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", "language": "en", "style": "realistic smartphone photography, vibrant sports atmosphere", "aspect_ratio": "3:4", "identity_preservation": { "use_reference_image": true, "strict_identity_lock": true, "alter_face": false, "alter_features": false, "notes": "Use the uploaded reference photo. Preserve 100% of the woman’s facial features, proportions, skin texture, hair, and identity." }, "subject": { "gender": "female", "pose": { "type": "selfie-style pose", "orientation": "facing the camera", "action": "static moment, as if pausing to take a selfie" }, "expression": "serious, confident, and admiring", "appearance": { "hair": "unchanged from reference image", "accessories": [ "aviator-style sunglasses with gold frame", "diamond stud earring in the right ear", "silver chain necklace with a pendant" ] }, "wardrobe": { "top": "official FC Barcelona jersey with Spotify sponsorship" } }, "composition": { "framing": "centered composition", "foreground": "woman occupying the first plane", "background": "football stadium and crowd", "perspective": "first-person selfie perspective" }, "environment": { "location": "packed football stadium", "elements": [ "vibrant green football pitch", "crowded stands full of fans", "energetic stadium atmosphere" ], "weather": "cloudy sky", "mood": "excitement, celebration, pride" }, "lighting": { "type": "natural daylight", "conditions": "bright but diffused due to cloudy sky", "effects": [ "vivid colors", "balanced exposure", "clear facial details" ] }, "camera": { "device_style": "smartphone rear camera", "shot_type": "selfie-style medium close-up", "focus": "sharp focus on the subject with slightly softened background", "quality": "high sharpness and clarity" }, "quality": { "realism": "highly realistic", "color": "vibrant and true-to-life", "detail_level": "clear textures on clothing, face, and stadium" }, "constraints": [ "Do not alter facial features", "No stylization or artistic filters", "No distortion of body or face", "No text overlays or watermarks", "Maintain realistic proportions and lighting" ], "output_goal": "Create a realistic, selfie-style photo of a woman wearing a Barcelona jersey in front of a packed football stadium, preserving her exact facial identity and conveying pride and admiration within a vibrant match-day 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": "{ \"type\": \"image_generation_prompt\", \"language\": \"en\", \"style\": \"realistic smartphone photography, vibrant sports atmosphere\", \"aspect_ratio\": \"3:4\", \"identity_preservation\": { \"use_reference_image\": true, \"strict_identity_lock\": true, \"alter_face\": false, \"alter_features\": false, \"notes\": \"Use the uploaded reference photo. Preserve 100% of the woman’s facial features, proportions, skin texture, hair, and identity.\" }, \"subject\": { \"gender\": \"female\", \"pose\": { \"type\": \"selfie-style pose\", \"orientation\": \"facing the camera\", \"action\": \"static moment, as if pausing to take a selfie\" }, \"expression\": \"serious, confident, and admiring\", \"appearance\": { \"hair\": \"unchanged from reference image\", \"accessories\": [ \"aviator-style sunglasses with gold frame\", \"diamond stud earring in the right ear\", \"silver chain necklace with a pendant\" ] }, \"wardrobe\": { \"top\": \"official FC Barcelona jersey with Spotify sponsorship\" } }, \"composition\": { \"framing\": \"centered composition\", \"foreground\": \"woman occupying the first plane\", \"background\": \"football stadium and crowd\", \"perspective\": \"first-person selfie perspective\" }, \"environment\": { \"location\": \"packed football stadium\", \"elements\": [ \"vibrant green football pitch\", \"crowded stands full of fans\", \"energetic stadium atmosphere\" ], \"weather\": \"cloudy sky\", \"mood\": \"excitement, celebration, pride\" }, \"lighting\": { \"type\": \"natural daylight\", \"conditions\": \"bright but diffused due to cloudy sky\", \"effects\": [ \"vivid colors\", \"balanced exposure\", \"clear facial details\" ] }, \"camera\": { \"device_style\": \"smartphone rear camera\", \"shot_type\": \"selfie-style medium close-up\", \"focus\": \"sharp focus on the subject with slightly softened background\", \"quality\": \"high sharpness and clarity\" }, \"quality\": { \"realism\": \"highly realistic\", \"color\": \"vibrant and true-to-life\", \"detail_level\": \"clear textures on clothing, face, and stadium\" }, \"constraints\": [ \"Do not alter facial features\", \"No stylization or artistic filters\", \"No distortion of body or face\", \"No text overlays or watermarks\", \"Maintain realistic proportions and lighting\" ], \"output_goal\": \"Create a realistic, selfie-style photo of a woman wearing a Barcelona jersey in front of a packed football stadium, preserving her exact facial identity and conveying pride and admiration within a vibrant match-day atmosphere.\" }"
}
JSON
Create a stylized miniature model of [CHARACTERS] shaped entirely from soft polymer clay. The figure has rounded, childlike anatomy — large head, small body, and simplified details that feel friendly and handcrafted. Its outfit and accessories match [CHARACTERS]’ iconic look, modeled with smooth curves and lively, saturated tones. The material appears dry and tactile, with a powdery matte finish and subtle surface texture—avoid gloss, shine, or reflections. Lighting should be gentle and even, wrapping softly around the form with faint ambient shading to reveal volume. Present the figurine standing upright, slightly turned toward the right, framed in a minimal off-white environment with a smooth floor and faint contact shadow beneath. The overall composition feels calm, neat, and balanced—like a clay sculpture photographed for a design catalog.
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 stylized miniature model of [CHARACTERS] shaped entirely from soft polymer clay. The figure has rounded, childlike anatomy — large head, small body, and simplified details that feel friendly and handcrafted. Its outfit and accessories match [CHARACTERS]’ iconic look, modeled with smooth curves and lively, saturated tones. The material appears dry and tactile, with a powdery matte finish and subtle surface texture—avoid gloss, shine, or reflections. Lighting should be gentle and even, wrapping softly around the form with faint ambient shading to reveal volume. Present the figurine standing upright, slightly turned toward the right, framed in a minimal off-white environment with a smooth floor and faint contact shadow beneath. The overall composition feels calm, neat, and balanced—like a clay sculpture photographed for a design catalog."
}
JSON
Create a cinematic, high-fashion half-length portrait of me with a dreamy editorial vibe. Use multi-exposure blur for ghosting and vertical streaks. Set against a blue gradient background (#0033A0 to #66CCFF), the subject wears an oversized white T-shirt. Apply high-contrast lighting (cool blue wash + orange/yellow edge highlights) for a futuristic glow. Expression: neutral/introspective, eyes softly lit. Simulate 50-85mm lens at f/1.8 with shallow dep r field Enhance with motion blur and chromatic separation, keeping central details sharp. Aim for a surreal, digital-youth mood blending minimalism and light play.
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 cinematic, high-fashion half-length portrait of me with a dreamy editorial vibe. Use multi-exposure blur for ghosting and vertical streaks. Set against a blue gradient background (#0033A0 to #66CCFF), the subject wears an oversized white T-shirt. Apply high-contrast lighting (cool blue wash + orange/yellow edge highlights) for a futuristic glow. Expression: neutral/introspective, eyes softly lit. Simulate 50-85mm lens at f/1.8 with shallow dep r field Enhance with motion blur and chromatic separation, keeping central details sharp. Aim for a surreal, digital-youth mood blending minimalism and light play."
}
JSON
Hip-hop fashion model standing full-frame, clothing distorted into stretched streaks like motion drag, bold red background, retro film grain, barcode + tiny technical text in bottom area, modern fashion-magazine layout, expressive weirdness, cool attitude , 4K high detail. --ar 4:5 --raw
A hyper-detailed 3D render of a collectible chess piece designed as [ICON]. The figure is sculpted in polished marble and gold accents, with a stylized base resembling a classic chess piece. The character’s iconic features, clothing, or accessories are faithfully captured in a simplified but instantly recognizable form. Studio lighting with soft reflections, dramatic shadows, photorealistic textures, cinematic presentation. Centered on a clean neutral background
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-detailed 3D render of a collectible chess piece designed as [ICON]. The figure is sculpted in polished marble and gold accents, with a stylized base resembling a classic chess piece. The character’s iconic features, clothing, or accessories are faithfully captured in a simplified but instantly recognizable form. Studio lighting with soft reflections, dramatic shadows, photorealistic textures, cinematic presentation. Centered on a clean neutral background"
}
JSON
Minimalist commercial ad featuring oversized white smartwatch, ultra-clean design. A young woman in all-white outfit leans casually against the giant watch, relaxed confident pose, eyes closed, also wearing the same smartwatch on her wrist. Soft gradient blue background with large bold white “APPLE” text behind. Glossy reflective floor, soft studio lighting, modern high-end fashion/product photography. Small top-right text “Designed by Mr Das”. Bottom center tagline in small white font: “Stay connected, move smarter.”
curl -X POST https://runapi.ai/api/v1/gpt_image_2/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "gpt-image-2",
"prompt": "Minimalist commercial ad featuring oversized white smartwatch, ultra-clean design. A young woman in all-white outfit leans casually against the giant watch, relaxed confident pose, eyes closed, also wearing the same smartwatch on her wrist. Soft gradient blue background with large bold white “APPLE” text behind. Glossy reflective floor, soft studio lighting, modern high-end fashion/product photography. Small top-right text “Designed by Mr Das”. Bottom center tagline in small white font: “Stay connected, move smarter.”"
}
JSON
Fantastic digital painting of a young man with high detail, smooth shading, and sharp, bold lines. He stands in a powerful victory pose with his arms outstretched, confident and fearless expression. A brilliantly blended background with swirling smoke and flame like energy effects surrounds him. Neon sparks radiate from his body, creating a vibrant, glowing aura with cinematic lighting and dramatic contrast.
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": "Fantastic digital painting of a young man with high detail, smooth shading, and sharp, bold lines. He stands in a powerful victory pose with his arms outstretched, confident and fearless expression. A brilliantly blended background with swirling smoke and flame like energy effects surrounds him. Neon sparks radiate from his body, creating a vibrant, glowing aura with cinematic lighting and dramatic contrast."
}
JSON
{ "type": "image_generation_prompt", "style": "Polaroid-style candid photography", "camera_style": { "camera": "Polaroid instant camera", "look": "ordinary snapshot", "effects": [ "slight blur", "soft focus", "flash-lit dark room glow", "light scattering from on-camera flash", "subtle film grain", "slight exposure falloff" ] }, "identity_preservation": { "use_reference_images": true, "strict_identity_lock": true, "alter_face": false, "notes": "Do not change or distort either person’s facial features, expressions, or proportions." }, "subjects": [ { "gender": "female", "identity": "user", "pose": "cute, casual pose standing close to the boy", "prop": "holding a burger", "expression": "natural, playful, candid" }, { "gender": "male", "identity": "boy from reference", "pose": "cute, relaxed pose next to the girl", "prop": "holding a red Coca-Cola can", "expression": "natural, playful, candid" } ], "interaction": { "relationship": "friendly and cute", "body_language": "standing close together, relaxed, slightly leaning toward each other" }, "environment": { "background": "plain white curtains", "location": "indoor room", "lighting": { "type": "single on-camera flash", "quality": "consistent, frontal flash lighting", "mood": "cozy, intimate, nostalgic" } }, "composition": { "framing": "medium shot", "angle": "eye-level", "balance": "centered, casual snapshot composition" }, "aesthetic": { "vibe": "cute, nostalgic, intimate", "era_feel": "classic instant film look", "imperfections": [ "minor blur", "soft edges", "natural exposure inconsistencies" ] }, "constraints": [ "No change to faces", "No dramatic posing", "No artificial glamour or studio look", "No text or watermarks", "Must look like a real Polaroid photo" ], "output_goal": "Create a realistic Polaroid-style instant photo of a boy and girl posing cutely together indoors, with white curtains behind them, flash-lit from a dark room, the boy holding a red Coca-Cola can and the girl holding a burger, maintaining an authentic, nostalgic snapshot feel." }
Advertising-style food photography of a stack of pancakes arranged on a rustic table, with maple syrup droplets floating above in mid-air and a splash of syrup frozen in motion. High-resolution photo manipulation with selective soft focus, clean negative space for text, dramatic lighting, and crisp detail. --ar 3:2 --v 7
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": "Advertising-style food photography of a stack of pancakes arranged on a rustic table, with maple syrup droplets floating above in mid-air and a splash of syrup frozen in motion. High-resolution photo manipulation with selective soft focus, clean negative space for text, dramatic lighting, and crisp detail. --ar 3:2 --v 7"
}
JSON
Full-body fashion editorial shot of a confident young person model sitting casually on a concrete ledge, legs slightly apart, one arm resting on knee, the other relaxed, looking straight at camera with a calm dominant expression. Wearing a light denim jacket over a plain white t-shirt, neutral shorts, bright socks, and modern sneakers. Clean styling, natural pose, wind slightly moving hair and fabric. Beside and partially interacting with a stylized cartoon [ANIMAL], positioned naturally as if sharing the same space. The [ANIMAL] is illustrated in bold cartoon style with thick black outlines, vibrant neon color palette (blue, green, yellow accents), exaggerated proportions, expressive features, playful yet powerful presence. Background: bright outdoor urban setting with clear blue sky, soft clouds, sunlit concrete textures, strong natural daylight, crisp shadows. Fusion of hyper-realistic photography and graphic illustration, seamless integration between subject and cartoon. Add graphic overlay elements: doodle arrows, scribbles, abstract shapes, comic-style symbols, dynamic motion lines. High contrast, HDR lighting, sharp focus, fashion editorial composition, surreal mixed-media aesthetic, ultra-detailed, 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": "Full-body fashion editorial shot of a confident young person model sitting casually on a concrete ledge, legs slightly apart, one arm resting on knee, the other relaxed, looking straight at camera with a calm dominant expression. Wearing a light denim jacket over a plain white t-shirt, neutral shorts, bright socks, and modern sneakers. Clean styling, natural pose, wind slightly moving hair and fabric. Beside and partially interacting with a stylized cartoon [ANIMAL], positioned naturally as if sharing the same space. The [ANIMAL] is illustrated in bold cartoon style with thick black outlines, vibrant neon color palette (blue, green, yellow accents), exaggerated proportions, expressive features, playful yet powerful presence. Background: bright outdoor urban setting with clear blue sky, soft clouds, sunlit concrete textures, strong natural daylight, crisp shadows. Fusion of hyper-realistic photography and graphic illustration, seamless integration between subject and cartoon. Add graphic overlay elements: doodle arrows, scribbles, abstract shapes, comic-style symbols, dynamic motion lines. High contrast, HDR lighting, sharp focus, fashion editorial composition, surreal mixed-media aesthetic, ultra-detailed, 8k resolution."
}
JSON
Person from the reference image, with a fade haircut, brown eyes, and a well-groomed short beard, wearing a glossy oversized red puffer jacket and loose red pants with white and red nike sneakers, crouching low with one knee up and one leg forward, left arm resting casually over the raised knee and right hand relaxed near the other leg, body angled slightly to the side while head tilts forward looking directly at the camera with a confident expression, ultra wide-angle low perspective shot emphasizing the front sneaker appearing large and dominant in the foreground, set in a fully red environment with smooth floor and backdrop featuring large white nike swoosh logos behind and flowing ribbon-like red shapes around, hyper-realistic photography, extremely sharp details on fabric shine and sneaker texture, dramatic studio lighting with strong highlights and soft shadows, saturated monochromatic red color palette with white accents, modern streetwear campaign style, no blur, no distortion, no extra limbs, no artifacts
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": "Person from the reference image, with a fade haircut, brown eyes, and a well-groomed short beard, wearing a glossy oversized red puffer jacket and loose red pants with white and red nike sneakers, crouching low with one knee up and one leg forward, left arm resting casually over the raised knee and right hand relaxed near the other leg, body angled slightly to the side while head tilts forward looking directly at the camera with a confident expression, ultra wide-angle low perspective shot emphasizing the front sneaker appearing large and dominant in the foreground, set in a fully red environment with smooth floor and backdrop featuring large white nike swoosh logos behind and flowing ribbon-like red shapes around, hyper-realistic photography, extremely sharp details on fabric shine and sneaker texture, dramatic studio lighting with strong highlights and soft shadows, saturated monochromatic red color palette with white accents, modern streetwear campaign style, no blur, no distortion, no extra limbs, no artifacts"
}
JSON
Ultra-clean modern editorial infographic on the topic of [ROUTINE] routine. Hero visual: a stylized flat-lay or floating arrangement of 3–4 objects closely associated with the routine — 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 items with small icons or emoji illustrations next to each. Each item has a name and a practical quantity or duration written like a recipe (e.g. ‘x minutes of Y’). Arranged in a cluster or list connected visually to the hero. Steps Section: 5–6 numbered panels with arrows or connecting lines forming a logical flow. Each step has a short action label and a small relevant icon. Panels use glassmorphism or frosted card styling. Stats Badges: 4–5 floating pill-shaped badges showing relevant metadata — total time, difficulty, consistency streak, energy cost — displayed as clean minimal bubbles near the hero. Visual Style: Warm, soft editorial background — cream, warm white, or soft morning light tones. Muted earthy accent colors with clean highlights. Bold modern sans-serif typography. Clean vector icons. Subtle grain or paper texture in background. Composition: Hero object cluster centered or slightly offset. Ingredients on one side. Steps flow opposite or below with connecting lines. Stat badges scattered as floating pills. Generous negative space to keep it airy and readable. Lighting: Soft warm natural light feel emanating from the hero cluster. Premium lifestyle 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 on the topic of [ROUTINE] routine. Hero visual: a stylized flat-lay or floating arrangement of 3–4 objects closely associated with the routine — 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 items with small icons or emoji illustrations next to each. Each item has a name and a practical quantity or duration written like a recipe (e.g. ‘x minutes of Y’). Arranged in a cluster or list connected visually to the hero. Steps Section: 5–6 numbered panels with arrows or connecting lines forming a logical flow. Each step has a short action label and a small relevant icon. Panels use glassmorphism or frosted card styling. Stats Badges: 4–5 floating pill-shaped badges showing relevant metadata — total time, difficulty, consistency streak, energy cost — displayed as clean minimal bubbles near the hero. Visual Style: Warm, soft editorial background — cream, warm white, or soft morning light tones. Muted earthy accent colors with clean highlights. Bold modern sans-serif typography. Clean vector icons. Subtle grain or paper texture in background. Composition: Hero object cluster centered or slightly offset. Ingredients on one side. Steps flow opposite or below with connecting lines. Stat badges scattered as floating pills. Generous negative space to keep it airy and readable. Lighting: Soft warm natural light feel emanating from the hero cluster. Premium lifestyle editorial aesthetic, social-feed optimized. Ultra-crisp. No watermark."
}
JSON
Convert this image into a dramatic, stylized portrait (use the same face as the uploaded photo), 9:16 aspect ratio, featuring a dark, almost silhouetted figure in profile looking to the left. The background is a deep electric blue. Intense black and sapphire paint splashes burst outward from the head and shoulders, creating powerful motion energy. Ultra-sharp lighting, cinematic contrast, HD photo. Signature: DUET
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": "Convert this image into a dramatic, stylized portrait (use the same face as the uploaded photo), 9:16 aspect ratio, featuring a dark, almost silhouetted figure in profile looking to the left. The background is a deep electric blue. Intense black and sapphire paint splashes burst outward from the head and shoulders, creating powerful motion energy. Ultra-sharp lighting, cinematic contrast, HD photo. Signature: DUET"
}
JSON
full body female model in confident fashion pose (one leg slightly raised, relaxed luxury stance), wearing oversized black blazer, fitted black crop top, high-waisted baggy blue denim jeans, black heels, slim sunglasses, holding a small black handbag, clean long hair, sharp facial features minimal luxury studio background, soft beige gradient wall, smooth shadows, editorial lighting, high-end fashion campaign style large embossed “PREMIUM” text in background, subtle 3D depth, tone-on-tone color blending with wall, elegant and soft keep “BAGGY” text bold and minimal near bottom, modern premium sans-serif font add “GUCCI” logo top right corner, clean spacing, luxury typography ultra realistic, sharp focus, premium color grading, soft highlights, depth of field, magazine-quality, clean composition, no clutter
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": "full body female model in confident fashion pose (one leg slightly raised, relaxed luxury stance), wearing oversized black blazer, fitted black crop top, high-waisted baggy blue denim jeans, black heels, slim sunglasses, holding a small black handbag, clean long hair, sharp facial features minimal luxury studio background, soft beige gradient wall, smooth shadows, editorial lighting, high-end fashion campaign style large embossed “PREMIUM” text in background, subtle 3D depth, tone-on-tone color blending with wall, elegant and soft keep “BAGGY” text bold and minimal near bottom, modern premium sans-serif font add “GUCCI” logo top right corner, clean spacing, luxury typography ultra realistic, sharp focus, premium color grading, soft highlights, depth of field, magazine-quality, clean composition, no clutter"
}
JSON
Low-angle close-up portrait of a platinum blonde woman wearing oversized sculptural sunglasses crafted from delicate translucent layered flower petals in vibrant magenta, amber, and lilac hues, subtle silk texture visible in each petal with soft golden light passing through the edges, an extravagant couture choker necklace constructed from densely layered matching petals wrapping seamlessly around her entire neck with dimensional depth and organic curvature, her chin slightly lifted with a confident sculpted jawline, subtle freckles dusted across the bridge of her nose, naturally hydrated glossy lips with a soft highlight along the cupid’s bow, fine platinum hair strands gently lifted by a warm breeze with delicate motion at the ends, standing against a softly textured architectural backdrop of warm terracotta walls washed in golden sunset light with cascading lilac bougainvillea and amber-toned stone details, background melting into creamy magenta and lavender bokeh with soft atmospheric glow, rich golden hour sunlight illuminating her face evenly with gentle shadow contouring, warm reflected light from terracotta surfaces enhancing skin luminosity, faint rim light outlining her hair and shoulders, ultra-photorealistic high-fashion editorial photography, cinematic jewel-toned color grading balancing amber highlights with soft lilac shadows and magenta accents, shallow depth of field with elegant telephoto compression, razor-sharp focus on eyelashes and petal contours, shot on Sony A1, 70–200mm lens at 135mm, f/2, ISO 125, 1/1000s, professional editorial sharpness, museum-quality detail, vertical 2:3 composition with eye aligned along upper third –ar 2:3 –v 6 –s 900 –q 3 –style raw –no text, harsh shadows, lens distortion, oversaturation, artifacts, artificial glow
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": "Low-angle close-up portrait of a platinum blonde woman wearing oversized sculptural sunglasses crafted from delicate translucent layered flower petals in vibrant magenta, amber, and lilac hues, subtle silk texture visible in each petal with soft golden light passing through the edges, an extravagant couture choker necklace constructed from densely layered matching petals wrapping seamlessly around her entire neck with dimensional depth and organic curvature, her chin slightly lifted with a confident sculpted jawline, subtle freckles dusted across the bridge of her nose, naturally hydrated glossy lips with a soft highlight along the cupid’s bow, fine platinum hair strands gently lifted by a warm breeze with delicate motion at the ends, standing against a softly textured architectural backdrop of warm terracotta walls washed in golden sunset light with cascading lilac bougainvillea and amber-toned stone details, background melting into creamy magenta and lavender bokeh with soft atmospheric glow, rich golden hour sunlight illuminating her face evenly with gentle shadow contouring, warm reflected light from terracotta surfaces enhancing skin luminosity, faint rim light outlining her hair and shoulders, ultra-photorealistic high-fashion editorial photography, cinematic jewel-toned color grading balancing amber highlights with soft lilac shadows and magenta accents, shallow depth of field with elegant telephoto compression, razor-sharp focus on eyelashes and petal contours, shot on Sony A1, 70–200mm lens at 135mm, f/2, ISO 125, 1/1000s, professional editorial sharpness, museum-quality detail, vertical 2:3 composition with eye aligned along upper third –ar 2:3 –v 6 –s 900 –q 3 –style raw –no text, harsh shadows, lens distortion, oversaturation, artifacts, artificial glow"
}
JSON
A vertical LEGO diorama showing [LANDMARK], [COUNTRY]). The scene is built entirely from LEGO bricks. A small [COUNTRY] flag is positioned at the top of the structure. Use a plain white background with a subtle shadow cast by the structure. 3D rendered, high-resolution, cute and clean LEGO style. 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 vertical LEGO diorama showing [LANDMARK], [COUNTRY]). The scene is built entirely from LEGO bricks. A small [COUNTRY] flag is positioned at the top of the structure. Use a plain white background with a subtle shadow cast by the structure. 3D rendered, high-resolution, cute and clean LEGO style. 1080x1080 dimension"
}
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.