{ "image_style": "surreal, dark cinematic, ethereal", "subject": { "person": "woman with features of reference image", "pose": "head tilted back, eyes closed, expression of freedom and release", "framing": "close-up portrait from chest upward", "clothing": "long-sleeve blouse made of organic, layered deep matte black raven feathers", "accessories": "large black hoop earrings" }, "visual_effects": { "hair": "loose, dynamically suspended, blowing upward and forward by wind", "dissolving_elements": [ "feathers and hair merging with black ink splatters", "charcoal dust", "wisps of dark smoke" ], "face_details": "fine black ink splatters and wisps spreading across face and neck" }, "environment": { "background": "smoky gray, moody atmosphere", "elements": "thick, dense, layered smoke swirling throughout the frame" }, "technical_aspects": { "resolution": "high-resolution", "lighting": "cinematic, moody, diffused through smoke" } }
Ultra-cinematic product photography of a matte black luxury soda bottle labeled “NOIR FIZZ”, floating mid-air at a sharp diagonal angle; carbonated bubbles and liquid soda waves frozen in motion, shattered ice cubes and glossy black citrus slices suspended; dramatic low-key lighting with strong rim lights, metallic highlights, deep shadows; black and gold color palette, volumetric mist, macro textures, hyper-realistic glass, 8K, premium commercial ad 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": "Ultra-cinematic product photography of a matte black luxury soda bottle labeled “NOIR FIZZ”, floating mid-air at a sharp diagonal angle; carbonated bubbles and liquid soda waves frozen in motion, shattered ice cubes and glossy black citrus slices suspended; dramatic low-key lighting with strong rim lights, metallic highlights, deep shadows; black and gold color palette, volumetric mist, macro textures, hyper-realistic glass, 8K, premium commercial ad style."
}
JSON
Low angle luxury product photography of a black ribbed glass perfume bottle placed on a dark horizontal podium, shot from below for a heroic, monumental feel. The bottle is Tom Ford Black Orchid, matte black texture clearly visible. Dramatic low key studio lighting. Soft diffused key light from above and slightly left, gently lighting the label and top, revealing volume and texture. Strong hard red rim light from behind and right, creating a bold red outline along the edge and cap, with a subtle red glow bleeding into the background. Deep soft shadows with smooth falloff. Slightly underexposed for drama. High contrast between highlights and shadows while keeping transitions soft. Color palette limited to deep black and rich burgundy red, warm color balance, black remains neutral and clean. Matte surface shows soft red reflections, not glossy, giving depth and form. Minimal background, dark red gradient, cinematic mood, luxury fragrance advertising style, photorealistic, ultra high detail, studio quality.
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 luxury product photography of a black ribbed glass perfume bottle placed on a dark horizontal podium, shot from below for a heroic, monumental feel. The bottle is Tom Ford Black Orchid, matte black texture clearly visible. Dramatic low key studio lighting. Soft diffused key light from above and slightly left, gently lighting the label and top, revealing volume and texture. Strong hard red rim light from behind and right, creating a bold red outline along the edge and cap, with a subtle red glow bleeding into the background. Deep soft shadows with smooth falloff. Slightly underexposed for drama. High contrast between highlights and shadows while keeping transitions soft. Color palette limited to deep black and rich burgundy red, warm color balance, black remains neutral and clean. Matte surface shows soft red reflections, not glossy, giving depth and form. Minimal background, dark red gradient, cinematic mood, luxury fragrance advertising style, photorealistic, ultra high detail, studio quality."
}
JSON
Photorealistic studio portrait of an average British man in his late 20s to early 40s, natural appearance, realistic facial features, short well-groomed hair, light stubble or clean-shaven. He stands confidently with a relaxed posture, conveying quiet self-assurance. He wears a stylish, comfortable, modern casual outfit, a well-fitted neutral-toned jacket or overshirt, premium plain t-shirt, tailored trousers or dark jeans, and clean minimalist sneakers. The look is contemporary, understated, and effortlessly fashionable. Shot in a professional studio with minimal lighting: a soft key light focused on the subject with gentle shadow falloff, dark neutral background, high contrast, and strong subject isolation. Lighting highlights facial structure, textures, and silhouette while keeping the environment subtle. Sharp focus on the subject, shallow depth of field, natural skin texture, realistic fabric detail, editorial fashion photography style, ultra-realistic, high resolution. Negative prompt (optional): blur, heavy retouching, unrealistic skin, dramatic fashion styling, cluttered background, extra limbs, distortion, cartoonish 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": "Photorealistic studio portrait of an average British man in his late 20s to early 40s, natural appearance, realistic facial features, short well-groomed hair, light stubble or clean-shaven. He stands confidently with a relaxed posture, conveying quiet self-assurance. He wears a stylish, comfortable, modern casual outfit, a well-fitted neutral-toned jacket or overshirt, premium plain t-shirt, tailored trousers or dark jeans, and clean minimalist sneakers. The look is contemporary, understated, and effortlessly fashionable. Shot in a professional studio with minimal lighting: a soft key light focused on the subject with gentle shadow falloff, dark neutral background, high contrast, and strong subject isolation. Lighting highlights facial structure, textures, and silhouette while keeping the environment subtle. Sharp focus on the subject, shallow depth of field, natural skin texture, realistic fabric detail, editorial fashion photography style, ultra-realistic, high resolution. Negative prompt (optional): blur, heavy retouching, unrealistic skin, dramatic fashion styling, cluttered background, extra limbs, distortion, cartoonish style."
}
JSON
Create an epic premium automotive poster of [CAR MODEL]. Place the car as the heroic central subject in a dynamic three-quarter side profile, visually dominant and impossible to ignore. Show the full beauty of the vehicle with aggressive stance, perfect proportions, premium wheels, signature headlights, aerodynamic lines, spoilers, performance details, and luxury design language. Add bold premium typography with the brand name, model name, performance stats, horsepower, acceleration, top speed, engine specs, and iconic achievements beautifully integrated into the composition. Include subtle background elements inspired by the car’s heritage: faded blueprint lines, racing legacy, silhouette overlays, iconic tracks, engineering details, speed graphics, and collector-poster aesthetics. Use strong visual contrast, bright premium colors (avoid dark black-heavy backgrounds), cinematic lighting, ultra-detailed reflections, glossy paint finish, luxury magazine quality, modern graphic design, and scroll-stopping masterpiece energy. Clean composition, high-end automotive advertisement style, collector poster aesthetic, highly detailed, visually powerful, premium 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": "Create an epic premium automotive poster of [CAR MODEL]. Place the car as the heroic central subject in a dynamic three-quarter side profile, visually dominant and impossible to ignore. Show the full beauty of the vehicle with aggressive stance, perfect proportions, premium wheels, signature headlights, aerodynamic lines, spoilers, performance details, and luxury design language. Add bold premium typography with the brand name, model name, performance stats, horsepower, acceleration, top speed, engine specs, and iconic achievements beautifully integrated into the composition. Include subtle background elements inspired by the car’s heritage: faded blueprint lines, racing legacy, silhouette overlays, iconic tracks, engineering details, speed graphics, and collector-poster aesthetics. Use strong visual contrast, bright premium colors (avoid dark black-heavy backgrounds), cinematic lighting, ultra-detailed reflections, glossy paint finish, luxury magazine quality, modern graphic design, and scroll-stopping masterpiece energy. Clean composition, high-end automotive advertisement style, collector poster aesthetic, highly detailed, visually powerful, premium masterpiece."
}
JSON
A high-fidelity 3D character render of a cute, stylized boy skateboarding in a dynamic pose. The boy has 'chibi' proportions with a large head, wearing oversized round wire-frame glasses and making a surprised 'O' mouth expression. He is dressed in an extremely fuzzy, textured blue mohair sweater with the text "OID" on the chest, a matching fuzzy blue beanie with a cream patch, and baggy camouflage-patterned pants made of a soft, velvet-like fabric. He wears chunky white sneakers and a small necklace pouch with a cartoon face. The background is a solid, seamless teal color. The lighting is soft and diffuse studio lighting, creating a clean, high-end "blind box" art toy aesthetic with hyper-realistic fabric textures.
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-fidelity 3D character render of a cute, stylized boy skateboarding in a dynamic pose. The boy has 'chibi' proportions with a large head, wearing oversized round wire-frame glasses and making a surprised 'O' mouth expression. He is dressed in an extremely fuzzy, textured blue mohair sweater with the text \"OID\" on the chest, a matching fuzzy blue beanie with a cream patch, and baggy camouflage-patterned pants made of a soft, velvet-like fabric. He wears chunky white sneakers and a small necklace pouch with a cartoon face. The background is a solid, seamless teal color. The lighting is soft and diffuse studio lighting, creating a clean, high-end \"blind box\" art toy aesthetic with hyper-realistic fabric textures."
}
JSON
Surreal premium commercial illustration for [BRAND NAME] [OIL TYPE], featuring the product bottle embedded into a massive natural landscape made entirely from the core ingredient. The ingredient appears at the top source, flowing as a natural element into the bottle, then transforming into waterfalls, rivers, or pools below. The environment, terrain, vegetation, textures, and color palette are all inspired by [PRIMARY INGREDIENT]. Small human figures interact naturally with the environment to emphasize scale. Cinematic lighting, soft painterly realism, ultra-detailed textures, fantasy-meets-nature aesthetic, vertical poster composition, 8K ultra-high 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": "Surreal premium commercial illustration for [BRAND NAME] [OIL TYPE], featuring the product bottle embedded into a massive natural landscape made entirely from the core ingredient. The ingredient appears at the top source, flowing as a natural element into the bottle, then transforming into waterfalls, rivers, or pools below. The environment, terrain, vegetation, textures, and color palette are all inspired by [PRIMARY INGREDIENT]. Small human figures interact naturally with the environment to emphasize scale. Cinematic lighting, soft painterly realism, ultra-detailed textures, fantasy-meets-nature aesthetic, vertical poster composition, 8K ultra-high resolution."
}
JSON
Create a dramatic, digital painting-style portrait of a male footballer looking upwards with a determined expression. The style should be bold and textured, using dynamic brushstrokes and a limited color palette mainly black, white, red, and yellow. The background should be split vertically with abstract red and yellow paint streaks. On the red side, include the bold motivational text ‘I’VE JUST BEGUN’ in large white, hand-painted font. Capture the intensity and ambition in the player’s gaze. The composition should feel motivational and powerful, ideal for a sports poster. 8k Resolution, Image Aspect Ratio 4:5."
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 dramatic, digital painting-style portrait of a male footballer looking upwards with a determined expression. The style should be bold and textured, using dynamic brushstrokes and a limited color palette mainly black, white, red, and yellow. The background should be split vertically with abstract red and yellow paint streaks. On the red side, include the bold motivational text ‘I’VE JUST BEGUN’ in large white, hand-painted font. Capture the intensity and ambition in the player’s gaze. The composition should feel motivational and powerful, ideal for a sports poster. 8k Resolution, Image Aspect Ratio 4:5.\""
}
JSON
The scene is lit by warm golden hour sunlight, with glowing dust particles floating in the air, creating a soft magical atmosphere. Background is a rustic wooden village setting, softly blurred with shallow depth of field. Cinematic lighting, soft rim light on hair, volumetric light rays, ultra-detailed, high quality, Pixar / Disney-style 3D render, cute, cozy, whimsical, warm color palette, 4k, bokeh, soft focus.
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": "The scene is lit by warm golden hour sunlight, with glowing dust particles floating in the air, creating a soft magical atmosphere. Background is a rustic wooden village setting, softly blurred with shallow depth of field. Cinematic lighting, soft rim light on hair, volumetric light rays, ultra-detailed, high quality, Pixar / Disney-style 3D render, cute, cozy, whimsical, warm color palette, 4k, bokeh, soft focus."
}
JSON
Create a technical infographic of [VEHICLE] with a 45-degree isometric 3D perspective showing the device slightly tilted to reveal depth and dimension. Combine a realistic photoreal render with black ink technical annotations on pure white background. Include: Key component labels with color-coded callout boxes Internal component visibility through transparent/cutaway sections Measurements, dimensions, and precise scale markers Material callouts and quantities Color-coded arrows for function/flow: RED (power/battery), BLUE (data/connectivity), ORANGE (thermal/processor), GREEN (sensors/haptics) Simple schematics or cross-sectional diagrams where relevant Place “VEHICLE” title in a hand-drawn technical box (top-left corner). Style: Black linework (technical pen/architectural), sketched but precise. Object remains clearly visible. Educational museum-exhibit vibe. Clean composition, balanced negative space. Perspective: Isometric 3D angle—tilted to show depth, dimension, and internal architecture dramatically. Like a professional product teardown or engineering manual. Colors: ~10-15% accent density. Black dominant. White background. Output: 1080×1080, ultra-crisp, social-feed optimized
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 technical infographic of [VEHICLE] with a 45-degree isometric 3D perspective showing the device slightly tilted to reveal depth and dimension. Combine a realistic photoreal render with black ink technical annotations on pure white background. Include: Key component labels with color-coded callout boxes Internal component visibility through transparent/cutaway sections Measurements, dimensions, and precise scale markers Material callouts and quantities Color-coded arrows for function/flow: RED (power/battery), BLUE (data/connectivity), ORANGE (thermal/processor), GREEN (sensors/haptics) Simple schematics or cross-sectional diagrams where relevant Place “VEHICLE” title in a hand-drawn technical box (top-left corner). Style: Black linework (technical pen/architectural), sketched but precise. Object remains clearly visible. Educational museum-exhibit vibe. Clean composition, balanced negative space. Perspective: Isometric 3D angle—tilted to show depth, dimension, and internal architecture dramatically. Like a professional product teardown or engineering manual. Colors: ~10-15% accent density. Black dominant. White background. Output: 1080×1080, ultra-crisp, social-feed optimized"
}
JSON
A soft, high-quality plush toy of [CHARACTER], with an oversized head, small body, and stubby limbs. Made of fuzzy fabric with visible stitching and embroidered facial features. The plush is shown sitting or standing against a neutral background. The expression is cute or expressive, and it wears simple clothes or iconic accessories if relevant. Lighting is soft and even, with a realistic, collectible plush look. Centered, full-body view
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 soft, high-quality plush toy of [CHARACTER], with an oversized head, small body, and stubby limbs. Made of fuzzy fabric with visible stitching and embroidered facial features. The plush is shown sitting or standing against a neutral background. The expression is cute or expressive, and it wears simple clothes or iconic accessories if relevant. Lighting is soft and even, with a realistic, collectible plush look. Centered, full-body view"
}
JSON
{ "prompt_name": "Lays_Spanish_Tomato_Tango_Explosion", "description": "Ultra-realistic commercial food photography showing a red Lay’s snack packet torn open from the top, positioned at the bottom center of the frame. Golden ridged potato chips are explosively bursting upward in frozen mid-air motion. Thick red tomato sauce splashes dynamically around the chips, forming arcs and droplets. Fresh whole tomatoes and halved tomatoes with visible seeds are flying around. Small crispy crumbs and seasoning particles are suspended in the air. The Lay’s logo is clearly visible on the packet, with readable text: 'Spanish Tomato Tango Flavour'. The packet surface is glossy and reflective with realistic wrinkles. Background is a deep red gradient filled with floating sauce droplets and particles, creating intense energy.", "lighting": "Dramatic warm studio lighting with strong highlights, deep shadows, and high contrast", "color_palette": ["deep red", "tomato red", "golden yellow", "dark orange"], "motion": "High-energy explosive upward motion with frozen splashes and flying fragments", "focus": "Ultra-sharp focus on chips, sauce splashes, and packet branding", "texture_detail": "Highly detailed ridged chip texture, glossy liquid splashes, realistic foil reflections", "style": "Premium FMCG commercial advertising, cinematic realism", "resolution": "8K", "aspect_ratio": "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": "{ \"prompt_name\": \"Lays_Spanish_Tomato_Tango_Explosion\", \"description\": \"Ultra-realistic commercial food photography showing a red Lay’s snack packet torn open from the top, positioned at the bottom center of the frame. Golden ridged potato chips are explosively bursting upward in frozen mid-air motion. Thick red tomato sauce splashes dynamically around the chips, forming arcs and droplets. Fresh whole tomatoes and halved tomatoes with visible seeds are flying around. Small crispy crumbs and seasoning particles are suspended in the air. The Lay’s logo is clearly visible on the packet, with readable text: 'Spanish Tomato Tango Flavour'. The packet surface is glossy and reflective with realistic wrinkles. Background is a deep red gradient filled with floating sauce droplets and particles, creating intense energy.\", \"lighting\": \"Dramatic warm studio lighting with strong highlights, deep shadows, and high contrast\", \"color_palette\": [\"deep red\", \"tomato red\", \"golden yellow\", \"dark orange\"], \"motion\": \"High-energy explosive upward motion with frozen splashes and flying fragments\", \"focus\": \"Ultra-sharp focus on chips, sauce splashes, and packet branding\", \"texture_detail\": \"Highly detailed ridged chip texture, glossy liquid splashes, realistic foil reflections\", \"style\": \"Premium FMCG commercial advertising, cinematic realism\", \"resolution\": \"8K\", \"aspect_ratio\": \"3:4\" }"
}
JSON
Generate a whimsical miniature world featuring [LANDMARK NAME] crafted entirely from colorful modeling clay. Every element - buildings, trees, waterways, and urban features - should appear hand-sculpted with visible fingerprints and organic clay textures. Use a playful, childlike style with vibrant colors: bright azure sky, puffy cream clouds, emerald trees, and buildings in warm yellows, oranges, reds, and blues. The handmade quality should be evident in every surface and gentle curve. Capture from a wide perspective showcasing the entire miniature landscape in a harmonious, joyful composition. Include no text, words, or signage - only sculptural clay elements that define the location through recognizable architectural features
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": "Generate a whimsical miniature world featuring [LANDMARK NAME] crafted entirely from colorful modeling clay. Every element - buildings, trees, waterways, and urban features - should appear hand-sculpted with visible fingerprints and organic clay textures. Use a playful, childlike style with vibrant colors: bright azure sky, puffy cream clouds, emerald trees, and buildings in warm yellows, oranges, reds, and blues. The handmade quality should be evident in every surface and gentle curve. Capture from a wide perspective showcasing the entire miniature landscape in a harmonious, joyful composition. Include no text, words, or signage - only sculptural clay elements that define the location through recognizable architectural features"
}
JSON
Depict [LANDMARK] frozen in an eternal state of construction. Camera & Angle (LOCKED): 45° elevated isometric view, camera distance fixed so the full landmark fills ~70% of the frame. No tilt variation. Structure: Lower sections are fully completed, solid, and instantly recognizable. Upper sections transition cleanly into unfinished construction: scaffolding, cranes, exposed beams, cables, and skeletal frameworks. The transition line between finished and unfinished is clearly visible and architecturally precise. Scale & Detail: Include small, static construction workers placed on scaffolding for scale. Include exactly 1–2 construction machines (crane arm, lift, or hoist), frozen in place. No motion, no blur, no debris falling. Materials (CONSISTENT): Finished areas: polished stone / glass / steel (appropriate to the landmark). Unfinished areas: raw concrete, steel beams, cables, structural frames. Materials are clean, realistic, and consistent across all renders. Lighting (LOCKED): Soft neutral cinematic lighting from upper left. Balanced exposure, gentle shadows, no dramatic highlights. Composition (LOCKED): Perfectly centered, symmetrical balance. Landmark sits on a subtle base or ground plane. Square format 1080×1080. Background (LOCKED): Minimal neutral sky or studio-gray backdrop. No clouds, no gradients, no distractions. Style: Hyper-realistic architectural render. Clean, precise, calm, and monumental. No stylization, no painterly effects. Mood: Timeless, quiet, contemplative. Frozen progress — never finished, never decaying.
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": "Depict [LANDMARK] frozen in an eternal state of construction. Camera & Angle (LOCKED): 45° elevated isometric view, camera distance fixed so the full landmark fills ~70% of the frame. No tilt variation. Structure: Lower sections are fully completed, solid, and instantly recognizable. Upper sections transition cleanly into unfinished construction: scaffolding, cranes, exposed beams, cables, and skeletal frameworks. The transition line between finished and unfinished is clearly visible and architecturally precise. Scale & Detail: Include small, static construction workers placed on scaffolding for scale. Include exactly 1–2 construction machines (crane arm, lift, or hoist), frozen in place. No motion, no blur, no debris falling. Materials (CONSISTENT): Finished areas: polished stone / glass / steel (appropriate to the landmark). Unfinished areas: raw concrete, steel beams, cables, structural frames. Materials are clean, realistic, and consistent across all renders. Lighting (LOCKED): Soft neutral cinematic lighting from upper left. Balanced exposure, gentle shadows, no dramatic highlights. Composition (LOCKED): Perfectly centered, symmetrical balance. Landmark sits on a subtle base or ground plane. Square format 1080×1080. Background (LOCKED): Minimal neutral sky or studio-gray backdrop. No clouds, no gradients, no distractions. Style: Hyper-realistic architectural render. Clean, precise, calm, and monumental. No stylization, no painterly effects. Mood: Timeless, quiet, contemplative. Frozen progress — never finished, never decaying."
}
JSON