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.
editorial portrait, Korean female idol, subtly sensual outfit: silk shirt or soft fabric top, slightly loose, elegant and flowing pose: body slightly turned away, face partially visible, one hand near collar or neck expression: soft but unreadable, eyes partially hidden lighting: strong directional light (window light), casting shadows across face and body background: dark or minimal interior composition: partial visibility, half-lit face, shadow covering features mood: mysterious, intimate, quiet tension style: cinematic editorial, light and shadow storytelling sensuality: created through concealment and ambiguity --3:2
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": "editorial portrait, Korean female idol, subtly sensual outfit: silk shirt or soft fabric top, slightly loose, elegant and flowing pose: body slightly turned away, face partially visible, one hand near collar or neck expression: soft but unreadable, eyes partially hidden lighting: strong directional light (window light), casting shadows across face and body background: dark or minimal interior composition: partial visibility, half-lit face, shadow covering features mood: mysterious, intimate, quiet tension style: cinematic editorial, light and shadow storytelling sensuality: created through concealment and ambiguity --3:2"
}
JSON
ultra-realistic IMAX-grade cinematic action shot, extreme high-angle perspective looking down from a massive height, 9:16 vertical aspect ratio, a man or woman matching the exact reference face and hairstyle climbing the side of a modern glass skyscraper, body stretched dynamically across the reflective facade, positioned on the right side of the frame, one leg raised gripping the glass while the other is bent for support, both palms pressed tightly against the glass surface creating tension and realism, wearing futuristic clear-framed glasses with subtle reflections, outfit: premium black fitted t-shirt, black tactical pants, futuristic black gloves with protective padding and bright green LED accents glowing softly, black tactical climbing boots with gold detailing and strong grip texture, a sleek black vest or harness securely fitted over the torso adding realism and safety gear detail, expression: determined and slightly tense with focused eyes and head slightly tilted forward, face lock: maintain exact facial structure, proportions, skin tone, hairstyle, and identity from reference with 100% accuracy, preserve micro-details and natural imperfections, no beautification, facial rendering: soft natural skin with visible pores, smooth tonal transitions, subtle subsurface scattering, no smoothing or artificial glow, environment: towering skyscraper with ultra-reflective glass panels showing the subject’s shadow, sky reflections, and a detailed cityscape far below including intricate walkways, a lush green circular park, and distant street traffic with tiny moving cars, strong sense of depth and scale, lighting: bright natural daylight casting sharp directional shadows, high contrast reflections on glass surface, crisp highlights with controlled roll-off, color science: ultra-clean cinematic color grading with high color separation, natural saturation, deep contrast, HDR dynamic range preserving both sky and ground detail, lens: full-frame Sony A7R, 24mm wide-angle lens to exaggerate height and perspective, sharp foreground subject with slight depth falloff into the city below, realism: extreme photorealistic detail, realistic reflections, natural perspective distortion, micro-contrast textures, no HDR overprocessing, no artificial sharpening negative prompt: distorted face, changed identity, altered hairstyle, flat lighting, dull colors, unrealistic reflections, floating pose, weak grip, plastic skin, over-smooth face, beauty filter effect, low detail, noise artifacts, color banding, extra limbs, incorrect anatomy, blurry subject
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 IMAX-grade cinematic action shot, extreme high-angle perspective looking down from a massive height, 9:16 vertical aspect ratio, a man or woman matching the exact reference face and hairstyle climbing the side of a modern glass skyscraper, body stretched dynamically across the reflective facade, positioned on the right side of the frame, one leg raised gripping the glass while the other is bent for support, both palms pressed tightly against the glass surface creating tension and realism, wearing futuristic clear-framed glasses with subtle reflections, outfit: premium black fitted t-shirt, black tactical pants, futuristic black gloves with protective padding and bright green LED accents glowing softly, black tactical climbing boots with gold detailing and strong grip texture, a sleek black vest or harness securely fitted over the torso adding realism and safety gear detail, expression: determined and slightly tense with focused eyes and head slightly tilted forward, face lock: maintain exact facial structure, proportions, skin tone, hairstyle, and identity from reference with 100% accuracy, preserve micro-details and natural imperfections, no beautification, facial rendering: soft natural skin with visible pores, smooth tonal transitions, subtle subsurface scattering, no smoothing or artificial glow, environment: towering skyscraper with ultra-reflective glass panels showing the subject’s shadow, sky reflections, and a detailed cityscape far below including intricate walkways, a lush green circular park, and distant street traffic with tiny moving cars, strong sense of depth and scale, lighting: bright natural daylight casting sharp directional shadows, high contrast reflections on glass surface, crisp highlights with controlled roll-off, color science: ultra-clean cinematic color grading with high color separation, natural saturation, deep contrast, HDR dynamic range preserving both sky and ground detail, lens: full-frame Sony A7R, 24mm wide-angle lens to exaggerate height and perspective, sharp foreground subject with slight depth falloff into the city below, realism: extreme photorealistic detail, realistic reflections, natural perspective distortion, micro-contrast textures, no HDR overprocessing, no artificial sharpening negative prompt: distorted face, changed identity, altered hairstyle, flat lighting, dull colors, unrealistic reflections, floating pose, weak grip, plastic skin, over-smooth face, beauty filter effect, low detail, noise artifacts, color banding, extra limbs, incorrect anatomy, blurry subject"
}
JSON
Create a dark, high‑contrast poster with a moody, underground club aesthetic. The composition features a monochrome portrait of a young woman from the chest up, shot from a slightly low angle for attitude and power. She wears large over‑ear headphones and reflective round sunglasses with warm amber‑gold lenses that stand out vividly against the black‑and‑white portrait. One hand is raised near her head, the other near her chin, creating a dynamic, expressive pose associated with music immersion. Behind her head is a large flat golden‑yellow circular shape, like a spotlight, creating a strong focal point and visual contrast. The background is deep black with subtle grunge textures, dust, scratches, and poster‑wear imperfections, giving it a raw, printed‑flyer feel. Use 4:5 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": "Create a dark, high‑contrast poster with a moody, underground club aesthetic. The composition features a monochrome portrait of a young woman from the chest up, shot from a slightly low angle for attitude and power. She wears large over‑ear headphones and reflective round sunglasses with warm amber‑gold lenses that stand out vividly against the black‑and‑white portrait. One hand is raised near her head, the other near her chin, creating a dynamic, expressive pose associated with music immersion. Behind her head is a large flat golden‑yellow circular shape, like a spotlight, creating a strong focal point and visual contrast. The background is deep black with subtle grunge textures, dust, scratches, and poster‑wear imperfections, giving it a raw, printed‑flyer feel. Use 4:5 aspect ratio."
}
JSON
A 3x3 grid storyboard contact sheet comprised of nine candid, cinematic movie stills showing a continuous sequence of a young man, approximately 20-25 years old. He has tousled brown hair and a youthful, expressive face, clean-shaven. Across all nine panels, he is consistently wearing a brown short-sleeved linen button-down shirt and is seated at a wooden dining table during a family dinner. The panels show varied natural actions: gesturing with his hands while animatedly talking, laughing, eating lasagna from a large dish, listening intently, and smiling. The environment is a warm, cozy home dining room with a wooden hutch filled with china and patterned wallpaper visible in the background. The lighting is soft, warm tungsten evening light creating natural shadows. The shots are a mix of medium angles and close-ups with a shallow depth of field, rendered with a film photography aesthetic and slight grain.
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 3x3 grid storyboard contact sheet comprised of nine candid, cinematic movie stills showing a continuous sequence of a young man, approximately 20-25 years old. He has tousled brown hair and a youthful, expressive face, clean-shaven. Across all nine panels, he is consistently wearing a brown short-sleeved linen button-down shirt and is seated at a wooden dining table during a family dinner. The panels show varied natural actions: gesturing with his hands while animatedly talking, laughing, eating lasagna from a large dish, listening intently, and smiling. The environment is a warm, cozy home dining room with a wooden hutch filled with china and patterned wallpaper visible in the background. The lighting is soft, warm tungsten evening light creating natural shadows. The shots are a mix of medium angles and close-ups with a shallow depth of field, rendered with a film photography aesthetic and slight grain."
}
JSON
A highly detailed digital artwork in a surreal, dynamic style inspired by premium athletic advertising for Nike, Inc. A young athletic woman with platinum blonde hair tied in a messy bun, fair skin, and a fiercely focused expression is captured mid-jump or leap, her body leaning slightly forward as if bursting with raw, untamed energy. She wears a loose, off-white Nike crewneck sweatshirt with subtle embossed Nike branding on the chest, paired with flowy, semi-transparent pants featuring a swirling marbled pattern in graphite grey and electric violet, billowing dramatically around her legs. On her feet are sleek, futuristic white Nike sneakers with glowing violet accents, visible Air-inspired sole details, and an aerodynamic design. Vibrant electric violet energy or ethereal smoke erupts dramatically from behind her, swirling and dissolving into abstract, cloud-like forms that interact with her clothing, creating a powerful sense of motion and release. The background is a deep, moody gradient transitioning from charcoal grey to luminous twilight violet, emphasizing a minimalist yet striking composition. Overlay large, bold metallic silver text reading “Just Do It” in a sharp, modern sans-serif font, partially integrated and obscured by the energy smoke and the figure, making it feel like an organic part of the scene. Include the iconic Nike Swoosh logo in the top-left corner in shimmering silver.
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 highly detailed digital artwork in a surreal, dynamic style inspired by premium athletic advertising for Nike, Inc. A young athletic woman with platinum blonde hair tied in a messy bun, fair skin, and a fiercely focused expression is captured mid-jump or leap, her body leaning slightly forward as if bursting with raw, untamed energy. She wears a loose, off-white Nike crewneck sweatshirt with subtle embossed Nike branding on the chest, paired with flowy, semi-transparent pants featuring a swirling marbled pattern in graphite grey and electric violet, billowing dramatically around her legs. On her feet are sleek, futuristic white Nike sneakers with glowing violet accents, visible Air-inspired sole details, and an aerodynamic design. Vibrant electric violet energy or ethereal smoke erupts dramatically from behind her, swirling and dissolving into abstract, cloud-like forms that interact with her clothing, creating a powerful sense of motion and release. The background is a deep, moody gradient transitioning from charcoal grey to luminous twilight violet, emphasizing a minimalist yet striking composition. Overlay large, bold metallic silver text reading “Just Do It” in a sharp, modern sans-serif font, partially integrated and obscured by the energy smoke and the figure, making it feel like an organic part of the scene. Include the iconic Nike Swoosh logo in the top-left corner in shimmering silver."
}
JSON
A vibrant 2000s scrapbook-style collage featuring the same young woman in multiple cutout poses. One portrait is centered and large, showing her wearing round glasses and a beige hoodie, making a finger-heart gesture toward the camera. Other cutouts show her squatting with a vintage instant camera, and another blowing a pink bubblegum bubble. The background looks like an open sketchbook with textured paper, filled with colorful paint strokes in rainbow tones, playful doodles, arrows, stars, hearts, butterflies, smiley faces, and pop-art stickers. Bold, bubbly typography stickers read phrases like “2000s Vibes,” “Dream Big,” “Be Yourself,” “Cool Dude,” “Say Cheese,” and “Pop!” The overall aesthetic is nostalgic, cheerful, and youthful — inspired by early 2000s teen magazines and scrapbook journals. High saturation, soft lighting, clean white sticker outlines around each cutout, whimsical and fun mood, creative flat-lay composition, digital collage illustration style.
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 vibrant 2000s scrapbook-style collage featuring the same young woman in multiple cutout poses. One portrait is centered and large, showing her wearing round glasses and a beige hoodie, making a finger-heart gesture toward the camera. Other cutouts show her squatting with a vintage instant camera, and another blowing a pink bubblegum bubble. The background looks like an open sketchbook with textured paper, filled with colorful paint strokes in rainbow tones, playful doodles, arrows, stars, hearts, butterflies, smiley faces, and pop-art stickers. Bold, bubbly typography stickers read phrases like “2000s Vibes,” “Dream Big,” “Be Yourself,” “Cool Dude,” “Say Cheese,” and “Pop!” The overall aesthetic is nostalgic, cheerful, and youthful — inspired by early 2000s teen magazines and scrapbook journals. High saturation, soft lighting, clean white sticker outlines around each cutout, whimsical and fun mood, creative flat-lay composition, digital collage illustration style."
}
JSON
Ultra-clean modern editorial infographic. The topic is [ROUTINE] routine. Base all visuals, colors, objects, mood, ingredients, and steps entirely on this topic. Hero visual: a stylized flat-lay or floating arrangement of 3–4 iconic objects associated with this topic — slightly angled or in soft perspective, glowing subtly. All elements arranged dynamically around the hero in a non-restrictive editorial layout. Ingredients Section: Label it ‘What You Need’ — include 6–8 relevant items with small icons or emoji illustrations next to each, with a practical quantity or duration written like a recipe. Steps Section: 5–6 numbered panels with arrows or connecting lines forming a logical flow, each with a short action label and small relevant icon, using glassmorphism or frosted card styling. Stats Badges: 4–5 floating pill-shaped badges showing relevant metadata, displayed as clean minimal bubbles near the hero. Visual Style: Choose background color, accent colors, typography weight, and texture to naturally match the topic’s mood. Bold modern sans-serif typography. Clean vector icons. Subtle grain or texture. Composition: Hero centered or slightly offset, ingredients one side, steps opposite or below with connecting lines, stat badges as floating pills, generous negative space. Lighting: Soft natural studio lighting matching the topic’s tone. Premium editorial aesthetic, social-feed optimized. Ultra-crisp. 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": "Ultra-clean modern editorial infographic. The topic is [ROUTINE] routine. Base all visuals, colors, objects, mood, ingredients, and steps entirely on this topic. Hero visual: a stylized flat-lay or floating arrangement of 3–4 iconic objects associated with this topic — slightly angled or in soft perspective, glowing subtly. All elements arranged dynamically around the hero in a non-restrictive editorial layout. Ingredients Section: Label it ‘What You Need’ — include 6–8 relevant items with small icons or emoji illustrations next to each, with a practical quantity or duration written like a recipe. Steps Section: 5–6 numbered panels with arrows or connecting lines forming a logical flow, each with a short action label and small relevant icon, using glassmorphism or frosted card styling. Stats Badges: 4–5 floating pill-shaped badges showing relevant metadata, displayed as clean minimal bubbles near the hero. Visual Style: Choose background color, accent colors, typography weight, and texture to naturally match the topic’s mood. Bold modern sans-serif typography. Clean vector icons. Subtle grain or texture. Composition: Hero centered or slightly offset, ingredients one side, steps opposite or below with connecting lines, stat badges as floating pills, generous negative space. Lighting: Soft natural studio lighting matching the topic’s tone. Premium editorial aesthetic, social-feed optimized. Ultra-crisp. No watermark"
}
JSON
Create a 4:5 vertical social poster in ultra high resolution, 8K print quality sharpness. Use the BMW car from the reference image as the main subject and use the background structure/composition from the reference image, but transform it into a BMW themed design. Replace all black tones with a flat high-saturation BMW blue background. Keep the same layout, spacing, visual balance, and poster composition from the reference image. Background should use a smooth gradient from slightly lighter electric blue at the top to deep navy blue at the bottom. Add subtle grain texture (2 to 3%) and faint rectangular overlays (2 to 4% opacity). Keep it clean, graphic, premium, and non-realistic. Add a soft contact shadow under the car. Use the same BMW from the reference image, changing only the paint color to matte frozen blue or deep metallic navy. Keep the original body shape, wheels, stance, and design details from the reference image. Show the car in a rear 3/4 perspective matching the reference image angle exactly. Use a slightly elevated camera angle. Position the car slightly right of center. Include visible carbon roof, aggressive rear diffuser, sharp controlled reflections, and subtle brake details. Keep composition identical to the reference image: Top: branding Middle: giant type Center: car overlapping text Bottom: editorial block and specs Typography: Primary text: “BMW” Ultra condensed bold sans serif, tall vertical scaling like the reference poster. Color deep navy or near black. Static text with no distortion. Acts as structural backdrop. Secondary header: “BMW M4 G82” Thin font with wide tracking. Logo area: BMW roundel centered above. Editorial block: Headline: “BMW — Where Driving Becomes Instinct” Body copy focused on: driver connection control performance precision Use the same boxed editorial layout as the reference image. Background faded text: “M4” large scale with 3 to 5% opacity behind the box. Bottom left: “ M4 G82” Bottom right specs: 405 kW / 550 PS 3.4 s 307 km/h Lighting should be clean studio lighting with sharp but controlled highlights. Color grading should use deep blues, high contrast, clean blacks. Camera lens: 50mm, slightly elevated rear 3/4 angle. Mood: Performance. Precision. Driver focus. Add Bottom-right watermark: harboriis , with small x and Instagram logo
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 4:5 vertical social poster in ultra high resolution, 8K print quality sharpness. Use the BMW car from the reference image as the main subject and use the background structure/composition from the reference image, but transform it into a BMW themed design. Replace all black tones with a flat high-saturation BMW blue background. Keep the same layout, spacing, visual balance, and poster composition from the reference image. Background should use a smooth gradient from slightly lighter electric blue at the top to deep navy blue at the bottom. Add subtle grain texture (2 to 3%) and faint rectangular overlays (2 to 4% opacity). Keep it clean, graphic, premium, and non-realistic. Add a soft contact shadow under the car. Use the same BMW from the reference image, changing only the paint color to matte frozen blue or deep metallic navy. Keep the original body shape, wheels, stance, and design details from the reference image. Show the car in a rear 3/4 perspective matching the reference image angle exactly. Use a slightly elevated camera angle. Position the car slightly right of center. Include visible carbon roof, aggressive rear diffuser, sharp controlled reflections, and subtle brake details. Keep composition identical to the reference image: Top: branding Middle: giant type Center: car overlapping text Bottom: editorial block and specs Typography: Primary text: “BMW” Ultra condensed bold sans serif, tall vertical scaling like the reference poster. Color deep navy or near black. Static text with no distortion. Acts as structural backdrop. Secondary header: “BMW M4 G82” Thin font with wide tracking. Logo area: BMW roundel centered above. Editorial block: Headline: “BMW — Where Driving Becomes Instinct” Body copy focused on: driver connection control performance precision Use the same boxed editorial layout as the reference image. Background faded text: “M4” large scale with 3 to 5% opacity behind the box. Bottom left: “ M4 G82” Bottom right specs: 405 kW / 550 PS 3.4 s 307 km/h Lighting should be clean studio lighting with sharp but controlled highlights. Color grading should use deep blues, high contrast, clean blacks. Camera lens: 50mm, slightly elevated rear 3/4 angle. Mood: Performance. Precision. Driver focus. Add Bottom-right watermark: harboriis , with small x and Instagram logo"
}
JSON
Make a portrait-sized wallpaper about several activities from the hobby of (Name Hobby), in the wallpaper it contains various movements in the hobby activity, make the wallpaper design as if it was designed by a professional graphic designer, the coloring and UI of the wallpaper are colorful and don't look commonplace, don't be monotonous, and don't look stiff from the visual of the wallpaper, arranged neatly and precisely, 8k resolution
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 portrait-sized wallpaper about several activities from the hobby of (Name Hobby), in the wallpaper it contains various movements in the hobby activity, make the wallpaper design as if it was designed by a professional graphic designer, the coloring and UI of the wallpaper are colorful and don't look commonplace, don't be monotonous, and don't look stiff from the visual of the wallpaper, arranged neatly and precisely, 8k resolution"
}
JSON
Create a highly detailed, hyper-realistic image of a miniature diorama inside a glass dome, placed on a wooden table near a softly lit window. Inside the dome, show a [COUNTRY] cultural figure with iconic attire, prominently positioned in the center foreground taking up significant space in the composition to really “pop” from the scene, smiling and waving, in a stylized 3D miniature version of [COUNTRY]’s iconic setting. Include the most iconic background features of that location, all scaled in a whimsical, miniature style. The time of day, season, and mood will vary by [COUNTRY]’s cultural theme. The scene is captured from a slightly elevated perspective. The base of the dome has a wooden plaque with bold, gold-colored text labeled: ‘[COUNTRY]’ in a strong, readable font that stands out prominently. The scene should be bright, magical, joyful, and feel like a collectible souvenir moment from a dream trip. Aspect ratio: 1080x1080
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, hyper-realistic image of a miniature diorama inside a glass dome, placed on a wooden table near a softly lit window. Inside the dome, show a [COUNTRY] cultural figure with iconic attire, prominently positioned in the center foreground taking up significant space in the composition to really “pop” from the scene, smiling and waving, in a stylized 3D miniature version of [COUNTRY]’s iconic setting. Include the most iconic background features of that location, all scaled in a whimsical, miniature style. The time of day, season, and mood will vary by [COUNTRY]’s cultural theme. The scene is captured from a slightly elevated perspective. The base of the dome has a wooden plaque with bold, gold-colored text labeled: ‘[COUNTRY]’ in a strong, readable font that stands out prominently. The scene should be bright, magical, joyful, and feel like a collectible souvenir moment from a dream trip. Aspect ratio: 1080x1080"
}
JSON
Ultra-modern high-end skincare advertising collage featuring four beautiful young Asian women, each portrait styled in a separate geometric section of a dynamic diagonal layout. Clean editorial beauty photography with soft natural skin texture, glowing healthy complexion, and subtle makeup. Bright vibrant color blocking design using pink, yellow, cyan, and coral tones. Minimal abstract background shapes, smooth gradients, and modern graphic design composition. Studio-quality lighting, fashion magazine aesthetic, premium cosmetic campaign feel. Each woman posed confidently in different angles, smiling softly, fresh and youthful vibe. Balanced symmetry with sharp diagonal divisions and circular portrait frames. Highly polished commercial beauty branding style, cinematic lighting, ultra-detailed, 4k resolution. IMPORTANT NEGATIVE PROMPT: No text, no typography, no logos, no brand names, no product bottles, no packaging, no watermark, no labels, no written elements.
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-modern high-end skincare advertising collage featuring four beautiful young Asian women, each portrait styled in a separate geometric section of a dynamic diagonal layout. Clean editorial beauty photography with soft natural skin texture, glowing healthy complexion, and subtle makeup. Bright vibrant color blocking design using pink, yellow, cyan, and coral tones. Minimal abstract background shapes, smooth gradients, and modern graphic design composition. Studio-quality lighting, fashion magazine aesthetic, premium cosmetic campaign feel. Each woman posed confidently in different angles, smiling softly, fresh and youthful vibe. Balanced symmetry with sharp diagonal divisions and circular portrait frames. Highly polished commercial beauty branding style, cinematic lighting, ultra-detailed, 4k resolution. IMPORTANT NEGATIVE PROMPT: No text, no typography, no logos, no brand names, no product bottles, no packaging, no watermark, no labels, no written elements."
}
JSON
Eye-level straight-on view, looking directly into a hyper-vibrant 3D layered paper cut-out diorama. Pokéball red and white, Pikachu yellow, sky blue and grass green accents, extremely high saturation, PHYSICAL PAPER LAYERS clearly visible with hard cut edges and thick paper cross-sections at every depth plane. Maximalist composition, crowded Pokémon world scene — layered Pokémon Center and gym architecture receding through all depth planes, Pikachu as central figure mid-thunderbolt on foreground layer, dozens of iconic Pokémon — Charizard, Gengar, Eevee, Snorlax, Mewtwo — each inhabiting separate depth planes, trainer Ash and rivals threading between battle layers, Pokéball burst effects frozen mid-release across all planes, tall grass and route pathways between habitat layers, legendary Pokémon silhouettes in remote background layers, scattered Pokéballs, badges and berry items crowding the vibrant foreground. Soft single-direction studio lighting creating deep drop shadows between every physical paper layer, matte paper texture throughout, NO glow, NO soft edges, NO volumetric lighting, octane render, 8k, clean details --ar 3:4
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": "Eye-level straight-on view, looking directly into a hyper-vibrant 3D layered paper cut-out diorama. Pokéball red and white, Pikachu yellow, sky blue and grass green accents, extremely high saturation, PHYSICAL PAPER LAYERS clearly visible with hard cut edges and thick paper cross-sections at every depth plane. Maximalist composition, crowded Pokémon world scene — layered Pokémon Center and gym architecture receding through all depth planes, Pikachu as central figure mid-thunderbolt on foreground layer, dozens of iconic Pokémon — Charizard, Gengar, Eevee, Snorlax, Mewtwo — each inhabiting separate depth planes, trainer Ash and rivals threading between battle layers, Pokéball burst effects frozen mid-release across all planes, tall grass and route pathways between habitat layers, legendary Pokémon silhouettes in remote background layers, scattered Pokéballs, badges and berry items crowding the vibrant foreground. Soft single-direction studio lighting creating deep drop shadows between every physical paper layer, matte paper texture throughout, NO glow, NO soft edges, NO volumetric lighting, octane render, 8k, clean details --ar 3:4"
}
JSON
Create a hyper-realistic, stylish vertical poster featuring a smartphone lying on a table, transformed into a hockey rink. The screen resembles cracked ice with deep fissures, while tiny hockey players compete in an intense game Use diffused daylight with elegant reflections and refractions to enhance depth. Add realistic details like fingerprints, smudges, and subtle scratches on the phone's surface for authenticity. Craft a dynamic perspective with an intriguing camera angle-slightly tilted for dramatic effect. The image should look like a high-quality DSLR photograph, with sharp focus, rich textures, and cinematic lighting to amplify the surreal yet lifelike atmosphere
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 hyper-realistic, stylish vertical poster featuring a smartphone lying on a table, transformed into a hockey rink. The screen resembles cracked ice with deep fissures, while tiny hockey players compete in an intense game Use diffused daylight with elegant reflections and refractions to enhance depth. Add realistic details like fingerprints, smudges, and subtle scratches on the phone's surface for authenticity. Craft a dynamic perspective with an intriguing camera angle-slightly tilted for dramatic effect. The image should look like a high-quality DSLR photograph, with sharp focus, rich textures, and cinematic lighting to amplify the surreal yet lifelike atmosphere"
}
JSON
A high-quality, candid street photography shot of a stylish young woman with short wavy brown hair. She is wearing a maroon cardigan, oversized beige denim cargo pants, and a maroon baseball cap. She has large white over-ear headphones around her ears and a black quilted shoulder bag with a small plush dog keychain hanging from it.Same face as in reference
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 high-quality, candid street photography shot of a stylish young woman with short wavy brown hair. She is wearing a maroon cardigan, oversized beige denim cargo pants, and a maroon baseball cap. She has large white over-ear headphones around her ears and a black quilted shoulder bag with a small plush dog keychain hanging from it.Same face as in reference"
}
JSON
Create a character promotional poster for “[XXX]”, using a unified vertical (portrait) key visual composition. Each poster follows a hierarchy of large top / smaller bottom structure: The upper half of the composition features a highly recognizable large silhouette of the character — focusing on the head, facial contour, mask, or upper-body outline — forming a bold and iconic primary visual. The middle to lower section includes a full-body version of the character as the secondary subject, shown in a stable standing pose or with subtle motion, serving as the visual core of the composition. Inside the large silhouette and around the character, apply double exposure and collage-style storytelling, blending multiple scenes, symbolic elements, small character interactions, supporting visuals, and environments into layered compositions of mist, ink wash, and negative space. On both the left and right sides, place complementary supporting elements to create narrative tension and spatial balance. A flowing visual line should run through the entire composition (top to bottom), connecting the main character, internal collage elements, and the large silhouette above — enhancing cohesion and guiding the viewer’s eye. The overall composition should preserve large areas of negative space, with edges treated using ink diffusion, soft blurring, and fragmented fading, evoking an Eastern aesthetic of balance between emptiness and form. The overall style should feel refined, restrained, premium, and cohesive, emphasizing depth, storytelling, strong visual impact, and a consistent series identity. Aspect ratio: 9:16.
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 character promotional poster for “[XXX]”, using a unified vertical (portrait) key visual composition. Each poster follows a hierarchy of large top / smaller bottom structure: The upper half of the composition features a highly recognizable large silhouette of the character — focusing on the head, facial contour, mask, or upper-body outline — forming a bold and iconic primary visual. The middle to lower section includes a full-body version of the character as the secondary subject, shown in a stable standing pose or with subtle motion, serving as the visual core of the composition. Inside the large silhouette and around the character, apply double exposure and collage-style storytelling, blending multiple scenes, symbolic elements, small character interactions, supporting visuals, and environments into layered compositions of mist, ink wash, and negative space. On both the left and right sides, place complementary supporting elements to create narrative tension and spatial balance. A flowing visual line should run through the entire composition (top to bottom), connecting the main character, internal collage elements, and the large silhouette above — enhancing cohesion and guiding the viewer’s eye. The overall composition should preserve large areas of negative space, with edges treated using ink diffusion, soft blurring, and fragmented fading, evoking an Eastern aesthetic of balance between emptiness and form. The overall style should feel refined, restrained, premium, and cohesive, emphasizing depth, storytelling, strong visual impact, and a consistent series identity. Aspect ratio: 9:16."
}
JSON
High-impact e-commerce infographic advertisement for "Fujifilm Instax Mini 11" blush pink instant camera. FOREGROUND: Extreme close-up of a hand holding a compact rounded blush-pink Fujifilm Instax Mini 11 camera angled toward camera, razor-sharp center focus, macro-lens shallow depth of field, visible 60mm silver lens ring, crystal pop-up flash, white instax mini 11 branding on body, red shutter button accent, fingertips softly blurred at edges. CENTRAL MODEL: confident young woman with straight dark brown hair, light natural makeup, cool editorial expression, wearing a bold orange and black vertical-striped sleeveless leather mini dress with deep red buckle details and silver stud buttons, holding the blush-pink Instax Mini 11 casually at chest height with camera face pointing outward, slight off-camera gaze, stylish composed energy. BACKGROUND: soft-focus cool light gray gradient studio backdrop fading to warm white center, diagonal pastel prism lens flares in pink peach and lavender cutting upper-left to lower-right, soft blush-pink and cream light leaks at corners, 4 to 5 blurred Fujifilm Instax Mini 11 cameras floating at various depths and rotation angles, scattered polaroid-style instant photo prints in background bokeh, subtle bokeh circles from studio lights. LIGHTING: professional three-point studio lighting, key light upper-left, fill light right side, rim light behind model for separation, glossy highlights on camera lens ring and flash unit. TYPOGRAPHY overlaid clean bold white sans-serif: massive semi-transparent "INSTAX" text spanning full width behind model at top center, top right bold text "Fujifilm Instax Mini 11" with subtitle "Instant Film Camera Blush Pink", mid-left small camera icon with bold "Shoot and Print Instantly" and subtext "Credit Card Sized Photos in Seconds", mid-right extra-large bold numeral "60" with smaller text "mm Instax Lens Auto Exposure", lower-left bold "selfie" with subtext "Built-in Selfie Mirror and Close-Up Lens Mode", bottom-right bold numeral "1" with subtext "Year Warranty Included", bottom center fine print "ISO 800 Film | Auto Flash | Focus Range 0.3m to infinity | AA Battery Powered | Available in 5 Colors". TECHNICAL: 8K ultra-sharp, hyperrealistic commercial ad aesthetic, editorial fashion meets lifestyle product photography style, color palette blush pink orange black cream pastel prism accents, tack-sharp on Instax camera with shallow DOF on everything else, 85mm macro slight low angle, warm vibrant professional color grading.
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": "High-impact e-commerce infographic advertisement for \"Fujifilm Instax Mini 11\" blush pink instant camera. FOREGROUND: Extreme close-up of a hand holding a compact rounded blush-pink Fujifilm Instax Mini 11 camera angled toward camera, razor-sharp center focus, macro-lens shallow depth of field, visible 60mm silver lens ring, crystal pop-up flash, white instax mini 11 branding on body, red shutter button accent, fingertips softly blurred at edges. CENTRAL MODEL: confident young woman with straight dark brown hair, light natural makeup, cool editorial expression, wearing a bold orange and black vertical-striped sleeveless leather mini dress with deep red buckle details and silver stud buttons, holding the blush-pink Instax Mini 11 casually at chest height with camera face pointing outward, slight off-camera gaze, stylish composed energy. BACKGROUND: soft-focus cool light gray gradient studio backdrop fading to warm white center, diagonal pastel prism lens flares in pink peach and lavender cutting upper-left to lower-right, soft blush-pink and cream light leaks at corners, 4 to 5 blurred Fujifilm Instax Mini 11 cameras floating at various depths and rotation angles, scattered polaroid-style instant photo prints in background bokeh, subtle bokeh circles from studio lights. LIGHTING: professional three-point studio lighting, key light upper-left, fill light right side, rim light behind model for separation, glossy highlights on camera lens ring and flash unit. TYPOGRAPHY overlaid clean bold white sans-serif: massive semi-transparent \"INSTAX\" text spanning full width behind model at top center, top right bold text \"Fujifilm Instax Mini 11\" with subtitle \"Instant Film Camera Blush Pink\", mid-left small camera icon with bold \"Shoot and Print Instantly\" and subtext \"Credit Card Sized Photos in Seconds\", mid-right extra-large bold numeral \"60\" with smaller text \"mm Instax Lens Auto Exposure\", lower-left bold \"selfie\" with subtext \"Built-in Selfie Mirror and Close-Up Lens Mode\", bottom-right bold numeral \"1\" with subtext \"Year Warranty Included\", bottom center fine print \"ISO 800 Film | Auto Flash | Focus Range 0.3m to infinity | AA Battery Powered | Available in 5 Colors\". TECHNICAL: 8K ultra-sharp, hyperrealistic commercial ad aesthetic, editorial fashion meets lifestyle product photography style, color palette blush pink orange black cream pastel prism accents, tack-sharp on Instax camera with shallow DOF on everything else, 85mm macro slight low angle, warm vibrant professional color grading."
}
JSON
Cinematic product poster for WELLBI, India's premium bamboo apparel brand. SCENE: A lone young Indian man emerges from a dense, luminous bamboo forest at golden hour. Wears a perfectly draped, ultra-clean ivory WELLBI bamboo polo. Bamboo stalks alive with warm amber and jade light filtering through canopy. VISUAL STORYTELLING: The bamboo forest IS the fabric — seamless living metaphor. Thin golden light rays land on the polo, suggesting softness and breathability. COMPOSITION: Low angle, subject centre-frame, bamboo framing both sides like a natural arch. Horizon at lower third. Cinematic 2.39:1 anamorphic crop. — TYPOGRAPHY SYSTEM — Hero line: "GROWN." — single word, massive scale, Helvetica Neue Ultra Light, all caps, extreme letter-spacing +600, ghost white at 15% opacity overlaid across the ENTIRE poster width — architectural, not decorative. Sub-line: "Not manufactured." — set in sharp Aktiv Grotesk Regular, sentence case, 18pt, tracking +80, positioned directly below hero word. White. Full opacity. Feels like a whisper after a shout. Brand name: "WELLBI" — bottom right corner. Neutral Grotesk Medium, all caps, tracking +300, 11pt. Separated by a 0.5pt hairline rule above it, 40px wide. Restrained. Premium. Legal/descriptor: "100% Bamboo Apparel — India" — micro text, 7pt, tracking +150, bottom left. Rotated 90° vertical. Acts as a structural edge element, not an afterthought. COLOUR PALETTE: Deep jungle green, warm amber, ivory white, earth brown. LIGHTING: ARRI Alexa Mini LF — golden hour rim, diffused fill, subtle lens flare grazing the polo fabric. MOOD: Grounded luxury. Like a Loro Piana campaign shot in Assam. CAMERA: 85mm f/1.4, shallow DOF, anamorphic lens flare. Editorial brand poster for WELLBI sustainable Indian fashion. SCENE: Extreme close-up of a weathered artisan's hands spinning bamboo thread. Blurred WELLBI tee draped elegantly in background. Warm-lit rural Indian workshop — clay walls, raw natural light. VISUAL STORYTELLING: Rough hands against silk-smooth bamboo fabric. Heritage craftsmanship. The contrast IS the message. COMPOSITION: Split tonal — dark warm left (hands, workshop), light cream right (garment). Hands at cross-point. Leica 50mm documentary realism. — TYPOGRAPHY SYSTEM — Hero line: "ONE LAKH HANDS." — Canela Display Thin, mixed case, enormous scale, set across 80% of poster width. The word "HANDS" drops to second line, indented right — staggered layout creates visual rhythm like musical notation. Counter-line: Below "HANDS", flush right: "One fabric." — same Canela Thin but 28pt, italic. The tonal shift from all-caps to italic sentence case creates emotional contrast — like going from statement to confession. Brand stamp: "WELLBI" centred bottom — pressed as if letterpress embossed. Freight Display Pro Bold, tracked tight at -20. Earthen cream on warm brown. Feels physical. Tactile. Descriptor line: "Handcrafted bamboo apparel since 2021 — India" — 9pt, Suisse Int'l Light, tracking +200, full width, very bottom edge. Reads like a footnote on a heritage certificate. COLOUR: Terracotta, aged ivory, saffron gold, deep walnut. LIGHTING: Soft natural window light, warm practical lamp. Documentary-editorial quality. MOOD: Deeply human. D&AD craft award energy. CAMERA: Leica 50mm Summilux, skin texture visible, documentary realism with fashion editorial polish.
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": "Cinematic product poster for WELLBI, India's premium bamboo apparel brand. SCENE: A lone young Indian man emerges from a dense, luminous bamboo forest at golden hour. Wears a perfectly draped, ultra-clean ivory WELLBI bamboo polo. Bamboo stalks alive with warm amber and jade light filtering through canopy. VISUAL STORYTELLING: The bamboo forest IS the fabric — seamless living metaphor. Thin golden light rays land on the polo, suggesting softness and breathability. COMPOSITION: Low angle, subject centre-frame, bamboo framing both sides like a natural arch. Horizon at lower third. Cinematic 2.39:1 anamorphic crop. — TYPOGRAPHY SYSTEM — Hero line: \"GROWN.\" — single word, massive scale, Helvetica Neue Ultra Light, all caps, extreme letter-spacing +600, ghost white at 15% opacity overlaid across the ENTIRE poster width — architectural, not decorative. Sub-line: \"Not manufactured.\" — set in sharp Aktiv Grotesk Regular, sentence case, 18pt, tracking +80, positioned directly below hero word. White. Full opacity. Feels like a whisper after a shout. Brand name: \"WELLBI\" — bottom right corner. Neutral Grotesk Medium, all caps, tracking +300, 11pt. Separated by a 0.5pt hairline rule above it, 40px wide. Restrained. Premium. Legal/descriptor: \"100% Bamboo Apparel — India\" — micro text, 7pt, tracking +150, bottom left. Rotated 90° vertical. Acts as a structural edge element, not an afterthought. COLOUR PALETTE: Deep jungle green, warm amber, ivory white, earth brown. LIGHTING: ARRI Alexa Mini LF — golden hour rim, diffused fill, subtle lens flare grazing the polo fabric. MOOD: Grounded luxury. Like a Loro Piana campaign shot in Assam. CAMERA: 85mm f/1.4, shallow DOF, anamorphic lens flare. Editorial brand poster for WELLBI sustainable Indian fashion. SCENE: Extreme close-up of a weathered artisan's hands spinning bamboo thread. Blurred WELLBI tee draped elegantly in background. Warm-lit rural Indian workshop — clay walls, raw natural light. VISUAL STORYTELLING: Rough hands against silk-smooth bamboo fabric. Heritage craftsmanship. The contrast IS the message. COMPOSITION: Split tonal — dark warm left (hands, workshop), light cream right (garment). Hands at cross-point. Leica 50mm documentary realism. — TYPOGRAPHY SYSTEM — Hero line: \"ONE LAKH HANDS.\" — Canela Display Thin, mixed case, enormous scale, set across 80% of poster width. The word \"HANDS\" drops to second line, indented right — staggered layout creates visual rhythm like musical notation. Counter-line: Below \"HANDS\", flush right: \"One fabric.\" — same Canela Thin but 28pt, italic. The tonal shift from all-caps to italic sentence case creates emotional contrast — like going from statement to confession. Brand stamp: \"WELLBI\" centred bottom — pressed as if letterpress embossed. Freight Display Pro Bold, tracked tight at -20. Earthen cream on warm brown. Feels physical. Tactile. Descriptor line: \"Handcrafted bamboo apparel since 2021 — India\" — 9pt, Suisse Int'l Light, tracking +200, full width, very bottom edge. Reads like a footnote on a heritage certificate. COLOUR: Terracotta, aged ivory, saffron gold, deep walnut. LIGHTING: Soft natural window light, warm practical lamp. Documentary-editorial quality. MOOD: Deeply human. D&AD craft award energy. CAMERA: Leica 50mm Summilux, skin texture visible, documentary realism with fashion editorial polish."
}
JSON
A hyperrealistic premium denim advertisement shot in a dark, moody editorial style. A male figure wearing raw selvedge denim jeans is captured mid-stride against a near-black charcoal background, body angled diagonally at a bold 45-degree perspective toward the camera. The jeans feature a slim tapered silhouette with deep indigo wash, subtle thigh and knee fading, reinforced copper rivets catching ambient light, and clean off-white contrast stitching, dominating the lower two-thirds of the frame. The composition uses shallow depth of field with sharp focus on the denim texture and soft blur on the upper torso. 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 figure at different angles reading phrases like "RAW. REAL. RELENTLESS." and "WEAR WHAT YOU'VE BEEN THROUGH" — some running vertically, some at 30-degree angles, creating a chaotic yet intentional graphic zine energy. At the upper right, a bold brand wordmark appears in clean white against the dark background. At the top center, a thin horizontal navigation-style text bar reads "AUTHENTIC FIT · LIVED-IN LUXURY · BUILT TO LAST" in spaced all-caps serif font. A large commanding headline is placed center-right — "OWN" in massive ultra-bold white letters followed by "THE MOMENT" in lighter weight creating dramatic type hierarchy. Small yellow plus (+) symbols and diagonal arrows (↗) are scattered throughout as accent details. Bottom left features a bold slogan lockup: "DEFINE YOUR DENIM" in large bold sans-serif white text with a thin subline reading "An unapologetic reminder that style is a statement. Every crease tells a story." The overall lighting is dramatic and directional — a single cold key light from the left causing copper rivets to shimmer and deep indigo denim to glow with subtle sheen against the darkness. Close macro detail visible on the fabric weave texture near the knee fade. 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 premium denim advertisement shot in a dark, moody editorial style. A male figure wearing raw selvedge denim jeans is captured mid-stride against a near-black charcoal background, body angled diagonally at a bold 45-degree perspective toward the camera. The jeans feature a slim tapered silhouette with deep indigo wash, subtle thigh and knee fading, reinforced copper rivets catching ambient light, and clean off-white contrast stitching, dominating the lower two-thirds of the frame. The composition uses shallow depth of field with sharp focus on the denim texture and soft blur on the upper torso. 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 figure at different angles reading phrases like \"RAW. REAL. RELENTLESS.\" and \"WEAR WHAT YOU'VE BEEN THROUGH\" — some running vertically, some at 30-degree angles, creating a chaotic yet intentional graphic zine energy. At the upper right, a bold brand wordmark appears in clean white against the dark background. At the top center, a thin horizontal navigation-style text bar reads \"AUTHENTIC FIT · LIVED-IN LUXURY · BUILT TO LAST\" in spaced all-caps serif font. A large commanding headline is placed center-right — \"OWN\" in massive ultra-bold white letters followed by \"THE MOMENT\" in lighter weight creating dramatic type hierarchy. Small yellow plus (+) symbols and diagonal arrows (↗) are scattered throughout as accent details. Bottom left features a bold slogan lockup: \"DEFINE YOUR DENIM\" in large bold sans-serif white text with a thin subline reading \"An unapologetic reminder that style is a statement. Every crease tells a story.\" The overall lighting is dramatic and directional — a single cold key light from the left causing copper rivets to shimmer and deep indigo denim to glow with subtle sheen against the darkness. Close macro detail visible on the fabric weave texture near the knee fade. Photorealistic. Commercial photography quality. High contrast. 4K resolution. 3:4 vertical format optimized for social media."
}
JSON
Epic 8K cinematic fantasy food scene: a colossal crispy fried chicken leg rising like a legendary artifact through a tidal explosion of molten creamy sauce. Sauce behaves like liquid clouds, forming waves and splashes in mid-air. Pickle chunks, herb leaves, and seasoning particles float like asteroids in a food universe. Extreme macro texture on the crust—cracks, bubbles, and crunch visible. Powerful dramatic lighting with deep shadows and glowing highlights. Vibrant golden-yellow background with cinematic depth and atmospheric particles. Hyper-realistic yet mythic, bold surreal advertising masterpiece.
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": "Epic 8K cinematic fantasy food scene: a colossal crispy fried chicken leg rising like a legendary artifact through a tidal explosion of molten creamy sauce. Sauce behaves like liquid clouds, forming waves and splashes in mid-air. Pickle chunks, herb leaves, and seasoning particles float like asteroids in a food universe. Extreme macro texture on the crust—cracks, bubbles, and crunch visible. Powerful dramatic lighting with deep shadows and glowing highlights. Vibrant golden-yellow background with cinematic depth and atmospheric particles. Hyper-realistic yet mythic, bold surreal advertising masterpiece."
}
JSON
A square, 1:1 photorealistic close-up photograph of an incredibly detailed physical miniature geography and city model of [CITY], focused only on the city’s most recognizable landmark area (not the full city map). The scene shows a compact 3D topographic environment built around the iconic landmark zone — realistic terrain, elevation changes, nearby rivers or coastline if relevant, and surrounding urban density scaled naturally to highlight the landmark as the clear focal point. The model feels like a premium museum diorama rather than a map. Thousands of tiny, highly detailed buildings, roads, bridges, and infrastructure cluster organically around the landmark. The landmark itself rises prominently above everything else, instantly recognizable even at a glance. Strong natural side sunlight casts long, realistic shadows across the miniature terrain, enhancing depth and realism. Shallow depth of field (tilt-shift style) keeps the landmark zone sharply in focus while softly blurring the outer edges of the square frame. The entire scene appears as a tangible, physical model illuminated by real-world light. Above the city, the sky is perfectly clean and empty — no clouds at all — except for the city name. The name [CITY] appears integrated into the sky as thick, three-dimensional cloud typography, sculpted from dense white vapor. The letters are bold, volumetric, and clearly readable, with soft shadowing and subtle depth, floating naturally in the open sky. Opacity ~70%, but with enough thickness to remain instantly legible. A small, minimal national flag is placed subtly near the sky text (corner or aligned to the typography), balanced and unobtrusive. Format: Square 1080×1080 Style: Ultra-photorealistic, cinematic, premium miniature realism Mood: Awe, clarity, instantly recognizable, highly shareable
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 square, 1:1 photorealistic close-up photograph of an incredibly detailed physical miniature geography and city model of [CITY], focused only on the city’s most recognizable landmark area (not the full city map). The scene shows a compact 3D topographic environment built around the iconic landmark zone — realistic terrain, elevation changes, nearby rivers or coastline if relevant, and surrounding urban density scaled naturally to highlight the landmark as the clear focal point. The model feels like a premium museum diorama rather than a map. Thousands of tiny, highly detailed buildings, roads, bridges, and infrastructure cluster organically around the landmark. The landmark itself rises prominently above everything else, instantly recognizable even at a glance. Strong natural side sunlight casts long, realistic shadows across the miniature terrain, enhancing depth and realism. Shallow depth of field (tilt-shift style) keeps the landmark zone sharply in focus while softly blurring the outer edges of the square frame. The entire scene appears as a tangible, physical model illuminated by real-world light. Above the city, the sky is perfectly clean and empty — no clouds at all — except for the city name. The name [CITY] appears integrated into the sky as thick, three-dimensional cloud typography, sculpted from dense white vapor. The letters are bold, volumetric, and clearly readable, with soft shadowing and subtle depth, floating naturally in the open sky. Opacity ~70%, but with enough thickness to remain instantly legible. A small, minimal national flag is placed subtly near the sky text (corner or aligned to the typography), balanced and unobtrusive. Format: Square 1080×1080 Style: Ultra-photorealistic, cinematic, premium miniature realism Mood: Awe, clarity, instantly recognizable, highly shareable"
}
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.