper right, the bold Nike wordmark and Swoosh logo appear in clean white against the dark background. At the top center, a thin horizontal navigation-style text bar reads: "PURE COMFORT · ALWAYS AHEAD · THE FUTURE IS NOW" in spaced all-caps serif font. A large, commanding headline is placed center-right in contrasting weight typography - "MOVE" in massive ultra-bold white letters followed by "BEYOND" in lighter weight, creating dramatic type hierarchy. Small yellow plus (+) symbols and diagonal arrows (↗) are scattered throughout the composition as accent details, adding a contemporary graphic zine aesthetic. Bottom left features a bold brand slogan lockup: "DEFINE YOUR STRIDE" in large bold sans-serif white text with a thin subline: "An inspiring reminder that speed is a mindset. Every step forward is a statement." The overall lighting is dramatic and directional - a single cold key light from the left, causing the Swoosh to shimmer and the white leather to glow against the darkness. Photorealistic. Commercial photography quality. High contrast. 4K resolution, 3:4 vertical format optimized for social media.
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 hyperrealistic Nike sneaker advertisement shot in a dark, moody editorial style. A male leg wearing crisp white athletic crew socks with subtle Nike logo detail is suspended mid-air against a near-black charcoal background, angled diagonally toward the camera at a bold 45-degree perspective. The sneaker — a Nike low-top silhouette featuring a clean two-tone colorway of glacier teal suede panels and off-white tumbled leather, with an iridescent chrome Swoosh catching ambient light — dominates the lower two-thirds of the frame. The composition uses shallow depth of field with sharp focus on the shoe and soft blur on the upper leg. The background is layered with subtle urban texture - faint graffiti strokes in electric yellow and muted olive, barely visible through a heavy dark vignette. Multiple rows of ultra-small all-caps typographic text orbit the sneaker at different angles, reading phrases like \"THE ONLY LIMITS ARE THE ONES YOU SET FOR YOURSELF\" - evoking motion, speed, and energy. Some text runs vertically, some at 30-degree angles, giving the composition a chaotic yet intentional graphic design feeling. At the upper right, the bold Nike wordmark and Swoosh logo appear in clean white against the dark background. At the top center, a thin horizontal navigation-style text bar reads: \"PURE COMFORT · ALWAYS AHEAD · THE FUTURE IS NOW\" in spaced all-caps serif font. A large, commanding headline is placed center-right in contrasting weight typography - \"MOVE\" in massive ultra-bold white letters followed by \"BEYOND\" in lighter weight, creating dramatic type hierarchy. Small yellow plus (+) symbols and diagonal arrows (↗) are scattered throughout the composition as accent details, adding a contemporary graphic zine aesthetic. Bottom left features a bold brand slogan lockup: \"DEFINE YOUR STRIDE\" in large bold sans-serif white text with a thin subline: \"An inspiring reminder that speed is a mindset. Every step forward is a statement.\" The overall lighting is dramatic and directional - a single cold key light from the left, causing the Swoosh to shimmer and the white leather to glow against the darkness. Photorealistic. Commercial photography quality. High contrast. 4K resolution, 3:4 vertical format optimized for social media."
}
JSON
A cinematic digital artwork of a stylish animated girl walking out of a modern X (Twitter) profile interface. The background shows a real mobile UI profile screen with the name "Noor 🌸", verified badge, username @Noor_ul_ain43, and detailed bio. The girl matches the profile picture — soft aesthetic illustration style, short wavy black hair, gold hoop earrings, minimal makeup, wearing a black turtleneck and beige coat with matching pants and sneakers. She is stepping forward confidently from the screen into real space. The right half of her body dissolves into dynamic particles — a mix of black dust, teal, and orange energy splashes, flowing outward like liquid + digital fragments. Clean composition: left side = structured UI, right side = abstract particle explosion. Soft cinematic lighting, depth of field, ultra-detailed textures, smooth shadows, 4K render, octane render, Unreal Engine 5 style, trending on ArtStation.
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 cinematic digital artwork of a stylish animated girl walking out of a modern X (Twitter) profile interface. The background shows a real mobile UI profile screen with the name \"Noor 🌸\", verified badge, username @Noor_ul_ain43, and detailed bio. The girl matches the profile picture — soft aesthetic illustration style, short wavy black hair, gold hoop earrings, minimal makeup, wearing a black turtleneck and beige coat with matching pants and sneakers. She is stepping forward confidently from the screen into real space. The right half of her body dissolves into dynamic particles — a mix of black dust, teal, and orange energy splashes, flowing outward like liquid + digital fragments. Clean composition: left side = structured UI, right side = abstract particle explosion. Soft cinematic lighting, depth of field, ultra-detailed textures, smooth shadows, 4K render, octane render, Unreal Engine 5 style, trending on ArtStation."
}
JSON
- Ultra-cinematic beverage advertising shot of a sparkling lime soda can, captured from a low three-quarter angle with the camera positioned slightly below the product for a heroic, powerful perspective; the can appears partially torn open as vivid lime wedges explode outward in slow motion, frozen mid-air with high-energy splashes of neon-green liquid and micro droplets; intense backlighting makes the citrus flesh glow translucently while sharp rim light outlines
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": "- Ultra-cinematic beverage advertising shot of a sparkling lime soda can, captured from a low three-quarter angle with the camera positioned slightly below the product for a heroic, powerful perspective; the can appears partially torn open as vivid lime wedges explode outward in slow motion, frozen mid-air with high-energy splashes of neon-green liquid and micro droplets; intense backlighting makes the citrus flesh glow translucently while sharp rim light outlines"
}
JSON
<instruction> Inputs: Ingredients = [User Choice, e.g., Chicken, Bacon] Step 1: Global Analysis Analyze the ingredients. Select 4 Distinct Countries with a famous dish using these ingredients Goal: A "Culinary Atlas" Grid showing 4 different cultural variations of the ingredients. Layout Rule: Output Format: A 2x2 Grid. Content per Panel: Each of the 4 panels must show a Single Open Book Spread for that specific country. Inside Each Panel (The Book Spread Rule): Left Page (The History): 2D Vintage Sepia Sketches. A visual timeline or illustrated recipe of the dish (e.g., "1850 -> 1920 -> Today"). Flat, ink-drawn style. Right Page (The Reality): 3D Pop-up Diorama. The finished, steaming meal emerges physically from the page. A tiny miniature chef from that country is standing on the page next to the massive food. Consistency: All 4 books should look like part of the same series, but with different cultural contents. Lighting: Cinematic top-down lighting, highlighting the depth difference between the flat left page and the 3D right page. Output: 2x2 Grid, High Definition, Macro Detail. </instruction>
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": "<instruction> Inputs: Ingredients = [User Choice, e.g., Chicken, Bacon] Step 1: Global Analysis Analyze the ingredients. Select 4 Distinct Countries with a famous dish using these ingredients Goal: A \"Culinary Atlas\" Grid showing 4 different cultural variations of the ingredients. Layout Rule: Output Format: A 2x2 Grid. Content per Panel: Each of the 4 panels must show a Single Open Book Spread for that specific country. Inside Each Panel (The Book Spread Rule): Left Page (The History): 2D Vintage Sepia Sketches. A visual timeline or illustrated recipe of the dish (e.g., \"1850 -> 1920 -> Today\"). Flat, ink-drawn style. Right Page (The Reality): 3D Pop-up Diorama. The finished, steaming meal emerges physically from the page. A tiny miniature chef from that country is standing on the page next to the massive food. Consistency: All 4 books should look like part of the same series, but with different cultural contents. Lighting: Cinematic top-down lighting, highlighting the depth difference between the flat left page and the 3D right page. Output: 2x2 Grid, High Definition, Macro Detail. </instruction>"
}
JSON
A hand-carved wooden miniature figure of [NAME], shaped with visible knife marks, natural grain texture, and smooth unfinished edges. Placed on a workshop table with carving tools, wood shavings, and soft warm directional lighting. 1080×1080.
A hyper-realistic 1080x1080 photograph of a glass cube diorama placed on a lush, mossy forest floor with dappled sunlight. Inside the cube are miniature, highly detailed landmarks and cultural icons from [COUNTRY]. Include its most famous and recognizable architecture—traditional and modern—surrounded by greenery. Prominently display the 3D word “COUNTRY” at the base inside the cube, using large, bold white block letters and a flagpole of the country's flag. The scene is crisp, elegant, and immersive, with the forest background softly blurred to focus on the diorama’s sharp details.
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 1080x1080 photograph of a glass cube diorama placed on a lush, mossy forest floor with dappled sunlight. Inside the cube are miniature, highly detailed landmarks and cultural icons from [COUNTRY]. Include its most famous and recognizable architecture—traditional and modern—surrounded by greenery. Prominently display the 3D word “COUNTRY” at the base inside the cube, using large, bold white block letters and a flagpole of the country's flag. The scene is crisp, elegant, and immersive, with the forest background softly blurred to focus on the diorama’s sharp details."
}
JSON
Create a highly detailed isometric 3D rendering of [LANDMARK] in architectural visualization style. The building is shown at a 45-degree angle from above, displaying three visible sides with intricate architectural detail. Photorealistic textures showing materials like stone, glass, metal, or brick. Include the base/ground level with tiny people, cars, and landscaping for scale. Clean white or light grey background. Professional architectural rendering with soft ambient shadows beneath the structure. Every window, column, ornamental detail, and structural element clearly visible. 1080x1080 dimension, centered composition. Style similar to video game building assets or architectural presentation models - clean, detailed, slightly stylized but realistic.
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 a highly detailed isometric 3D rendering of [LANDMARK] in architectural visualization style. The building is shown at a 45-degree angle from above, displaying three visible sides with intricate architectural detail. Photorealistic textures showing materials like stone, glass, metal, or brick. Include the base/ground level with tiny people, cars, and landscaping for scale. Clean white or light grey background. Professional architectural rendering with soft ambient shadows beneath the structure. Every window, column, ornamental detail, and structural element clearly visible. 1080x1080 dimension, centered composition. Style similar to video game building assets or architectural presentation models - clean, detailed, slightly stylized but realistic."
}
JSON
Present a clear, 45° top-down isometric miniature 3D cartoon scene of [STADIUM], with soft refined textures, realistic PBR materials, and gentle lifelike lighting. Use a clean solid [COLOR] background. At the top-center, display the name of this stadium in large bold text, then directly beneath it show its real seating capacity in medium text, and place the official logo associated with this stadium below the capacity. All text must match the background contrast automatically (white or black). Centered layout, square 1080x1080 dimension
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 scene of [STADIUM], with soft refined textures, realistic PBR materials, and gentle lifelike lighting. Use a clean solid [COLOR] background. At the top-center, display the name of this stadium in large bold text, then directly beneath it show its real seating capacity in medium text, and place the official logo associated with this stadium below the capacity. All text must match the background contrast automatically (white or black). Centered layout, square 1080x1080 dimension"
}
JSON
A hand-painted isometric bird’s-eye view illustration of [COUNTRY] in a vintage map style, featuring iconic landmarks and natural scenery unique to the country. The landscape should blend seamlessly with a parchment-colored map background, and include detailed miniature architecture, cultural symbols, and geographical elements. The country name '[COUNTRY]' should appear in bold serif text below the scene. Maintain warm, earthy tones and soft lighting for a classic, illustrated map feel. 1080x1080 dimension.
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 hand-painted isometric bird’s-eye view illustration of [COUNTRY] in a vintage map style, featuring iconic landmarks and natural scenery unique to the country. The landscape should blend seamlessly with a parchment-colored map background, and include detailed miniature architecture, cultural symbols, and geographical elements. The country name '[COUNTRY]' should appear in bold serif text below the scene. Maintain warm, earthy tones and soft lighting for a classic, illustrated map feel. 1080x1080 dimension."
}
JSON
create a A 3D, Pixar-style animated young man sits cross-legged on a pure white, isolated background. He has bright, olive-toned skin, a neatly styled bright brown haircut with a slight wave, and a well-groomed bright brown beard and mustache. His large, expressive eyes, a deep hazel-brown, are slightly upturned and gaze thoughtfully to his left, with a subtle, dreamy smile playing on his lips and his right hand resting gently on his cheek.He wears a bright, textured orange knit cardigan over a light blue t-shirt, complemented by bright wash denim jeans. His footwear consists of stylish sneakers with a navy blue, grey, and white color scheme. A bright grey, modern backpack is slung over his left shoulder, and a matching bright grey lunchbox rests beside his right leg.The lighting is soft and even, creating gentle highlights on his hair and clothing, and a subtle bright beneath him, emphasizing his rounded, stylized form. The overall mood is one of relaxed contemplation and youthful optimism..
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 a A 3D, Pixar-style animated young man sits cross-legged on a pure white, isolated background. He has bright, olive-toned skin, a neatly styled bright brown haircut with a slight wave, and a well-groomed bright brown beard and mustache. His large, expressive eyes, a deep hazel-brown, are slightly upturned and gaze thoughtfully to his left, with a subtle, dreamy smile playing on his lips and his right hand resting gently on his cheek.He wears a bright, textured orange knit cardigan over a light blue t-shirt, complemented by bright wash denim jeans. His footwear consists of stylish sneakers with a navy blue, grey, and white color scheme. A bright grey, modern backpack is slung over his left shoulder, and a matching bright grey lunchbox rests beside his right leg.The lighting is soft and even, creating gentle highlights on his hair and clothing, and a subtle bright beneath him, emphasizing his rounded, stylized form. The overall mood is one of relaxed contemplation and youthful optimism.."
}
JSON
Ultra-realistic photo featuring a young man (insert user’s photo) in perfect detail, preserving 100% of his facial features, wearing warm winter clothing suitable for the penguins’ icy habitat (thick jacket, scarf, gloves, beanie). The man is interacting naturally with penguins in their snowy and icy environment (snow, ice, rocks, frozen water reflections). Include natural and spontaneous photo poses: – sitting on a rock while touching a penguin
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": "Ultra-realistic photo featuring a young man (insert user’s photo) in perfect detail, preserving 100% of his facial features, wearing warm winter clothing suitable for the penguins’ icy habitat (thick jacket, scarf, gloves, beanie). The man is interacting naturally with penguins in their snowy and icy environment (snow, ice, rocks, frozen water reflections). Include natural and spontaneous photo poses: – sitting on a rock while touching a penguin"
}
JSON
A surreal, hyper-realistic close-up scene of a miniature [CAR] driving along a winding road that seamlessly transforms into a printed paper map of [CITY], [COUNTRY]. The road transitions naturally into the map’s printed streets, borders, and typography, with the vehicle driving directly over the map label “[CITY]”. The surrounding terrain reflects the natural landscape of [COUNTRY] — terrain texture, ground color, and environmental details match the region authentically (e.g. desert, mountains, coast, countryside). The map features crisp cartographic details, labeled roads, subtle borders, and realistic paper texture. The vehicle is highly detailed and proportionally scaled, feeling tangible and grounded within the scene. Lighting is bright and natural, directionally cast to create realistic highlights and defined shadows along the road’s curves. Shot from a slightly elevated angle with shallow depth of field, keeping the car and map sharply in focus while the background softly fades. Visual style is cinematic and ultra-realistic, blending tactile paper map textures with realistic terrain and vehicle materials. Aspect ratio 1:1, high resolution, premium editorial quality, no text overlays, no watermark
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 surreal, hyper-realistic close-up scene of a miniature [CAR] driving along a winding road that seamlessly transforms into a printed paper map of [CITY], [COUNTRY]. The road transitions naturally into the map’s printed streets, borders, and typography, with the vehicle driving directly over the map label “[CITY]”. The surrounding terrain reflects the natural landscape of [COUNTRY] — terrain texture, ground color, and environmental details match the region authentically (e.g. desert, mountains, coast, countryside). The map features crisp cartographic details, labeled roads, subtle borders, and realistic paper texture. The vehicle is highly detailed and proportionally scaled, feeling tangible and grounded within the scene. Lighting is bright and natural, directionally cast to create realistic highlights and defined shadows along the road’s curves. Shot from a slightly elevated angle with shallow depth of field, keeping the car and map sharply in focus while the background softly fades. Visual style is cinematic and ultra-realistic, blending tactile paper map textures with realistic terrain and vehicle materials. Aspect ratio 1:1, high resolution, premium editorial quality, no text overlays, no watermark"
}
JSON
Transform this image [UPLOAD YOUR IMAGE] into a 64K DSLR-quality shot resolution Ultra-hyperrealistic cinematic Create a photorealistic, beauty portrait in a vertical 4:5 frame, captured as a tight close-up to extreme close-up. The framing focuses primarily on the face - from just above the forehead to slightly below the lips — with minimal negative space. The camera is positioned mid-close to the subject (same face as the uploaded
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": "Transform this image [UPLOAD YOUR IMAGE] into a 64K DSLR-quality shot resolution Ultra-hyperrealistic cinematic Create a photorealistic, beauty portrait in a vertical 4:5 frame, captured as a tight close-up to extreme close-up. The framing focuses primarily on the face - from just above the forehead to slightly below the lips — with minimal negative space. The camera is positioned mid-close to the subject (same face as the uploaded"
}
JSON
Create an infographic image of [washing machine], combining a realistic photograph or photoreal render of the object with technical annotation overlays placed directly on top. Use black ink–style line drawings and text (technical pen / architectural sketch look) on a pure white studio background, including: •Key component labels •Internal cutaway or exploded-view outlines •Measurements, dimensions, and scale markers •Material callouts and quantities •Arrows indicating function, force, or flow (air, sound, power, pressure) •Simple schematic or sectional diagrams where relevant Place the title [PRODUCT] inside a hand-drawn technical annotation box in one corner. Style & layout rules: •The real object remains clearly visible beneath the annotations •Annotations feel sketched, technical, and architectural •Clean composition with balanced negative space •Educational, museum-exhibit / engineering-manual vibe Visual style: Minimal technical illustration aesthetic, black linework over realistic imagery, precise but slightly hand-drawn feel. Color palette: White background, black annotation lines and text only. No colors. Output: 1080×1080, ultra-crisp, social-feed optimized, no watermark.
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 infographic image of [washing machine], combining a realistic photograph or photoreal render of the object with technical annotation overlays placed directly on top. Use black ink–style line drawings and text (technical pen / architectural sketch look) on a pure white studio background, including: •Key component labels •Internal cutaway or exploded-view outlines •Measurements, dimensions, and scale markers •Material callouts and quantities •Arrows indicating function, force, or flow (air, sound, power, pressure) •Simple schematic or sectional diagrams where relevant Place the title [PRODUCT] inside a hand-drawn technical annotation box in one corner. Style & layout rules: •The real object remains clearly visible beneath the annotations •Annotations feel sketched, technical, and architectural •Clean composition with balanced negative space •Educational, museum-exhibit / engineering-manual vibe Visual style: Minimal technical illustration aesthetic, black linework over realistic imagery, precise but slightly hand-drawn feel. Color palette: White background, black annotation lines and text only. No colors. Output: 1080×1080, ultra-crisp, social-feed optimized, no watermark."
}
JSON
A hyper-realistic, high-speed commercial photograph featuring a man with uploaded face as reference in a chef's jacket, apron, and checkered trousers. He stands in a rustic, high-end kitchen, lifting the lid off a large, steaming copper pot with a look of pure amazement. From the pot, a literal galaxy of gourmet food explodes upwards and outwards in suspended animation: whole roasted spices, vibrant vegetables, splashes of rich sauces, floating plates of intricately plated fine dining dishes,and swirling clouds of aromatic steam filled with golden glitter. The ingredients form spiral nebulae around him. The background is a warm, blurred professional kitchen with copper cookware hanging. The lighting is warm, cinematic, and focused, highlighting the textures of the flying food with macro-level detail. Shot with a fast shutter speed to freeze motion, 8k resolution, Octane Render culinary aesthetic. 100% use my real face.
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, high-speed commercial photograph featuring a man with uploaded face as reference in a chef's jacket, apron, and checkered trousers. He stands in a rustic, high-end kitchen, lifting the lid off a large, steaming copper pot with a look of pure amazement. From the pot, a literal galaxy of gourmet food explodes upwards and outwards in suspended animation: whole roasted spices, vibrant vegetables, splashes of rich sauces, floating plates of intricately plated fine dining dishes,and swirling clouds of aromatic steam filled with golden glitter. The ingredients form spiral nebulae around him. The background is a warm, blurred professional kitchen with copper cookware hanging. The lighting is warm, cinematic, and focused, highlighting the textures of the flying food with macro-level detail. Shot with a fast shutter speed to freeze motion, 8k resolution, Octane Render culinary aesthetic. 100% use my real face."
}
JSON
A futuristic cyber-aesthetic portrait of a young woman wearing glowing neon-yellow glasses, with luminous mathematical equations projected across her face and jacket. Soft bokeh blue lights in the background create a high-tech atmosphereHyper-realistic detail, sharp eyes, smooth skin, and vivid color contrast. Sci-fi digital-glow style, immersive and modern." Her expression is calm and focused. The lighting is vibrant and cinematic, with reflections on the glasses and warm yellow highlights on her clothing.
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 futuristic cyber-aesthetic portrait of a young woman wearing glowing neon-yellow glasses, with luminous mathematical equations projected across her face and jacket. Soft bokeh blue lights in the background create a high-tech atmosphereHyper-realistic detail, sharp eyes, smooth skin, and vivid color contrast. Sci-fi digital-glow style, immersive and modern.\" Her expression is calm and focused. The lighting is vibrant and cinematic, with reflections on the glasses and warm yellow highlights on her clothing."
}
JSON
A cinematic epic sci-fi fantasy movie poster featuring three powerful tech leaders standing together as rival kings of artificial intelligence, dramatic futuristic battlefield, dark stormy sky, glowing AI energy, towering digital fortress in the background, armies of advanced robots below, intense blue and golden lighting contrast, ultra-detailed armor-inspired futuristic outfits, heroic serious expressions, high-budget streaming series poster style, dramatic composition, sharp facial details, atmospheric smoke, lightning, sparks, cinematic depth, professional poster typography with the title “THE FINAL AI BATTLE”, subtitle “The future is intelligent. The battle is real.”, 4:3 aspect ratio
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 cinematic epic sci-fi fantasy movie poster featuring three powerful tech leaders standing together as rival kings of artificial intelligence, dramatic futuristic battlefield, dark stormy sky, glowing AI energy, towering digital fortress in the background, armies of advanced robots below, intense blue and golden lighting contrast, ultra-detailed armor-inspired futuristic outfits, heroic serious expressions, high-budget streaming series poster style, dramatic composition, sharp facial details, atmospheric smoke, lightning, sparks, cinematic depth, professional poster typography with the title “THE FINAL AI BATTLE”, subtitle “The future is intelligent. The battle is real.”, 4:3 aspect ratio"
}
JSON
A luxury high-fashion magazine cover. Magazine name at the very top in massive elegant serif font reads "LUMIÈRE" — the letters are large, slightly transparent/ghost-style overlapping the model's head just like ELLE magazine, in soft platinum silver color blending into the background. Character: A young beautiful white woman, early 20s, soft feminine features, big blue eyes, naturally full lips, flawless porcelain skin, subtle makeup — rosy cheeks, nude lips, defined brows. Her hair is platinum blonde, long and wavy, loosely flowing over one shoulder. She looks directly into the camera with a soft yet powerful gaze. Slight tilt of the head, naturally elegant posture. Outfit: She is wearing a dramatic deep burgundy wine-red ballgown — structured corset top with off-shoulder neckline, voluminous layered satin skirt billowing around her dramatically. Behind her shoulders, large sculptural fabric rises like rose petals — same architectural drama as reference. She leans slightly forward, both hands resting gently on her knees. Background: Pure soft warm white/ivory background — completely clean, minimal, high-end studio editorial. Soft diffused light, no harsh shadows. Typography — placed EXACTLY like ELLE magazine reference: Top: "LUMIÈRE" massive serif, platinum/silver, overlapping model's head slightly Left mid: "GRACE & POWER" bold serif, then smaller below "THE NEW VISION OF LUXURY" Right mid: "TIMELESS & FEARLESS" bold, then "PURE OPULENCE" smaller below Bottom right large: "ICONIC & UNSTOPPABLE" elegant large serif All text in deep charcoal/dark navy. Font style: classic high fashion serif — same weight, spacing, and elegance as ELLE. Text naturally integrated into the composition, NOT floating randomly. Ultra photorealistic, 8K, real magazine cover quality, perfect typography placement, vertical 9:13 format.
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 luxury high-fashion magazine cover. Magazine name at the very top in massive elegant serif font reads \"LUMIÈRE\" — the letters are large, slightly transparent/ghost-style overlapping the model's head just like ELLE magazine, in soft platinum silver color blending into the background. Character: A young beautiful white woman, early 20s, soft feminine features, big blue eyes, naturally full lips, flawless porcelain skin, subtle makeup — rosy cheeks, nude lips, defined brows. Her hair is platinum blonde, long and wavy, loosely flowing over one shoulder. She looks directly into the camera with a soft yet powerful gaze. Slight tilt of the head, naturally elegant posture. Outfit: She is wearing a dramatic deep burgundy wine-red ballgown — structured corset top with off-shoulder neckline, voluminous layered satin skirt billowing around her dramatically. Behind her shoulders, large sculptural fabric rises like rose petals — same architectural drama as reference. She leans slightly forward, both hands resting gently on her knees. Background: Pure soft warm white/ivory background — completely clean, minimal, high-end studio editorial. Soft diffused light, no harsh shadows. Typography — placed EXACTLY like ELLE magazine reference: Top: \"LUMIÈRE\" massive serif, platinum/silver, overlapping model's head slightly Left mid: \"GRACE & POWER\" bold serif, then smaller below \"THE NEW VISION OF LUXURY\" Right mid: \"TIMELESS & FEARLESS\" bold, then \"PURE OPULENCE\" smaller below Bottom right large: \"ICONIC & UNSTOPPABLE\" elegant large serif All text in deep charcoal/dark navy. Font style: classic high fashion serif — same weight, spacing, and elegance as ELLE. Text naturally integrated into the composition, NOT floating randomly. Ultra photorealistic, 8K, real magazine cover quality, perfect typography placement, vertical 9:13 format."
}
JSON
Soft poetic children's book illustration with watercolor and gouache textures.Clear gentle daylight with slightly brighter highlights.Muted pastel colors with soft blue and warm tones.Visible brush strokes and paper grain.Minimalist composition with large negative space.Calm, thoughtful, slightly open-ended atmosphere. Child character (around 12 years old).Subtle visual metaphors like light, shadow, perspective, reflection.Hand-painted picture book style, not cartoon, not anime, not 3D. Two children in calm conversation,soft connection forming.
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": "Soft poetic children's book illustration with watercolor and gouache textures.Clear gentle daylight with slightly brighter highlights.Muted pastel colors with soft blue and warm tones.Visible brush strokes and paper grain.Minimalist composition with large negative space.Calm, thoughtful, slightly open-ended atmosphere. Child character (around 12 years old).Subtle visual metaphors like light, shadow, perspective, reflection.Hand-painted picture book style, not cartoon, not anime, not 3D. Two children in calm conversation,soft connection forming."
}
JSON
FAQ
Using gpt-image-2 prompts
What is %{model}?
%{model} is available through RunAPI as part of the unified model catalog. These prompts show practical input patterns that agents and backend services can reuse.
How do I use these prompts?
Copy any prompt and paste it into Claude Code, Codex, Cursor, or Windsurf after installing the RunAPI MCP Server. Developers can also copy the API example and send the prompt directly.
Do these prompts cost money to browse?
Browsing and copying prompt examples is free. Generation requests only cost money when you call a RunAPI model with your API key.
Can I adapt the prompts for production?
Yes. Treat each prompt as a starting point, then add your brand rules, output dimensions, safety constraints, and application-specific context before using it in production.