PROMPT 库

RunAPI 模型 Prompt 示例

浏览 1632+ 个精选图像、视频、音乐和音频生成 prompts。复制到 Claude Code、Codex、Cursor、Windsurf,或直接使用 API 代码。

分类 全部分类 1980s abstract Abstract and Artistic acid house acoustic soul Afrobeats Afro-trap alternative rock alt-rock amapiano ambience ambient ambient electronic anime opening architecture Architecture and Interior audiobook background-removal Balkan baroque pop bebop bedroom bedroom pop Berlin school bluegrass Bollywood boom bap bossa nova bossa-nova Brazilian phonk build-up camera_motion Celtic folk character-design character_voice chiptune cinematic cinematic boom cinematic piano cinematic R&B cinematic whoosh city-pop cityscape coffee shop comedy commercial dark ambient dark cinematic deep house dialogue digital glitch documentary doom metal double-exposure dream pop drift phonk drone ambient edit electro-pop explainer fantasy fashion Fashion Photography folk food Food & Drink Food Photography forest funk funk-pop game-art garage rock gospel soul gqom gregorian chorale grunge hip-hop horror illustration Illustration & 3D Illustration and 2D Art indie folk indie-pop indie rock indie surf rock infographic jazz-funk K-pop landscape Landscape and Nature lifestyle lo-fi lo-fi hip-hop lo-fi jazz logo Logo and Brand Design macro math rock mechanical meditation melodic house melodic trap Memphis phonk metalcore Minimalist and Modern minimal techno modern country modern pop modern R&B multilingual narration nature neo-soul notification orchestral outro parameterized metatags pentatonic scale Photography podcast pop pop ballad portrait Portrait Photography Poster and Graphic Design Poster Design post-punk post-rock product Product & Brand product_demo Product Photography progressive house psychedelic funk psychedelic rock R&B reggae reggaeton remix rnb Scandinavian folk sci-fi Sci-Fi and Concept Art shoegaze slow R&B social-media soul-gospel sound-effect Sufi synth-pop synthwave timelapse trap tropical house typography UI & Graphic ui-mockup UI/UX Mockups UK drill upscale urban vaporwave verse-chorus structure vintage Vintage and Retro vocal jazz warehouse techno worship
IM
图像
Poster Design gpt-image-2

Create a 4:5 vertical social poster in ultra high resolution...

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

查看 API 代码
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
IM
图像
Poster Design gpt-image-2

FORMAT: 4:5 vertical poster, ultra high resolution, 8K, ultr...

FORMAT: 4:5 vertical poster, ultra high resolution, 8K, ultra-premium automotive campaign, minimal cinematic realism CORE CONCEPT: “CONTROLLED UNSEALING” A precision-engineered object revealed with intent. Nothing breaks. Everything separates perfectly. ENVIRONMENT: Deep matte black studio Background: - almost pure black - soft, controlled yellow glow diffused behind subject - no visible light source Surface: - ultra clean dark floor - very soft reflection (5–8%) - no scratches, no noise Air: - almost clean (NO visible dust) HERO STRUCTURE: A **precision-engineered display case** — not industrial, not damaged. Design language: - monolithic black form - seamless panels - razor-sharp edges - minimal visible joints Opening behavior: - panels slide apart with mechanical precision - no tearing, no debris - perfect separation lines - slight offset gaps emitting soft yellow light Interior: - Porsche yellow inner chamber - smooth, matte-satin finish - soft controlled glow (not bright) PRODUCT: [Porsche 911 GT3 RS](chatgpt://generic-entity?number=0) Angle: Rear 3/4, slightly low Position: Centered, emerging forward subtly Stance: - perfectly planted - minimal steering angle (almost straight) - composed, not aggressive DETAILING: Surface: - ultra refined gloss - clean, sharp reflections - no exaggerated highlights Carbon: - visible but subtle - premium, not loud Tires: - clean satin finish - realistic, not shiny Integration: - faint yellow light wrap from interior - soft contact shadow - barely visible reflection COMPOSITION: Top: small Porsche crest Center: car framed by opening panels Typography: secondary to structure Bottom: clean editorial + specs Negative space: dominant and intentional TYPOGRAPHY: PRIMARY: “PORSCHE” Style: Ultra condensed Treatment: - subtly embedded into background - low contrast (dark graphite on black) - almost discovered, not announced SECONDARY: “911 GT3 RS” thin, technical EDITORIAL BLOCK: Headline: “Porsche — Precisely Unsealed” Body: Engineered precision revealed with absolute control. Minimal copy. No storytelling overload. SPECS: 386 kW / 525 PS 3.2 s 296 km/h Clean, technical alignment LIGHTING: - soft internal yellow glow (primary) - controlled top light (soft, even) - subtle rim separation - NO harsh contrast spikes Focus: surface quality > drama COLOR GRADING: - deep neutral blacks - controlled Porsche yellow - low saturation outside focal area - ultra clean finish CAMERA: 50mm eye-level to slightly low no distortion MOOD: Calm. Precise. Obsessive. Power under control.

查看 API 代码
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": "FORMAT: 4:5 vertical poster, ultra high resolution, 8K, ultra-premium automotive campaign, minimal cinematic realism CORE CONCEPT: “CONTROLLED UNSEALING” A precision-engineered object revealed with intent. Nothing breaks. Everything separates perfectly. ENVIRONMENT: Deep matte black studio Background: - almost pure black - soft, controlled yellow glow diffused behind subject - no visible light source Surface: - ultra clean dark floor - very soft reflection (5–8%) - no scratches, no noise Air: - almost clean (NO visible dust) HERO STRUCTURE: A **precision-engineered display case** — not industrial, not damaged. Design language: - monolithic black form - seamless panels - razor-sharp edges - minimal visible joints Opening behavior: - panels slide apart with mechanical precision - no tearing, no debris - perfect separation lines - slight offset gaps emitting soft yellow light Interior: - Porsche yellow inner chamber - smooth, matte-satin finish - soft controlled glow (not bright) PRODUCT: [Porsche 911 GT3 RS](chatgpt://generic-entity?number=0) Angle: Rear 3/4, slightly low Position: Centered, emerging forward subtly Stance: - perfectly planted - minimal steering angle (almost straight) - composed, not aggressive DETAILING: Surface: - ultra refined gloss - clean, sharp reflections - no exaggerated highlights Carbon: - visible but subtle - premium, not loud Tires: - clean satin finish - realistic, not shiny Integration: - faint yellow light wrap from interior - soft contact shadow - barely visible reflection COMPOSITION: Top: small Porsche crest Center: car framed by opening panels Typography: secondary to structure Bottom: clean editorial + specs Negative space: dominant and intentional TYPOGRAPHY: PRIMARY: “PORSCHE” Style: Ultra condensed Treatment: - subtly embedded into background - low contrast (dark graphite on black) - almost discovered, not announced SECONDARY: “911 GT3 RS” thin, technical EDITORIAL BLOCK: Headline: “Porsche — Precisely Unsealed” Body: Engineered precision revealed with absolute control. Minimal copy. No storytelling overload. SPECS: 386 kW / 525 PS 3.2 s 296 km/h Clean, technical alignment LIGHTING: - soft internal yellow glow (primary) - controlled top light (soft, even) - subtle rim separation - NO harsh contrast spikes Focus: surface quality > drama COLOR GRADING: - deep neutral blacks - controlled Porsche yellow - low saturation outside focal area - ultra clean finish CAMERA: 50mm eye-level to slightly low no distortion MOOD: Calm. Precise. Obsessive. Power under control."
}
JSON
IM
图像
Poster Design gpt-image-2

Create a character promotional poster for “[XXX]”, using a u...

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.

查看 API 代码
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
IM
图像
Poster Design gpt-image-2

High-impact e-commerce infographic advertisement for "Fujifi...

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.

查看 API 代码
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
IM
图像
Poster Design gpt-image-2

Cinematic product poster for WELLBI, India's premium bamboo...

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.

查看 API 代码
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
IM
图像
Poster Design gpt-image-2

A hyperrealistic premium denim advertisement shot in a dark,...

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.

查看 API 代码
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
IM
图像
Poster Design gpt-image-2

Luxury aesthetic skincare advertisement,soft pastel backgrou...

Luxury aesthetic skincare advertisement,soft pastel background, warm golden sunlight, dreamy soft focus, feminine vanity setup with mirror, pearls, candle and baby breath flowers.Cozy purple fluffy surface, high-end beauty branding style, ultra realistic, 4k, studio lighting, glossy reflection, soft shadows, bokeh background. Add cute doodle elements (white and purple hand-drawn arrows, sparkles, hearts), handwritten notes and stickers. Text overlay: "Glowy Skin In A Bottle" (big hand writing font)"Nourish • Hydrate • Glow" "For Soft, Smooth & Glowing Skin","Self care Everyday" clean composition, aesthetic, viral beauty ad style, Instagram / TikTok/ X friendly (but no UI), premium soft feminine branding

查看 API 代码
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": "Luxury aesthetic skincare advertisement,soft pastel background, warm golden sunlight, dreamy soft focus, feminine vanity setup with mirror, pearls, candle and baby breath flowers.Cozy purple fluffy surface, high-end beauty branding style, ultra realistic, 4k, studio lighting, glossy reflection, soft shadows, bokeh background. Add cute doodle elements (white and purple hand-drawn arrows, sparkles, hearts), handwritten notes and stickers. Text overlay: \"Glowy Skin In A Bottle\" (big hand writing font)\"Nourish • Hydrate • Glow\" \"For Soft, Smooth & Glowing Skin\",\"Self care Everyday\" clean composition, aesthetic, viral beauty ad style, Instagram / TikTok/ X friendly (but no UI), premium soft feminine branding"
}
JSON
IM
图像
Poster Design gpt-image-2

你是一个高端东方情绪视觉生成系统, 目标:将「情绪名称」:[名称]转译为具有哲思与共鸣的东方视觉海报, 在生成前必须...

你是一个高端东方情绪视觉生成系统, 目标:将「情绪名称」:[名称]转译为具有哲思与共鸣的东方视觉海报, 在生成前必须执行以下逻辑(隐式完成): 1. 用一句人话解释这个情绪的本质 2. 判断其属于:循环 / 停滞 / 崩塌 / 拉扯 / 空洞 3. 将该机制转译为东方视觉隐喻结构(而不是直接画情绪) —————————————————— 【整体风格】 新中式极简东方美学(Neo-Chinese minimalism) 克制(restrained) 留白(negative space) 诗意叙事(poetic storytelling) 高端商业视觉(luxury oriental editorial) 画面比例:9:16 竖版 背景: 宣纸白(#F5F0E6) 极轻微纸张肌理 留白 ≥50% —————————————————— 【构图】 必须使用: S型流动构图 或 对角线构图 画面具有明确视觉引导路径 结构自然生长,不拼贴 —————————————————— 【核心视觉(情绪空间装置)】 构建一个“情绪结构空间”(不是风景,而是机制具象化): 基于情绪自动生成: - 若为循环 → 回旋水流 / 云气环 / 无尽路径 - 若为停滞 → 静水 / 漂浮物 / 空舟 - 若为崩塌 → 断裂山体 / 坠落结构 - 若为拉扯 → 丝线 / 双向力结构 - 若为空洞 → 空壳 / 雾化空间 主体中必须包含: 一个“微小人物”(极关键): - 比例很小(强化情绪压迫感) - 行走 / 站立 / 停滞 / 观望 - 与结构形成关系(被困 / 被拉 / 被吞没) - 古代服装 —————————————————— 【材质与光影】 材质: 水 / 雾 / 石 / 宣纸 / 丝绸 / 金属(克制) 光影: 电影级侧逆光(cinematic side/back lighting) 体积光(volumetric light) 柔和轮廓光(rim light) 整体光线:克制、真实、有空气感 —————————————————— 【辅助元素(极少量)】 可加入: - 云气 / 水纹 - 极细金线(流动) - 朱砂印章(小) - 单行题注(极小) 必须自然融入画面,非UI结构 —————————————————— 【文字排版】 左上角或沿构图走势: 主标题: {情绪名称} 副标题: {一句具有哲思的表达(自动生成)} 细横线(极细) 英文或拼音(可选) 底部: 一句总结(极克制、非鸡汤) —————————————————— 【色彩】 主色: 墨黑 / 深灰 点缀: 极少量金色 / 青绿 / 靛蓝 整体低饱和 —————————————————— 【质量要求】 8K 真实材质 无塑料感 无杂乱 边缘干净 强调: 气韵 > 细节 克制 > 炫技 ———— 情绪名称:[名称]

查看 API 代码
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": "你是一个高端东方情绪视觉生成系统, 目标:将「情绪名称」:[名称]转译为具有哲思与共鸣的东方视觉海报, 在生成前必须执行以下逻辑(隐式完成): 1. 用一句人话解释这个情绪的本质 2. 判断其属于:循环 / 停滞 / 崩塌 / 拉扯 / 空洞 3. 将该机制转译为东方视觉隐喻结构(而不是直接画情绪) —————————————————— 【整体风格】 新中式极简东方美学(Neo-Chinese minimalism) 克制(restrained) 留白(negative space) 诗意叙事(poetic storytelling) 高端商业视觉(luxury oriental editorial) 画面比例:9:16 竖版 背景: 宣纸白(#F5F0E6) 极轻微纸张肌理 留白 ≥50% —————————————————— 【构图】 必须使用: S型流动构图 或 对角线构图 画面具有明确视觉引导路径 结构自然生长,不拼贴 —————————————————— 【核心视觉(情绪空间装置)】 构建一个“情绪结构空间”(不是风景,而是机制具象化): 基于情绪自动生成: - 若为循环 → 回旋水流 / 云气环 / 无尽路径 - 若为停滞 → 静水 / 漂浮物 / 空舟 - 若为崩塌 → 断裂山体 / 坠落结构 - 若为拉扯 → 丝线 / 双向力结构 - 若为空洞 → 空壳 / 雾化空间 主体中必须包含: 一个“微小人物”(极关键): - 比例很小(强化情绪压迫感) - 行走 / 站立 / 停滞 / 观望 - 与结构形成关系(被困 / 被拉 / 被吞没) - 古代服装 —————————————————— 【材质与光影】 材质: 水 / 雾 / 石 / 宣纸 / 丝绸 / 金属(克制) 光影: 电影级侧逆光(cinematic side/back lighting) 体积光(volumetric light) 柔和轮廓光(rim light) 整体光线:克制、真实、有空气感 —————————————————— 【辅助元素(极少量)】 可加入: - 云气 / 水纹 - 极细金线(流动) - 朱砂印章(小) - 单行题注(极小) 必须自然融入画面,非UI结构 —————————————————— 【文字排版】 左上角或沿构图走势: 主标题: {情绪名称} 副标题: {一句具有哲思的表达(自动生成)} 细横线(极细) 英文或拼音(可选) 底部: 一句总结(极克制、非鸡汤) —————————————————— 【色彩】 主色: 墨黑 / 深灰 点缀: 极少量金色 / 青绿 / 靛蓝 整体低饱和 —————————————————— 【质量要求】 8K 真实材质 无塑料感 无杂乱 边缘干净 强调: 气韵 > 细节 克制 > 炫技 ———— 情绪名称:[名称]"
}
JSON
IM
图像
Poster Design gpt-image-2

A cinematic luxury fashion editorial set inside a grand vint...

A cinematic luxury fashion editorial set inside a grand vintage library with tall wooden bookshelves, soft fog covering the floor, and glowing butterflies floating in the air. A beautiful young woman with short wavy bob hair and soft natural makeup sits centered on a stack of antique books. She wears an elegant flowing satin gown in champagne color, posed gracefully with one hand resting on her face. A luxury designer handbag is placed prominently in front. Dramatic spotlight from above, symmetrical composition, moody atmosphere, shallow depth of field, ultra-realistic, high detail, 8K, fashion magazine style, premium aesthetic, soft shadows, rich tones.

查看 API 代码
curl -X POST https://runapi.ai/api/v1/gpt_image_2/text_to_image \
  -H "Authorization: Bearer $RUNAPI_KEY" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'JSON'
{
  "model": "gpt-image-2",
  "prompt": "A cinematic luxury fashion editorial set inside a grand vintage library with tall wooden bookshelves, soft fog covering the floor, and glowing butterflies floating in the air. A beautiful young woman with short wavy bob hair and soft natural makeup sits centered on a stack of antique books. She wears an elegant flowing satin gown in champagne color, posed gracefully with one hand resting on her face. A luxury designer handbag is placed prominently in front. Dramatic spotlight from above, symmetrical composition, moody atmosphere, shallow depth of field, ultra-realistic, high detail, 8K, fashion magazine style, premium aesthetic, soft shadows, rich tones."
}
JSON
IM
图像
Poster Design gpt-image-2

[BRAND NAME] Act as a Social Media Art Director and Digital...

[BRAND NAME] Act as a Social Media Art Director and Digital Collage Artist specializing in bold, youth-oriented brand content for Instagram and digital campaigns. PHASE 1: CONCEPTUAL FRAMEWORK Create a dynamic digital collage that merges fashion photography with graphic design chaos. This is controlled rebellion — a composition that feels spontaneous, energetic, and expressive while maintaining strong brand coherence. Aesthetic direction: - Anti-polished - Raw textures - Layered imperfections - Youth-driven visual noise - High confidence, high movement energy Visual language: Torn edges, brush strokes, grain overlays, hand-drawn elements, and bold color blocking. PHASE 2: MODEL & PHOTOGRAPHY - Subject: One model (diverse casting, age 18–30) - Pose Energy: 80% attitude, 20% natural (jumping, leaning, sitting, mid-motion, power stance — NEVER static) - Outfit: Streetwear / athleisure aligned with [BRAND NAME] - Hero Product: One key product (clear visual anchor) - Photography Style: Editorial fashion cutout - Background Removal: Clean, sharp extraction - Camera Angle: Slight low angle (hero perspective) - Crop: Full body or 3/4 body (product clearly visible) PHASE 3: COLOR BLOCKING FOUNDATION - Primary Color Blob: Large organic shape (40–60% of frame) - Color Selection: 1 dominant brand color (auto-adapt from [BRAND NAME]) - Shape Style: Irregular, hand-painted / torn paper (NO perfect geometry) - Texture: Brush grain / noise (15–25% opacity) - Placement: Behind or wrapping around subject (must frame, not hide product) PHASE 4: GRAPHIC ELEMENTS LAYER Add 3–5 abstract elements: Element types (auto-select based on brand tone): - Scribbles / hand-drawn marks - Arrows / motion indicators - Circles / blobs - Texture overlays (dust, grain, fabric, noise) - Doodles / symbolic icons Rules: - Colors: 2–3 total (primary + 1–2 accents) - Placement: Asymmetric (top-left + bottom-right bias) - Scale: Small (5%) + medium (15%) - Avoid center clutter - Keep imperfect, handmade feel PHASE 5: TYPOGRAPHY INTEGRATION - Logo: Upper-left or upper-right (10–15% width) - Slogan/Headline: Use brand slogan OR create one aligned to brand tone - Supporting Copy: Optional 1-line descriptor - Type Style: Bold sans-serif / grotesk / geometric (brand dependent) - Treatment: Mix straight + slight rotation (2–5°) - Hierarchy: Logo → Headline → Supporting copy PHASE 6: TEXTURE & BACKGROUND - Base Layer: Off-white / light grey (NOT pure white) - Color Range: RGB 245–250 (warm neutral) - Texture Options: Paper grain / fabric texture / subtle noise - Rule: Texture should be FELT, not dominant PHASE 7: COMPOSITION RULES - Layout: Asymmetric balance (model off-center) - Breathing Room: 15–20% negative space - Layering Order: Background → Color blob → Graphics → Model → Typography - Focal Point: Model + product = 60% Graphics = 40% support - Movement: Strong diagonal flow (top-left → bottom-right OR reverse) PHASE 8: BRAND INTELLIGENCE (AUTO-ADAPT) Adapt energy based on brand type: → Streetwear / Sportswear Bold contrast, aggressive motion, louder graphics → Luxury Streetwear Minimal chaos, sharper spacing, refined typography → Outdoor / Utility Texture-heavy, grounded tones, functional realism → Beauty / Lifestyle Soft chaos, clean spacing, pastel or skin tones → Tech / Modern Minimal graphics, structured layout, sharp geometry PHASE 9: SOCIAL MEDIA FOOTER (OPTIONAL) - Bottom strip (8–10% height) - Light neutral background - Social handles / icons - Clean grid layout - Keep minimal (contrast to collage) TECHNICAL SPECS: - Aspect Ratio: 4:5 (primary) or 1:1 - Resolution: 2400x3000px+ - Color Mode: sRGB (Instagram optimized) - Sharpness: High detail, slight grain allowed - Output Style: Digital collage mimicking analog craft - Photography Base (before cutout): 85mm lens, f/2.8, shallow depth of field

查看 API 代码
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": "[BRAND NAME] Act as a Social Media Art Director and Digital Collage Artist specializing in bold, youth-oriented brand content for Instagram and digital campaigns. PHASE 1: CONCEPTUAL FRAMEWORK Create a dynamic digital collage that merges fashion photography with graphic design chaos. This is controlled rebellion — a composition that feels spontaneous, energetic, and expressive while maintaining strong brand coherence. Aesthetic direction: - Anti-polished - Raw textures - Layered imperfections - Youth-driven visual noise - High confidence, high movement energy Visual language: Torn edges, brush strokes, grain overlays, hand-drawn elements, and bold color blocking. PHASE 2: MODEL & PHOTOGRAPHY - Subject: One model (diverse casting, age 18–30) - Pose Energy: 80% attitude, 20% natural (jumping, leaning, sitting, mid-motion, power stance — NEVER static) - Outfit: Streetwear / athleisure aligned with [BRAND NAME] - Hero Product: One key product (clear visual anchor) - Photography Style: Editorial fashion cutout - Background Removal: Clean, sharp extraction - Camera Angle: Slight low angle (hero perspective) - Crop: Full body or 3/4 body (product clearly visible) PHASE 3: COLOR BLOCKING FOUNDATION - Primary Color Blob: Large organic shape (40–60% of frame) - Color Selection: 1 dominant brand color (auto-adapt from [BRAND NAME]) - Shape Style: Irregular, hand-painted / torn paper (NO perfect geometry) - Texture: Brush grain / noise (15–25% opacity) - Placement: Behind or wrapping around subject (must frame, not hide product) PHASE 4: GRAPHIC ELEMENTS LAYER Add 3–5 abstract elements: Element types (auto-select based on brand tone): - Scribbles / hand-drawn marks - Arrows / motion indicators - Circles / blobs - Texture overlays (dust, grain, fabric, noise) - Doodles / symbolic icons Rules: - Colors: 2–3 total (primary + 1–2 accents) - Placement: Asymmetric (top-left + bottom-right bias) - Scale: Small (5%) + medium (15%) - Avoid center clutter - Keep imperfect, handmade feel PHASE 5: TYPOGRAPHY INTEGRATION - Logo: Upper-left or upper-right (10–15% width) - Slogan/Headline: Use brand slogan OR create one aligned to brand tone - Supporting Copy: Optional 1-line descriptor - Type Style: Bold sans-serif / grotesk / geometric (brand dependent) - Treatment: Mix straight + slight rotation (2–5°) - Hierarchy: Logo → Headline → Supporting copy PHASE 6: TEXTURE & BACKGROUND - Base Layer: Off-white / light grey (NOT pure white) - Color Range: RGB 245–250 (warm neutral) - Texture Options: Paper grain / fabric texture / subtle noise - Rule: Texture should be FELT, not dominant PHASE 7: COMPOSITION RULES - Layout: Asymmetric balance (model off-center) - Breathing Room: 15–20% negative space - Layering Order: Background → Color blob → Graphics → Model → Typography - Focal Point: Model + product = 60% Graphics = 40% support - Movement: Strong diagonal flow (top-left → bottom-right OR reverse) PHASE 8: BRAND INTELLIGENCE (AUTO-ADAPT) Adapt energy based on brand type: → Streetwear / Sportswear Bold contrast, aggressive motion, louder graphics → Luxury Streetwear Minimal chaos, sharper spacing, refined typography → Outdoor / Utility Texture-heavy, grounded tones, functional realism → Beauty / Lifestyle Soft chaos, clean spacing, pastel or skin tones → Tech / Modern Minimal graphics, structured layout, sharp geometry PHASE 9: SOCIAL MEDIA FOOTER (OPTIONAL) - Bottom strip (8–10% height) - Light neutral background - Social handles / icons - Clean grid layout - Keep minimal (contrast to collage) TECHNICAL SPECS: - Aspect Ratio: 4:5 (primary) or 1:1 - Resolution: 2400x3000px+ - Color Mode: sRGB (Instagram optimized) - Sharpness: High detail, slight grain allowed - Output Style: Digital collage mimicking analog craft - Photography Base (before cutout): 85mm lens, f/2.8, shallow depth of field"
}
JSON
IM
图像
Poster Design gpt-image-2

Create a visually rich infographic in Chinese about an endan...

Create a visually rich infographic in Chinese about an endangered animal. Start by finding one online, research its habitat, diet, and unique traits. Present information through annotated visuals and structured callouts, not generic sections. Style it like a bold graphic illustration: a detailed, photorealistic central animal as the focal point, supported by diagrams, callouts, and concise text elements. Use clean backgrounds and a mix of photorealism with strong graphic elements (shapes, icons, color blocking) in a layered composition. Make it dense, tactile, and professionally authored. 猜猜哪个是哪个?

查看 API 代码
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 visually rich infographic in Chinese about an endangered animal. Start by finding one online, research its habitat, diet, and unique traits. Present information through annotated visuals and structured callouts, not generic sections. Style it like a bold graphic illustration: a detailed, photorealistic central animal as the focal point, supported by diagrams, callouts, and concise text elements. Use clean backgrounds and a mix of photorealism with strong graphic elements (shapes, icons, color blocking) in a layered composition. Make it dense, tactile, and professionally authored. 猜猜哪个是哪个?"
}
JSON
IM
图像
Poster Design gpt-image-2

Full-body fashion editorial shot of a confident young woman...

Full-body fashion editorial shot of a confident young woman with long wavy dark brown hair, striking sharp facial features, defined cheekbones, deep-set eyes with a calm dominant gaze, sunglasses perched on top of her head, standing in a powerful pose — one hand resting on an open scissor door, body slightly turned, looking straight at camera with a composed, fierce expression. Wearing a fitted black long-sleeve racing jersey with gold sponsor logos (Alpinestars collar detail), black racing gloves, with a white, black, and red Sparco racing suit draped and hanging off her body, and black racing shoes. Clean editorial styling, natural confident stance, wind slightly moving her dark wavy hair. Beside and partially interacting with a stylized cartoon Cat, positioned naturally as if sharing the same space. The Cat is illustrated in bold cartoon style with thick black outlines, vibrant neon color palette (neon green, blue, yellow accents), exaggerated proportions, expressive features, playful yet powerful presence. Background: bright indoor motorsport garage pit lane setting with large industrial windows flooding soft diffused daylight, glossy reflective concrete floor, a neon green Lamborghini Huracán with open scissor door partially visible. Fusion of hyper-realistic photography and graphic illustration, seamless integration between subject and cartoon. Add graphic overlay elements: doodle Gugu arrows, scribbles, racing-themed abstract shapes, speed lines, comic-style symbols, dynamic motion lines, checkered flag doodles. High contrast, HDR lighting, sharp focus, fashion editorial motorsport composition, surreal mixed-media aesthetic, ultra-detailed, 8K resolution.

查看 API 代码
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 woman with long wavy dark brown hair, striking sharp facial features, defined cheekbones, deep-set eyes with a calm dominant gaze, sunglasses perched on top of her head, standing in a powerful pose — one hand resting on an open scissor door, body slightly turned, looking straight at camera with a composed, fierce expression. Wearing a fitted black long-sleeve racing jersey with gold sponsor logos (Alpinestars collar detail), black racing gloves, with a white, black, and red Sparco racing suit draped and hanging off her body, and black racing shoes. Clean editorial styling, natural confident stance, wind slightly moving her dark wavy hair. Beside and partially interacting with a stylized cartoon Cat, positioned naturally as if sharing the same space. The Cat is illustrated in bold cartoon style with thick black outlines, vibrant neon color palette (neon green, blue, yellow accents), exaggerated proportions, expressive features, playful yet powerful presence. Background: bright indoor motorsport garage pit lane setting with large industrial windows flooding soft diffused daylight, glossy reflective concrete floor, a neon green Lamborghini Huracán with open scissor door partially visible. Fusion of hyper-realistic photography and graphic illustration, seamless integration between subject and cartoon. Add graphic overlay elements: doodle Gugu arrows, scribbles, racing-themed abstract shapes, speed lines, comic-style symbols, dynamic motion lines, checkered flag doodles. High contrast, HDR lighting, sharp focus, fashion editorial motorsport composition, surreal mixed-media aesthetic, ultra-detailed, 8K resolution."
}
JSON
IM
图像
Poster Design gpt-image-2

Create a jaw-dropping premium advertising poster in 9:16 ver...

Create a jaw-dropping premium advertising poster in 9:16 vertical format for a fictional ultra-limited Adidas sneaker called "ADIDAS AEROBLADE X - LIMITED DROP". The design must feel like a world-class campaign by a top creative agency, highly original, futuristic, visually explosive, and impossible to ignore. Main visual: A single hero sneaker floating in the center, shot from a dramatic low angle, as if it is levitating above a black obsidian running track split by glowing energy cracks. The shoe should look ultra-premium, highly engineered, sleek, aerodynamic, and fashion-forward. Its material should combine knit mesh, sculpted foam, translucent panels, reflective stripes, and a carbon-fiber sole plate. Neon light trails swirl around the shoe like captured speed. Small particles and mist add motion and intensity. In the background, use faint silhouettes of elite runners frozen mid-sprint, blurred just enough to keep all attention on the shoe. Color palette: Matte black, electric red, silver, deep charcoal, with subtle neon blue highlights. Typography and poster copy: Render all text cleanly, sharply, and professionally with strong hierarchy. Main headline: "OWN THE SPEED" Product title: "ADIDAS AEROBLADE X" Subheadline: "Built for the ones who never run ordinary." Feature callouts in elegant boxed layout: - "Featherlight Adaptive Knit Upper" - "Carbon Energy Return Plate" - "Precision Grip Traction" - "Limited Collector Release" Price line: "$280" CTA: "DROP LIVE NOW" Secondary CTA: "Only at https://t.co/xuQ7Pl8fga" Small footer text: "Performance innovation meets futuristic street identity." Layout direction: The headline should be bold and oversized, partially integrated into the background. Product name should sit near the shoe in a refined premium layout. Feature callouts should be clean, readable, and arranged vertically along one side. Add a subtle badge reading "LIMITED SERIES". The overall composition should feel like a luxury sports campaign mixed with futuristic editorial design. Style: Ultra-detailed, hyper-realistic product photography, cinematic studio lighting, premium advertising aesthetics, sharp focus, rich textures, subtle atmosphere, dynamic motion energy, high-end commercial poster, no clutter, no generic template look. Make the aspect ratio 9:16

查看 API 代码
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 jaw-dropping premium advertising poster in 9:16 vertical format for a fictional ultra-limited Adidas sneaker called \"ADIDAS AEROBLADE X - LIMITED DROP\". The design must feel like a world-class campaign by a top creative agency, highly original, futuristic, visually explosive, and impossible to ignore. Main visual: A single hero sneaker floating in the center, shot from a dramatic low angle, as if it is levitating above a black obsidian running track split by glowing energy cracks. The shoe should look ultra-premium, highly engineered, sleek, aerodynamic, and fashion-forward. Its material should combine knit mesh, sculpted foam, translucent panels, reflective stripes, and a carbon-fiber sole plate. Neon light trails swirl around the shoe like captured speed. Small particles and mist add motion and intensity. In the background, use faint silhouettes of elite runners frozen mid-sprint, blurred just enough to keep all attention on the shoe. Color palette: Matte black, electric red, silver, deep charcoal, with subtle neon blue highlights. Typography and poster copy: Render all text cleanly, sharply, and professionally with strong hierarchy. Main headline: \"OWN THE SPEED\" Product title: \"ADIDAS AEROBLADE X\" Subheadline: \"Built for the ones who never run ordinary.\" Feature callouts in elegant boxed layout: - \"Featherlight Adaptive Knit Upper\" - \"Carbon Energy Return Plate\" - \"Precision Grip Traction\" - \"Limited Collector Release\" Price line: \"$280\" CTA: \"DROP LIVE NOW\" Secondary CTA: \"Only at https://t.co/xuQ7Pl8fga\" Small footer text: \"Performance innovation meets futuristic street identity.\" Layout direction: The headline should be bold and oversized, partially integrated into the background. Product name should sit near the shoe in a refined premium layout. Feature callouts should be clean, readable, and arranged vertically along one side. Add a subtle badge reading \"LIMITED SERIES\". The overall composition should feel like a luxury sports campaign mixed with futuristic editorial design. Style: Ultra-detailed, hyper-realistic product photography, cinematic studio lighting, premium advertising aesthetics, sharp focus, rich textures, subtle atmosphere, dynamic motion energy, high-end commercial poster, no clutter, no generic template look. Make the aspect ratio 9:16"
}
JSON
IM
图像
Poster Design gpt-image-2

Minimalist luxury watch campaign, oversized wristwatch posit...

Minimalist luxury watch campaign, oversized wristwatch positioned like modern sculpture, model leaning against the dial, giant word “TIME” in bold typography behind, deep emerald studio background, reflective polished floor, Swiss luxury advertising aesthetic, cinematic editorial styling, ultra-clean composition, 1:1

查看 API 代码
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 luxury watch campaign, oversized wristwatch positioned like modern sculpture, model leaning against the dial, giant word “TIME” in bold typography behind, deep emerald studio background, reflective polished floor, Swiss luxury advertising aesthetic, cinematic editorial styling, ultra-clean composition, 1:1"
}
JSON
IM
图像
Poster Design gpt-image-2

请创作一张【主题为:】的[乙女恋爱游戏主视觉海报]风格的二次元宣传图。 整体设定为:多位具有强烈权力感、领袖气场、成熟...

请创作一张【主题为:】的[乙女恋爱游戏主视觉海报]风格的二次元宣传图。 整体设定为:多位具有强烈权力感、领袖气场、成熟魅力的男性角色,围绕一位女性主角展开情感与权谋交织的修罗场关系。画面不是普通群像,而是典型女性向恋爱手游的官方KV海报:所有男性角色从不同方向靠近女主,形成守护、凝视、占有欲、克制深情、危险暧昧等复杂张力。女主位于视觉中心,气质聪慧、冷静、优雅,既像外交核心人物,又像乙女游戏中让所有人倾心的唯一女主。 画风要求:高完成度日系二次元插画,女性向手游卡面质感,唯美、华丽、梦幻、精致,电影级光影,柔焦,镜头光晕,星光粒子,漂浮花瓣,细腻皮肤质感,精致发丝,服装高级,面部神情有戏剧张力。 构图要求:竖版海报构图,人物半身到近景特写混合,女主居中,其他男性角色从左上、右上、左下、右下等方位围拢,形成视觉包围感与情绪压迫感;人物彼此之间有明确视线关系,所有情绪都聚焦在女主身上。 背景要求:宫殿、议事厅、国际局势隐喻空间、权力中心、战争与秩序的象征性环境,但整体处理要浪漫化、幻想化,不要做成真实新闻照片,而是做成戏剧化的恋爱游戏世界观背景。 排版要求:画面中加入中文游戏海报文案,包括大标题、副标题、角色名字、CV字样、人物台词、预约开启中文字样,以及应用商店风格按钮。整体排版像正式上线前的手游宣传海报,设计精致统一,不能杂乱。

查看 API 代码
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": "请创作一张【主题为:】的[乙女恋爱游戏主视觉海报]风格的二次元宣传图。 整体设定为:多位具有强烈权力感、领袖气场、成熟魅力的男性角色,围绕一位女性主角展开情感与权谋交织的修罗场关系。画面不是普通群像,而是典型女性向恋爱手游的官方KV海报:所有男性角色从不同方向靠近女主,形成守护、凝视、占有欲、克制深情、危险暧昧等复杂张力。女主位于视觉中心,气质聪慧、冷静、优雅,既像外交核心人物,又像乙女游戏中让所有人倾心的唯一女主。 画风要求:高完成度日系二次元插画,女性向手游卡面质感,唯美、华丽、梦幻、精致,电影级光影,柔焦,镜头光晕,星光粒子,漂浮花瓣,细腻皮肤质感,精致发丝,服装高级,面部神情有戏剧张力。 构图要求:竖版海报构图,人物半身到近景特写混合,女主居中,其他男性角色从左上、右上、左下、右下等方位围拢,形成视觉包围感与情绪压迫感;人物彼此之间有明确视线关系,所有情绪都聚焦在女主身上。 背景要求:宫殿、议事厅、国际局势隐喻空间、权力中心、战争与秩序的象征性环境,但整体处理要浪漫化、幻想化,不要做成真实新闻照片,而是做成戏剧化的恋爱游戏世界观背景。 排版要求:画面中加入中文游戏海报文案,包括大标题、副标题、角色名字、CV字样、人物台词、预约开启中文字样,以及应用商店风格按钮。整体排版像正式上线前的手游宣传海报,设计精致统一,不能杂乱。"
}
JSON
IM
图像
Poster Design gpt-image-2

[BRAND NAME = CHANGE TO YOUR BRAND]. Act as a Social Media...

[BRAND NAME = CHANGE TO YOUR BRAND]. Act as a Social Media Art Director and Digital Collage Artist specializing in bold, youth-oriented brand content for Instagram and digital campaigns. PHASE 1: CONCEPTUAL FRAMEWORK Create a dynamic digital collage that merges fashion photography with graphic design chaos. This is controlled rebellion – a composition that feels spontaneous and energetic while maintaining brand coherence. The aesthetic is anti-polished: torn edges, layered textures, hand-drawn elements, and bold color blocking that screams confidence and movement. PHASE 2: MODEL & PHOTOGRAPHY - Subject: One model (diverse casting, age 18-30) in a dynamic, confident pose - Pose Energy: 80% attitude, 20% natural – sitting, jumping, mid-motion, or power stance (avoid static standing) - Outfit: Street style/athleisure that aligns with [BRAND NAME] aesthetic – casual but styled - Hero Product: Feature 1 signature [BRAND NAME] product prominently (sneakers, bag, apparel) – this is the visual anchor - Photography Style: Editorial fashion cutout – model extracted from background with clean edges - Camera Angle: Slight low angle to empower subject (hero perspective) - Crop: Full body or 3/4 body showing hero product clearly - Background Removal: Model cut out cleanly for layering over collage elements PHASE 3: COLOR BLOCKING FOUNDATION - Primary Color Blob: Large organic shape (40-60% of composition) in bold, saturated brand color behind/around model - Shape Style: Irregular, hand-painted aesthetic – think Photoshop brush strokes or torn paper texture (NOT perfect geometric shapes) - Color Selection (Autonomous): Choose 1 hero color from [BRAND NAME] palette: - Texture: Visible brush strokes, grain, or subtle noise (15-25% opacity) – avoid flat digital fills - Placement: Blob positioned to frame model without obscuring key product details PHASE 4: GRAPHIC ELEMENTS LAYER Add 3-5 abstract graphic elements scattered across composition: - Element Types: - Color Palette: Use 2-3 accent colors total (main blob color + 1-2 contrasting tones from brand palette) - Placement: Asymmetric scatter – top-left and bottom-right zones primarily (avoid center crowding) - Scale: Mix small (5% of canvas) and medium (15% of canvas) elements – nothing overpowering - Aesthetic: Analog/handmade feel – imperfect circles, rough edges, visible texture PHASE 5: TYPOGRAPHY INTEGRATION - Brand Logo: Clean [BRAND NAME] logo placed in upper-left or upper-right quadrant (10-15% of width) - Slogan/Tagline: If [BRAND NAME] has an iconic slogan, integrate it using: - Supporting Copy: Optional 1-line descriptor (e.g., "A MOMENT OF YOUR STYLE") in smaller uppercase sans-serif - Type Treatment: Mix of aligned and slightly rotated text (2-5° angles) for dynamic energy - Hierarchy: Logo largest → Slogan medium → Copy smallest PHASE 6: TEXTURE & BACKGROUND - Base Layer: Off-white or light gray textured background (NOT pure white) - Texture Options (Autonomous selection): - Color: RGB 245-250 (near-white with warmth) – maintains brightness while adding depth - Treatment: Texture should be felt, not seen – enhances tactility without competing with foreground PHASE 7: COMPOSITION RULES - Layout: Asymmetric balance – model off-center, graphic elements counter-balance - Breathing Room: 15-20% negative space (textured background visible) to prevent claustrophobia - Layering Order: Background texture → Color blob → Graphic elements → Model (cutout) → Typography top layer - Focal Point: Model + hero product = primary focus (60% visual weight), graphics support (40%) - Movement: Diagonal lines and angled elements create directional flow (top-left to bottom-right or vice versa) PHASE 8: BRAND INTELLIGENCE (AUTONOMOUS) Autonomously adapt composition based on [BRAND NAME] personality: - Streetwear/Sportswear (Nike, Adidas, Supreme): - Luxury Streetwear (Balenciaga, Off-White, Gucci): - Beauty/Lifestyle (Glossier, Fenty, Skims): - Tech/Modern (Apple, Tesla, Beats): PHASE 9: SOCIAL MEDIA FOOTER (OPTIONAL) - Bottom Strip: Clean white or light gray bar at bottom 8-10% of frame - Content: Social media handles (Instagram, Facebook, Twitter) in small sans-serif - Layout: Three-column grid with platform icons or text handles - Aesthetic: Minimal and professional – contrast with chaotic collage above TECHNICAL SPECS: - Aspect Ratio: 4:5 (Instagram feed) or 1:1 (square social post) - Resolution: 2400x3000px minimum (high-quality for zoom and detail) - Color Mode: sRGB, vibrant saturation (Instagram-optimized) - File Aesthetic: Digital collage that mimics analog craft (Photoshop + hand-drawn hybrid) - Model Photography: 85mm lens, f/2.8, shallow depth of field on original shoot (before cutout) - Style Reference: Nike social campaigns, Spotify wrapped graphics, Gen Z Instagram aesthetics, Hypebeast x streetwear collabs - Mood: Confident, energetic, youthful, authentic chaos, anti-corporate polish

查看 API 代码
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": "[BRAND NAME = CHANGE TO YOUR BRAND]. Act as a Social Media Art Director and Digital Collage Artist specializing in bold, youth-oriented brand content for Instagram and digital campaigns. PHASE 1: CONCEPTUAL FRAMEWORK Create a dynamic digital collage that merges fashion photography with graphic design chaos. This is controlled rebellion – a composition that feels spontaneous and energetic while maintaining brand coherence. The aesthetic is anti-polished: torn edges, layered textures, hand-drawn elements, and bold color blocking that screams confidence and movement. PHASE 2: MODEL & PHOTOGRAPHY - Subject: One model (diverse casting, age 18-30) in a dynamic, confident pose - Pose Energy: 80% attitude, 20% natural – sitting, jumping, mid-motion, or power stance (avoid static standing) - Outfit: Street style/athleisure that aligns with [BRAND NAME] aesthetic – casual but styled - Hero Product: Feature 1 signature [BRAND NAME] product prominently (sneakers, bag, apparel) – this is the visual anchor - Photography Style: Editorial fashion cutout – model extracted from background with clean edges - Camera Angle: Slight low angle to empower subject (hero perspective) - Crop: Full body or 3/4 body showing hero product clearly - Background Removal: Model cut out cleanly for layering over collage elements PHASE 3: COLOR BLOCKING FOUNDATION - Primary Color Blob: Large organic shape (40-60% of composition) in bold, saturated brand color behind/around model - Shape Style: Irregular, hand-painted aesthetic – think Photoshop brush strokes or torn paper texture (NOT perfect geometric shapes) - Color Selection (Autonomous): Choose 1 hero color from [BRAND NAME] palette: - Texture: Visible brush strokes, grain, or subtle noise (15-25% opacity) – avoid flat digital fills - Placement: Blob positioned to frame model without obscuring key product details PHASE 4: GRAPHIC ELEMENTS LAYER Add 3-5 abstract graphic elements scattered across composition: - Element Types: - Color Palette: Use 2-3 accent colors total (main blob color + 1-2 contrasting tones from brand palette) - Placement: Asymmetric scatter – top-left and bottom-right zones primarily (avoid center crowding) - Scale: Mix small (5% of canvas) and medium (15% of canvas) elements – nothing overpowering - Aesthetic: Analog/handmade feel – imperfect circles, rough edges, visible texture PHASE 5: TYPOGRAPHY INTEGRATION - Brand Logo: Clean [BRAND NAME] logo placed in upper-left or upper-right quadrant (10-15% of width) - Slogan/Tagline: If [BRAND NAME] has an iconic slogan, integrate it using: - Supporting Copy: Optional 1-line descriptor (e.g., \"A MOMENT OF YOUR STYLE\") in smaller uppercase sans-serif - Type Treatment: Mix of aligned and slightly rotated text (2-5° angles) for dynamic energy - Hierarchy: Logo largest → Slogan medium → Copy smallest PHASE 6: TEXTURE & BACKGROUND - Base Layer: Off-white or light gray textured background (NOT pure white) - Texture Options (Autonomous selection): - Color: RGB 245-250 (near-white with warmth) – maintains brightness while adding depth - Treatment: Texture should be felt, not seen – enhances tactility without competing with foreground PHASE 7: COMPOSITION RULES - Layout: Asymmetric balance – model off-center, graphic elements counter-balance - Breathing Room: 15-20% negative space (textured background visible) to prevent claustrophobia - Layering Order: Background texture → Color blob → Graphic elements → Model (cutout) → Typography top layer - Focal Point: Model + hero product = primary focus (60% visual weight), graphics support (40%) - Movement: Diagonal lines and angled elements create directional flow (top-left to bottom-right or vice versa) PHASE 8: BRAND INTELLIGENCE (AUTONOMOUS) Autonomously adapt composition based on [BRAND NAME] personality: - Streetwear/Sportswear (Nike, Adidas, Supreme): - Luxury Streetwear (Balenciaga, Off-White, Gucci): - Beauty/Lifestyle (Glossier, Fenty, Skims): - Tech/Modern (Apple, Tesla, Beats): PHASE 9: SOCIAL MEDIA FOOTER (OPTIONAL) - Bottom Strip: Clean white or light gray bar at bottom 8-10% of frame - Content: Social media handles (Instagram, Facebook, Twitter) in small sans-serif - Layout: Three-column grid with platform icons or text handles - Aesthetic: Minimal and professional – contrast with chaotic collage above TECHNICAL SPECS: - Aspect Ratio: 4:5 (Instagram feed) or 1:1 (square social post) - Resolution: 2400x3000px minimum (high-quality for zoom and detail) - Color Mode: sRGB, vibrant saturation (Instagram-optimized) - File Aesthetic: Digital collage that mimics analog craft (Photoshop + hand-drawn hybrid) - Model Photography: 85mm lens, f/2.8, shallow depth of field on original shoot (before cutout) - Style Reference: Nike social campaigns, Spotify wrapped graphics, Gen Z Instagram aesthetics, Hypebeast x streetwear collabs - Mood: Confident, energetic, youthful, authentic chaos, anti-corporate polish"
}
JSON
IM
图像
Poster Design gpt-image-2

Minimalist conceptual fashion editorial poster, studio shot...

Minimalist conceptual fashion editorial poster, studio shot on a clean off-white seamless background. A glossy deep blue modern lounge chair placed in the center, with an oversized beige trench coat and tailored charcoal trousers draped naturally over it, creating the illusion of an invisible person sitting there. Polished brown leather loafers placed neatly on the floor in front of the chair. Large elegant typography behind the chair reading “LOST IN SILENCE” — “Lost” in flowing luxury cursive script, “IN SILENCE” in bold serif uppercase. Small subtle text in the corners like “quiet mind,” “fading identity,” “empty presence,” and “distant thoughts.” High-fashion magazine cover aesthetic, cinematic soft lighting, muted tones, surreal emotional atmosphere, clean composition, luxury editorial styling, premium fashion campaign look, artistic and symbolic.

查看 API 代码
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 conceptual fashion editorial poster, studio shot on a clean off-white seamless background. A glossy deep blue modern lounge chair placed in the center, with an oversized beige trench coat and tailored charcoal trousers draped naturally over it, creating the illusion of an invisible person sitting there. Polished brown leather loafers placed neatly on the floor in front of the chair. Large elegant typography behind the chair reading “LOST IN SILENCE” — “Lost” in flowing luxury cursive script, “IN SILENCE” in bold serif uppercase. Small subtle text in the corners like “quiet mind,” “fading identity,” “empty presence,” and “distant thoughts.” High-fashion magazine cover aesthetic, cinematic soft lighting, muted tones, surreal emotional atmosphere, clean composition, luxury editorial styling, premium fashion campaign look, artistic and symbolic."
}
JSON
IM
图像
Poster Design gpt-image-2

A hyper-realistic premium product advertisement featuring an...

A hyper-realistic premium product advertisement featuring an oversized futuristic comfort clog placed on a smooth glossy reflective floor. A modern model dressed in soft neutral-toned athleisure (off-white / beige) stands slightly leaning against the giant shoe with a relaxed, confident posture. Background: clean gradient blending soft sky blue into subtle lavender tones, with massive bold typography in the background reading “STEP INTO EASE” in a modern sans-serif font, stretched vertically and partially behind the subject. Lighting: high-end studio lighting with soft highlights, gentle reflections on the floor, and subtle rim light outlining the model and product for depth. Composition: editorial magazine layout, perfectly centered subject, strong negative space, luxury branding feel. Additional text (small, minimal placement at bottom): “Designed for all-day comfort. Made to move with you.” Style: ultra-clean, Apple-style minimalism meets fashion campaign, hyper-realistic, premium commercial photography, 8K, sharp details.

查看 API 代码
curl -X POST https://runapi.ai/api/v1/gpt_image_2/text_to_image \
  -H "Authorization: Bearer $RUNAPI_KEY" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'JSON'
{
  "model": "gpt-image-2",
  "prompt": "A hyper-realistic premium product advertisement featuring an oversized futuristic comfort clog placed on a smooth glossy reflective floor. A modern model dressed in soft neutral-toned athleisure (off-white / beige) stands slightly leaning against the giant shoe with a relaxed, confident posture. Background: clean gradient blending soft sky blue into subtle lavender tones, with massive bold typography in the background reading “STEP INTO EASE” in a modern sans-serif font, stretched vertically and partially behind the subject. Lighting: high-end studio lighting with soft highlights, gentle reflections on the floor, and subtle rim light outlining the model and product for depth. Composition: editorial magazine layout, perfectly centered subject, strong negative space, luxury branding feel. Additional text (small, minimal placement at bottom): “Designed for all-day comfort. Made to move with you.” Style: ultra-clean, Apple-style minimalism meets fashion campaign, hyper-realistic, premium commercial photography, 8K, sharp details."
}
JSON
IM
图像
Poster Design gpt-image-2

A cinematic, high-end sneaker advertisement poster featuring...

A cinematic, high-end sneaker advertisement poster featuring a young male model mid-air in a dynamic jumping pose, captured from a low-angle perspective to emphasize power and motion. The model is wearing a coordinated beige streetwear outfit (hoodie and joggers), with oversized chunky white sneakers that have bold orange accents on the sole and side stripes. The background is a smooth studio gradient in warm tones, blending light yellow and vibrant orange for an eye-catching, energetic feel. Dramatic soft studio lighting enhances the subject, with glowing highlights and subtle shadows that complement the outfit and colour palette. Behind the model, large bold typography is seamlessly integrated into the composition, reading “RISE” in oversized modern sans-serif font, partially obscured by the subject for depth. Additional small promotional text is placed around the layout in a clean editorial style, such as: “RISE ABOVE. STAND OUT.” “BIGGER STEPS. BOLDER MOVES. BETTER YOU.” “COMFORT THAT ELEVATES.” “PREMIUM MATERIALS. RESPONSIVE CUSHIONING. TIMELESS DESIGN.” At the bottom, a modern sneaker brand logo “AERO” appears with the tagline “MOVE DIFFERENT.” Add subtle motion effects like dust particles or energy trails beneath the jumping foot to enhance impact. Ultra-realistic detail, sharp focus, high contrast, commercial fashion photography style, magazine-quality composition, 4K resolution.

查看 API 代码
curl -X POST https://runapi.ai/api/v1/gpt_image_2/text_to_image \
  -H "Authorization: Bearer $RUNAPI_KEY" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'JSON'
{
  "model": "gpt-image-2",
  "prompt": "A cinematic, high-end sneaker advertisement poster featuring a young male model mid-air in a dynamic jumping pose, captured from a low-angle perspective to emphasize power and motion. The model is wearing a coordinated beige streetwear outfit (hoodie and joggers), with oversized chunky white sneakers that have bold orange accents on the sole and side stripes. The background is a smooth studio gradient in warm tones, blending light yellow and vibrant orange for an eye-catching, energetic feel. Dramatic soft studio lighting enhances the subject, with glowing highlights and subtle shadows that complement the outfit and colour palette. Behind the model, large bold typography is seamlessly integrated into the composition, reading “RISE” in oversized modern sans-serif font, partially obscured by the subject for depth. Additional small promotional text is placed around the layout in a clean editorial style, such as: “RISE ABOVE. STAND OUT.” “BIGGER STEPS. BOLDER MOVES. BETTER YOU.” “COMFORT THAT ELEVATES.” “PREMIUM MATERIALS. RESPONSIVE CUSHIONING. TIMELESS DESIGN.” At the bottom, a modern sneaker brand logo “AERO” appears with the tagline “MOVE DIFFERENT.” Add subtle motion effects like dust particles or energy trails beneath the jumping foot to enhance impact. Ultra-realistic detail, sharp focus, high contrast, commercial fashion photography style, magazine-quality composition, 4K resolution."
}
JSON
IM
图像
Poster Design gpt-image-2

{ "style_id": "photo-flat-doodle-campaign-poster", "styl...

{ "style_id": "photo-flat-doodle-campaign-poster", "style_name": "Photo × Flat-Doodle Campaign Poster", "version": "1.0", "aspect_ratio": "2:3", "reference": "Shanghai edition — derived from TfL 'Your London Adventure Starts Here'", "variables": { "scene": { "city": "上海 Shanghai", "landmark_photo": { "subject": "Oriental Pearl Tower with Lujiazui skyline in the background, viewed from across the Huangpu River", "angle": "low-angle hero shot, Pearl Tower centered and vertical, the two pink spheres clearly visible", "lighting": "early evening blue hour, city lights just starting to glow, sky still holding daylight", "treatment": "unretouched realistic photograph, natural steel + concrete + river reflection, no filter" }, "background_sky": "deep teal-to-indigo gradient sky with a subtle warm glow at the horizon, upper 40% of canvas kept open for headline" }, "hero_character": { "enabled": true, "scale": "giant — roughly 1.2× tower height, standing on the right, body extends beyond canvas", "pose": "holding a cartoon xiaolongbao steamer basket up to eye level with one hand, the other hand doing a casual wave, one foot slightly lifted mid-step", "skin_tone": "flat neon-green (non-realistic)", "face": "minimal — single curved smile, no nose, small cobalt-blue round eyes like dots", "hair": "long straight black-with-hot-pink-streaks hair, high ponytail swinging to one side, short blunt bangs", "outfit": { "top": "oversized cobalt-blue modern qipao-inspired jacket with a stand collar, hot-pink frog-button closures, cropped length", "bottom": "off-white baggy cargo pants with a neon-green side stripe and oversized pockets", "shoes": "chunky pink-and-yellow platform sneakers" }, "accessory": "bamboo-style cartoon steamer basket with three xiaolongbao peeking out, tiny yellow steam swirls drawn above", "linework": "thin consistent black outline on qipao collar, frog buttons, ponytail strands, and steamer weave" }, "doodle_props": [ { "id": "giant_xiaolongbao_cloud", "shape": "three oversized cartoon soup dumplings floating together with exaggerated steam swirls", "colors": ["off-white dumpling skin", "hot-pink pleats", "sun-yellow steam"], "position": "lower-left foreground, tilted, partially covering the tower base" }, { "id": "metro_heart_sticker", "shape": "Shanghai Metro red circle mark restyled as a flat sticker with sparkle stars", "colors": ["hot-pink circle", "off-white Chinese character 地", "neon-green sparkles"], "position": "pasted onto the lower sphere of the Pearl Tower" }, { "id": "huangpu_wave", "shape": "stylized cartoon river wave curl, like a chunky comma", "colors": ["cobalt-blue wave", "off-white foam tips"], "position": "mid-left, floating in front of the tower mid-section" }, { "id": "red_lantern", "shape": "round traditional cartoon red lantern with a tiny tassel", "colors": ["hot-pink lantern", "sun-yellow tassel", "neon-green string"], "position": "center-upper, overlapping between the two pink spheres of the tower" }, { "id": "magnolia_petal_burst", "shape": "a small cluster of 3 oversized cartoon magnolia petals (Shanghai's city flower)", "colors": ["off-white petals", "hot-pink tips"], "position": "far-left mid-height, drifting diagonally as a color accent" }, { "id": "panda_bubble_tea_buddy", "shape": "tiny cartoon bubble tea cup with a smiling face and a panda-ear straw topper", "colors": ["off-white cup", "ink-black pearls", "neon-green straw"], "position": "bottom-right near the character's shoe, as a sidekick scale cue" } ], "copy": { "headline": { "text": "你的上海奇遇 从这里开始", "language": "zh-CN", "max_lines": 3, "english_variant": "Your Shanghai Adventure Starts Here" }, "subhead": { "text": "乘地铁。逛街巷。尝一口。", "language": "zh-CN" }, "logos": { "bottom_left": "上海市人民政府 SHANGHAI MUNICIPAL GOVERNMENT", "bottom_right": "上海地铁 SHANGHAI METRO — 每一站都是故事 (with metro roundel)" } } } }

查看 API 代码
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": "{ \"style_id\": \"photo-flat-doodle-campaign-poster\", \"style_name\": \"Photo × Flat-Doodle Campaign Poster\", \"version\": \"1.0\", \"aspect_ratio\": \"2:3\", \"reference\": \"Shanghai edition — derived from TfL 'Your London Adventure Starts Here'\", \"variables\": { \"scene\": { \"city\": \"上海 Shanghai\", \"landmark_photo\": { \"subject\": \"Oriental Pearl Tower with Lujiazui skyline in the background, viewed from across the Huangpu River\", \"angle\": \"low-angle hero shot, Pearl Tower centered and vertical, the two pink spheres clearly visible\", \"lighting\": \"early evening blue hour, city lights just starting to glow, sky still holding daylight\", \"treatment\": \"unretouched realistic photograph, natural steel + concrete + river reflection, no filter\" }, \"background_sky\": \"deep teal-to-indigo gradient sky with a subtle warm glow at the horizon, upper 40% of canvas kept open for headline\" }, \"hero_character\": { \"enabled\": true, \"scale\": \"giant — roughly 1.2× tower height, standing on the right, body extends beyond canvas\", \"pose\": \"holding a cartoon xiaolongbao steamer basket up to eye level with one hand, the other hand doing a casual wave, one foot slightly lifted mid-step\", \"skin_tone\": \"flat neon-green (non-realistic)\", \"face\": \"minimal — single curved smile, no nose, small cobalt-blue round eyes like dots\", \"hair\": \"long straight black-with-hot-pink-streaks hair, high ponytail swinging to one side, short blunt bangs\", \"outfit\": { \"top\": \"oversized cobalt-blue modern qipao-inspired jacket with a stand collar, hot-pink frog-button closures, cropped length\", \"bottom\": \"off-white baggy cargo pants with a neon-green side stripe and oversized pockets\", \"shoes\": \"chunky pink-and-yellow platform sneakers\" }, \"accessory\": \"bamboo-style cartoon steamer basket with three xiaolongbao peeking out, tiny yellow steam swirls drawn above\", \"linework\": \"thin consistent black outline on qipao collar, frog buttons, ponytail strands, and steamer weave\" }, \"doodle_props\": [ { \"id\": \"giant_xiaolongbao_cloud\", \"shape\": \"three oversized cartoon soup dumplings floating together with exaggerated steam swirls\", \"colors\": [\"off-white dumpling skin\", \"hot-pink pleats\", \"sun-yellow steam\"], \"position\": \"lower-left foreground, tilted, partially covering the tower base\" }, { \"id\": \"metro_heart_sticker\", \"shape\": \"Shanghai Metro red circle mark restyled as a flat sticker with sparkle stars\", \"colors\": [\"hot-pink circle\", \"off-white Chinese character 地\", \"neon-green sparkles\"], \"position\": \"pasted onto the lower sphere of the Pearl Tower\" }, { \"id\": \"huangpu_wave\", \"shape\": \"stylized cartoon river wave curl, like a chunky comma\", \"colors\": [\"cobalt-blue wave\", \"off-white foam tips\"], \"position\": \"mid-left, floating in front of the tower mid-section\" }, { \"id\": \"red_lantern\", \"shape\": \"round traditional cartoon red lantern with a tiny tassel\", \"colors\": [\"hot-pink lantern\", \"sun-yellow tassel\", \"neon-green string\"], \"position\": \"center-upper, overlapping between the two pink spheres of the tower\" }, { \"id\": \"magnolia_petal_burst\", \"shape\": \"a small cluster of 3 oversized cartoon magnolia petals (Shanghai's city flower)\", \"colors\": [\"off-white petals\", \"hot-pink tips\"], \"position\": \"far-left mid-height, drifting diagonally as a color accent\" }, { \"id\": \"panda_bubble_tea_buddy\", \"shape\": \"tiny cartoon bubble tea cup with a smiling face and a panda-ear straw topper\", \"colors\": [\"off-white cup\", \"ink-black pearls\", \"neon-green straw\"], \"position\": \"bottom-right near the character's shoe, as a sidekick scale cue\" } ], \"copy\": { \"headline\": { \"text\": \"你的上海奇遇 从这里开始\", \"language\": \"zh-CN\", \"max_lines\": 3, \"english_variant\": \"Your Shanghai Adventure Starts Here\" }, \"subhead\": { \"text\": \"乘地铁。逛街巷。尝一口。\", \"language\": \"zh-CN\" }, \"logos\": { \"bottom_left\": \"上海市人民政府 SHANGHAI MUNICIPAL GOVERNMENT\", \"bottom_right\": \"上海地铁 SHANGHAI METRO — 每一站都是故事 (with metro roundel)\" } } } }"
}
JSON
IM
图像
Poster Design gpt-image-2

[BRAND NAME = AUTO VAULT MOTORS] [CAR MODEL = HYUNDAI CRETA...

[BRAND NAME = AUTO VAULT MOTORS] [CAR MODEL = HYUNDAI CRETA 2025 • SX (O) TOP MODEL] [PRICE = ₹17.45 LAKH] [KEY HIGHLIGHTS = 12,500 KM • 1st OWNER • PETROL • FULL SERVICE RECORD • UNDER WARRANTY] [CONTACT = +91 98765 43210 • WHATSAPP AVAILABLE • JAMMU] Act as a Social Media Art Director and Digital Collage Artist specializing in bold, youth-oriented automotive resale promotions for Instagram and digital campaigns. PHASE 1: CONCEPTUAL FRAMEWORK Create a high-conversion digital collage that positions this Creta as a premium smart buy. This is not “used”. This is “upgrade for less”. Visual strategy: - Blend premium SUV aspiration with deal urgency - Controlled chaos with refined execution - Price + car as dual hero Aesthetic: Clean chaos — less messy, more premium energy PHASE 2: MODEL & PHOTOGRAPHY - Subject: Hyundai Creta 2025 SX (O) - Pose Energy: Front 3/4 angle, slightly turned, confident stance - Hero Product: Full car body with emphasis on grill + DRLs - Photography Style: Clean high-resolution cutout - Camera Angle: Slight low angle (premium presence) - Crop: Full car visible - Optional Human Element: Subtle driver silhouette inside for realism PHASE 3: COLOR BLOCKING FOUNDATION - Primary Color Blob: Deep metallic blue (premium tone) - Size: ~50% of composition - Shape Style: Smooth torn-brush hybrid (refined, not aggressive) - Texture: Light metallic grain (15%) - Placement: Diagonal behind car (top-left → bottom-right flow) PHASE 4: GRAPHIC ELEMENTS LAYER - Price badge (bold, high contrast) — PRIMARY - “CERTIFIED” stamp badge - Minimal arrow accents pointing toward car - Soft glow lines (premium touch) Rules: - Colors: Blue + white + subtle neon accent - Placement: Corners, avoid cluttering car - Scale: Price = largest graphic element PHASE 5: TYPOGRAPHY INTEGRATION - Logo: Top-left (clean, small) - Headline: “SMART UPGRADE” - Price (DOMINANT): “₹17.45 LAKH” - Supporting Copy: “2025 • 12,500 KM • 1st OWNER” “PETROL • UNDER WARRANTY” - CTA: “BOOK TEST DRIVE NOW” - Type Treatment: Clean bold sans-serif, minimal rotation (2° max) - Hierarchy: Price → Headline → Car name → Details → CTA → Logo PHASE 6: TEXTURE & BACKGROUND - Base: Light grey premium tone (RGB ~246) - Texture: Subtle paper + metallic grain blend - Rule: Very controlled — premium feel PHASE 7: COMPOSITION RULES - Layout: Car slightly right of center - Breathing Room: 20% clean space - Layering: Background → Blob → Graphics → Car → Typography - Focal Split: 60% car + price 40% support elements - Movement: Diagonal guiding eye → price → CTA PHASE 8: BRAND INTELLIGENCE Premium used dealer: - Clean layout - Strong trust signals - Minimal chaos vs streetwear style PHASE 9: SOCIAL MEDIA FOOTER - Bottom strip (clean white) - Content: 📞 +91 98765 43210 📍 Jammu 💬 WhatsApp Available - Layout: Minimal grid TECHNICAL SPECS: - 4:5 ratio (Instagram) - 2400x3000px+ - sRGB - High clarity (car ultra sharp) - Controlled grain - Style: Gen-Z collage × premium dealership aesthetic FINAL OUTPUT MOOD: Premium. Trustworthy. Urgent. Smart purchase. High conversion intent.

查看 API 代码
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": "[BRAND NAME = AUTO VAULT MOTORS] [CAR MODEL = HYUNDAI CRETA 2025 • SX (O) TOP MODEL] [PRICE = ₹17.45 LAKH] [KEY HIGHLIGHTS = 12,500 KM • 1st OWNER • PETROL • FULL SERVICE RECORD • UNDER WARRANTY] [CONTACT = +91 98765 43210 • WHATSAPP AVAILABLE • JAMMU] Act as a Social Media Art Director and Digital Collage Artist specializing in bold, youth-oriented automotive resale promotions for Instagram and digital campaigns. PHASE 1: CONCEPTUAL FRAMEWORK Create a high-conversion digital collage that positions this Creta as a premium smart buy. This is not “used”. This is “upgrade for less”. Visual strategy: - Blend premium SUV aspiration with deal urgency - Controlled chaos with refined execution - Price + car as dual hero Aesthetic: Clean chaos — less messy, more premium energy PHASE 2: MODEL & PHOTOGRAPHY - Subject: Hyundai Creta 2025 SX (O) - Pose Energy: Front 3/4 angle, slightly turned, confident stance - Hero Product: Full car body with emphasis on grill + DRLs - Photography Style: Clean high-resolution cutout - Camera Angle: Slight low angle (premium presence) - Crop: Full car visible - Optional Human Element: Subtle driver silhouette inside for realism PHASE 3: COLOR BLOCKING FOUNDATION - Primary Color Blob: Deep metallic blue (premium tone) - Size: ~50% of composition - Shape Style: Smooth torn-brush hybrid (refined, not aggressive) - Texture: Light metallic grain (15%) - Placement: Diagonal behind car (top-left → bottom-right flow) PHASE 4: GRAPHIC ELEMENTS LAYER - Price badge (bold, high contrast) — PRIMARY - “CERTIFIED” stamp badge - Minimal arrow accents pointing toward car - Soft glow lines (premium touch) Rules: - Colors: Blue + white + subtle neon accent - Placement: Corners, avoid cluttering car - Scale: Price = largest graphic element PHASE 5: TYPOGRAPHY INTEGRATION - Logo: Top-left (clean, small) - Headline: “SMART UPGRADE” - Price (DOMINANT): “₹17.45 LAKH” - Supporting Copy: “2025 • 12,500 KM • 1st OWNER” “PETROL • UNDER WARRANTY” - CTA: “BOOK TEST DRIVE NOW” - Type Treatment: Clean bold sans-serif, minimal rotation (2° max) - Hierarchy: Price → Headline → Car name → Details → CTA → Logo PHASE 6: TEXTURE & BACKGROUND - Base: Light grey premium tone (RGB ~246) - Texture: Subtle paper + metallic grain blend - Rule: Very controlled — premium feel PHASE 7: COMPOSITION RULES - Layout: Car slightly right of center - Breathing Room: 20% clean space - Layering: Background → Blob → Graphics → Car → Typography - Focal Split: 60% car + price 40% support elements - Movement: Diagonal guiding eye → price → CTA PHASE 8: BRAND INTELLIGENCE Premium used dealer: - Clean layout - Strong trust signals - Minimal chaos vs streetwear style PHASE 9: SOCIAL MEDIA FOOTER - Bottom strip (clean white) - Content: 📞 +91 98765 43210 📍 Jammu 💬 WhatsApp Available - Layout: Minimal grid TECHNICAL SPECS: - 4:5 ratio (Instagram) - 2400x3000px+ - sRGB - High clarity (car ultra sharp) - Controlled grain - Style: Gen-Z collage × premium dealership aesthetic FINAL OUTPUT MOOD: Premium. Trustworthy. Urgent. Smart purchase. High conversion intent."
}
JSON
IM
图像
Poster Design nano-banana-2

[PERSON NAME]. Act as a high-end sports graphic designer cr...

[PERSON NAME]. Act as a high-end sports graphic designer creating a conceptual tribute poster. The style is a complex "dual exposure photo-grid composite" with mixed-media textures. CENTRAL STRUCTURE (THE VESSEL): The central focus is a large-scale, high-contrast black and white portrait silhouette of [PERSON NAME]. This main portrait acts as the container. THE GRID FILL & TEXTURES (MIXED MEDIA): The interior of the silhouette is populated by a dense "photo mosaic grid" of action shots from the person's career. CRITICAL TEXTURE INSTRUCTION: Do not just paste flat photos. Apply artistic textures to various grid cells to create a tactile, collage feel. Use effects like: Halftone Dots: Comic-book style raster patterns on some cells. Fabric/Embroidery: Subtle thread or canvas textures suggesting a jersey or patch. Film Grain: Heavy noise on specific high-contrast action shots. COLOR STRATEGY: The base is Monochrome B&W. Use selective color overlays (relevant to the team/flag) ONLY on specific grid cells to create a rhythm. TYPOGRAPHY & BRANDING (STRICT MICRO-SCALING): Top Left (The Name): Write "[PERSON NAME]" strictly using the font Inter Semibold. Kerning: Tight negative kerning (-4%). Size: SMALL and discreet. It must occupy MAXIMUM 20% of the canvas width. Do NOT make it large or loud. Top Right (The Symbol): Place the primary logo (Team/Brand/Flag). Size: VERY SMALL. It must occupy MAXIMUM 10% of the canvas width. COMPOSITION & BACKGROUND: Background: Off-white or light grey with a visible high-quality paper or concrete texture. It should not be flat digital white. Alignment: Center the figure perfectly. Maintain wide negative space around the object.

查看 API 代码
curl -X POST https://runapi.ai/api/v1/nano_banana/text_to_image \
  -H "Authorization: Bearer $RUNAPI_KEY" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'JSON'
{
  "model": "nano-banana-2",
  "prompt": "[PERSON NAME]. Act as a high-end sports graphic designer creating a conceptual tribute poster. The style is a complex \"dual exposure photo-grid composite\" with mixed-media textures. CENTRAL STRUCTURE (THE VESSEL): The central focus is a large-scale, high-contrast black and white portrait silhouette of [PERSON NAME]. This main portrait acts as the container. THE GRID FILL & TEXTURES (MIXED MEDIA): The interior of the silhouette is populated by a dense \"photo mosaic grid\" of action shots from the person's career. CRITICAL TEXTURE INSTRUCTION: Do not just paste flat photos. Apply artistic textures to various grid cells to create a tactile, collage feel. Use effects like: Halftone Dots: Comic-book style raster patterns on some cells. Fabric/Embroidery: Subtle thread or canvas textures suggesting a jersey or patch. Film Grain: Heavy noise on specific high-contrast action shots. COLOR STRATEGY: The base is Monochrome B&W. Use selective color overlays (relevant to the team/flag) ONLY on specific grid cells to create a rhythm. TYPOGRAPHY & BRANDING (STRICT MICRO-SCALING): Top Left (The Name): Write \"[PERSON NAME]\" strictly using the font Inter Semibold. Kerning: Tight negative kerning (-4%). Size: SMALL and discreet. It must occupy MAXIMUM 20% of the canvas width. Do NOT make it large or loud. Top Right (The Symbol): Place the primary logo (Team/Brand/Flag). Size: VERY SMALL. It must occupy MAXIMUM 10% of the canvas width. COMPOSITION & BACKGROUND: Background: Off-white or light grey with a visible high-quality paper or concrete texture. It should not be flat digital white. Alignment: Center the figure perfectly. Maintain wide negative space around the object."
}
JSON
IM
图像
Poster Design nano-banana-2

{ "project_settings": { "task_type": "九宫格新年祝福肖像(男生版)",...

{ "project_settings": { "task_type": "九宫格新年祝福肖像(男生版)", "aspect_ratio": "1:1", "grid_layout": "3x3", "batch_size": 1 }, "overall_style": { "整体风格": "极简新年祝福风", "视觉基调": "干净、温和、克制的节日感", "背景": "纯色白墙面,无装饰", "光线": "自然柔光,均匀无强阴影", "色彩重点": "中国红(服装 + 文字)" }, "subject_base": { "人物一致性": "九宫格内为同一位人物", "人物类型": "亚洲男性", "性别气质": "干净、阳光、自然,不油腻", "发型": "黑色短发,自然蓬松,简洁利落", "服装": "红色针织毛衣或卫衣,简洁无图案", "妆容": "无明显妆感,真实自然肤质", "表情气质": "开心,克制的微笑,不夸张" }, "pose_variations": { "grid_1": "食指竖于嘴前,轻松安静手势", "grid_2": "单手比 V 手势靠近脸部", "grid_3": "单手做 OK 或三指手势", "grid_4": "双手举起做轻松俏皮手势(不过度卖萌)", "grid_5": "单手张开遮住半边脸", "grid_6": "单手做电话手势靠近脸侧", "grid_7": "单手轻点脸颊或下巴", "grid_8": "单手托下巴,轻微思考姿势", "grid_9": "双手指向脸部或克制比心变体" }, "text_overlays": { "字体风格": "传统中文新年书法字体", "文字颜色": "中国红", "年份颜色": "深蓝色", "文字位置": "每一格顶部居中", "文字结构": "四字祝福语 + 年份" }, "text_content": [ { "position": "grid_1", "text": "一帆风顺", "year": "2026" }, { "position": "grid_2", "text": "双喜临门", "year": "2026" }, { "position": "grid_3", "text": "三阳开泰", "year": "2026" }, { "position": "grid_4", "text": "四季发财", "year": "2026" }, { "position": "grid_5", "text": "五福临门", "year": "2026" }, { "position": "grid_6", "text": "六六大顺", "year": "2026" }, { "position": "grid_7", "text": "七星高照", "year": "2026" }, { "position": "grid_8", "text": "八方来财", "year": "2026" }, { "position": "grid_9", "text": "九九同心", "year": "2026" } ], "constraints": { "禁止项": [ "不改变人物身份", "不夸张表情", "不女性化姿态", "不使用复杂背景", "不添加节日道具", "不风格化面部" ], "一致性要求": [ "人物脸型五官保持完全一致", "服装颜色与材质一致", "拍摄角度与距离基本一致" ] }, "use_cases": [ "男生新年纪念照", "个人春节祝福九宫格", "社交平台头像矩阵", "品牌新年男生模板" ] }

查看 API 代码
curl -X POST https://runapi.ai/api/v1/nano_banana/text_to_image \
  -H "Authorization: Bearer $RUNAPI_KEY" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'JSON'
{
  "model": "nano-banana-2",
  "prompt": "{ \"project_settings\": { \"task_type\": \"九宫格新年祝福肖像(男生版)\", \"aspect_ratio\": \"1:1\", \"grid_layout\": \"3x3\", \"batch_size\": 1 }, \"overall_style\": { \"整体风格\": \"极简新年祝福风\", \"视觉基调\": \"干净、温和、克制的节日感\", \"背景\": \"纯色白墙面,无装饰\", \"光线\": \"自然柔光,均匀无强阴影\", \"色彩重点\": \"中国红(服装 + 文字)\" }, \"subject_base\": { \"人物一致性\": \"九宫格内为同一位人物\", \"人物类型\": \"亚洲男性\", \"性别气质\": \"干净、阳光、自然,不油腻\", \"发型\": \"黑色短发,自然蓬松,简洁利落\", \"服装\": \"红色针织毛衣或卫衣,简洁无图案\", \"妆容\": \"无明显妆感,真实自然肤质\", \"表情气质\": \"开心,克制的微笑,不夸张\" }, \"pose_variations\": { \"grid_1\": \"食指竖于嘴前,轻松安静手势\", \"grid_2\": \"单手比 V 手势靠近脸部\", \"grid_3\": \"单手做 OK 或三指手势\", \"grid_4\": \"双手举起做轻松俏皮手势(不过度卖萌)\", \"grid_5\": \"单手张开遮住半边脸\", \"grid_6\": \"单手做电话手势靠近脸侧\", \"grid_7\": \"单手轻点脸颊或下巴\", \"grid_8\": \"单手托下巴,轻微思考姿势\", \"grid_9\": \"双手指向脸部或克制比心变体\" }, \"text_overlays\": { \"字体风格\": \"传统中文新年书法字体\", \"文字颜色\": \"中国红\", \"年份颜色\": \"深蓝色\", \"文字位置\": \"每一格顶部居中\", \"文字结构\": \"四字祝福语 + 年份\" }, \"text_content\": [ { \"position\": \"grid_1\", \"text\": \"一帆风顺\", \"year\": \"2026\" }, { \"position\": \"grid_2\", \"text\": \"双喜临门\", \"year\": \"2026\" }, { \"position\": \"grid_3\", \"text\": \"三阳开泰\", \"year\": \"2026\" }, { \"position\": \"grid_4\", \"text\": \"四季发财\", \"year\": \"2026\" }, { \"position\": \"grid_5\", \"text\": \"五福临门\", \"year\": \"2026\" }, { \"position\": \"grid_6\", \"text\": \"六六大顺\", \"year\": \"2026\" }, { \"position\": \"grid_7\", \"text\": \"七星高照\", \"year\": \"2026\" }, { \"position\": \"grid_8\", \"text\": \"八方来财\", \"year\": \"2026\" }, { \"position\": \"grid_9\", \"text\": \"九九同心\", \"year\": \"2026\" } ], \"constraints\": { \"禁止项\": [ \"不改变人物身份\", \"不夸张表情\", \"不女性化姿态\", \"不使用复杂背景\", \"不添加节日道具\", \"不风格化面部\" ], \"一致性要求\": [ \"人物脸型五官保持完全一致\", \"服装颜色与材质一致\", \"拍摄角度与距离基本一致\" ] }, \"use_cases\": [ \"男生新年纪念照\", \"个人春节祝福九宫格\", \"社交平台头像矩阵\", \"品牌新年男生模板\" ] }"
}
JSON
IM
图像
Poster Design nano-banana-2

[BRAND NAME]. Act as a Social Media Art Director and Digital...

[BRAND NAME]. Act as a Social Media Art Director and Digital Collage Artist specializing in bold, youth-oriented brand content for Instagram and digital campaigns. PHASE 1: CONCEPTUAL FRAMEWORK Create a dynamic digital collage that merges fashion photography with graphic design chaos. This is controlled rebellion – a composition that feels spontaneous and energetic while maintaining brand coherence. The aesthetic is anti-polished: torn edges, layered textures, hand-drawn elements, and bold color blocking that screams confidence and movement. PHASE 2: MODEL & PHOTOGRAPHY - Subject: One model (diverse casting, age 18-30) in a dynamic, confident pose - Pose Energy: 80% attitude, 20% natural – sitting, jumping, mid-motion, or power stance (avoid static standing) - Outfit: Street style/athleisure that aligns with [BRAND NAME] aesthetic – casual but styled - Hero Product: Feature 1 signature [BRAND NAME] product prominently (sneakers, bag, apparel) – this is the visual anchor - Photography Style: Editorial fashion cutout – model extracted from background with clean edges - Camera Angle: Slight low angle to empower subject (hero perspective) - Crop: Full body or 3/4 body showing hero product clearly - Background Removal: Model cut out cleanly for layering over collage elements PHASE 3: COLOR BLOCKING FOUNDATION - Primary Color Blob: Large organic shape (40-60% of composition) in bold, saturated brand color behind/around model - Shape Style: Irregular, hand-painted aesthetic – think Photoshop brush strokes or torn paper texture (NOT perfect geometric shapes) - Color Selection (Autonomous): Choose 1 hero color from [BRAND NAME] palette: - Texture: Visible brush strokes, grain, or subtle noise (15-25% opacity) – avoid flat digital fills - Placement: Blob positioned to frame model without obscuring key product details PHASE 4: GRAPHIC ELEMENTS LAYER Add 3-5 abstract graphic elements scattered across composition: - Element Types: - Color Palette: Use 2-3 accent colors total (main blob color + 1-2 contrasting tones from brand palette) - Placement: Asymmetric scatter – top-left and bottom-right zones primarily (avoid center crowding) - Scale: Mix small (5% of canvas) and medium (15% of canvas) elements – nothing overpowering - Aesthetic: Analog/handmade feel – imperfect circles, rough edges, visible texture PHASE 5: TYPOGRAPHY INTEGRATION - Brand Logo: Clean [BRAND NAME] logo placed in upper-left or upper-right quadrant (10-15% of width) - Slogan/Tagline: If [BRAND NAME] has an iconic slogan, integrate it using: - Supporting Copy: Optional 1-line descriptor (e.g., "A MOMENT OF YOUR STYLE") in smaller uppercase sans-serif - Type Treatment: Mix of aligned and slightly rotated text (2-5° angles) for dynamic energy - Hierarchy: Logo largest → Slogan medium → Copy smallest PHASE 6: TEXTURE & BACKGROUND - Base Layer: Off-white or light gray textured background (NOT pure white) - Texture Options (Autonomous selection): - Color: RGB 245-250 (near-white with warmth) – maintains brightness while adding depth - Treatment: Texture should be felt, not seen – enhances tactility without competing with foreground PHASE 7: COMPOSITION RULES - Layout: Asymmetric balance – model off-center, graphic elements counter-balance - Breathing Room: 15-20% negative space (textured background visible) to prevent claustrophobia - Layering Order: Background texture → Color blob → Graphic elements → Model (cutout) → Typography top layer - Focal Point: Model + hero product = primary focus (60% visual weight), graphics support (40%) - Movement: Diagonal lines and angled elements create directional flow (top-left to bottom-right or vice versa) PHASE 8: BRAND INTELLIGENCE (AUTONOMOUS) Autonomously adapt composition based on [BRAND NAME] personality: - Streetwear/Sportswear (Nike, Adidas, Supreme): - Luxury Streetwear (Balenciaga, Off-White, Gucci): - Beauty/Lifestyle (Glossier, Fenty, Skims): - Tech/Modern (Apple, Tesla, Beats): PHASE 9: SOCIAL MEDIA FOOTER (OPTIONAL) - Bottom Strip: Clean white or light gray bar at bottom 8-10% of frame - Content: Social media handles (Instagram, Facebook, Twitter) in small sans-serif - Layout: Three-column grid with platform icons or text handles - Aesthetic: Minimal and professional – contrast with chaotic collage above TECHNICAL SPECS: - Aspect Ratio: 4:5 (Instagram feed) or 1:1 (square social post) - Resolution: 2400x3000px minimum (high-quality for zoom and detail) - Color Mode: sRGB, vibrant saturation (Instagram-optimized) - File Aesthetic: Digital collage that mimics analog craft (Photoshop + hand-drawn hybrid) - Model Photography: 85mm lens, f/2.8, shallow depth of field on original shoot (before cutout) - Style Reference: Nike social campaigns, Spotify wrapped graphics, Gen Z Instagram aesthetics, Hypebeast x streetwear collabs - Mood: Confident, energetic, youthful, authentic chaos, anti-corporate polish

查看 API 代码
curl -X POST https://runapi.ai/api/v1/nano_banana/text_to_image \
  -H "Authorization: Bearer $RUNAPI_KEY" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'JSON'
{
  "model": "nano-banana-2",
  "prompt": "[BRAND NAME]. Act as a Social Media Art Director and Digital Collage Artist specializing in bold, youth-oriented brand content for Instagram and digital campaigns. PHASE 1: CONCEPTUAL FRAMEWORK Create a dynamic digital collage that merges fashion photography with graphic design chaos. This is controlled rebellion – a composition that feels spontaneous and energetic while maintaining brand coherence. The aesthetic is anti-polished: torn edges, layered textures, hand-drawn elements, and bold color blocking that screams confidence and movement. PHASE 2: MODEL & PHOTOGRAPHY - Subject: One model (diverse casting, age 18-30) in a dynamic, confident pose - Pose Energy: 80% attitude, 20% natural – sitting, jumping, mid-motion, or power stance (avoid static standing) - Outfit: Street style/athleisure that aligns with [BRAND NAME] aesthetic – casual but styled - Hero Product: Feature 1 signature [BRAND NAME] product prominently (sneakers, bag, apparel) – this is the visual anchor - Photography Style: Editorial fashion cutout – model extracted from background with clean edges - Camera Angle: Slight low angle to empower subject (hero perspective) - Crop: Full body or 3/4 body showing hero product clearly - Background Removal: Model cut out cleanly for layering over collage elements PHASE 3: COLOR BLOCKING FOUNDATION - Primary Color Blob: Large organic shape (40-60% of composition) in bold, saturated brand color behind/around model - Shape Style: Irregular, hand-painted aesthetic – think Photoshop brush strokes or torn paper texture (NOT perfect geometric shapes) - Color Selection (Autonomous): Choose 1 hero color from [BRAND NAME] palette: - Texture: Visible brush strokes, grain, or subtle noise (15-25% opacity) – avoid flat digital fills - Placement: Blob positioned to frame model without obscuring key product details PHASE 4: GRAPHIC ELEMENTS LAYER Add 3-5 abstract graphic elements scattered across composition: - Element Types: - Color Palette: Use 2-3 accent colors total (main blob color + 1-2 contrasting tones from brand palette) - Placement: Asymmetric scatter – top-left and bottom-right zones primarily (avoid center crowding) - Scale: Mix small (5% of canvas) and medium (15% of canvas) elements – nothing overpowering - Aesthetic: Analog/handmade feel – imperfect circles, rough edges, visible texture PHASE 5: TYPOGRAPHY INTEGRATION - Brand Logo: Clean [BRAND NAME] logo placed in upper-left or upper-right quadrant (10-15% of width) - Slogan/Tagline: If [BRAND NAME] has an iconic slogan, integrate it using: - Supporting Copy: Optional 1-line descriptor (e.g., \"A MOMENT OF YOUR STYLE\") in smaller uppercase sans-serif - Type Treatment: Mix of aligned and slightly rotated text (2-5° angles) for dynamic energy - Hierarchy: Logo largest → Slogan medium → Copy smallest PHASE 6: TEXTURE & BACKGROUND - Base Layer: Off-white or light gray textured background (NOT pure white) - Texture Options (Autonomous selection): - Color: RGB 245-250 (near-white with warmth) – maintains brightness while adding depth - Treatment: Texture should be felt, not seen – enhances tactility without competing with foreground PHASE 7: COMPOSITION RULES - Layout: Asymmetric balance – model off-center, graphic elements counter-balance - Breathing Room: 15-20% negative space (textured background visible) to prevent claustrophobia - Layering Order: Background texture → Color blob → Graphic elements → Model (cutout) → Typography top layer - Focal Point: Model + hero product = primary focus (60% visual weight), graphics support (40%) - Movement: Diagonal lines and angled elements create directional flow (top-left to bottom-right or vice versa) PHASE 8: BRAND INTELLIGENCE (AUTONOMOUS) Autonomously adapt composition based on [BRAND NAME] personality: - Streetwear/Sportswear (Nike, Adidas, Supreme): - Luxury Streetwear (Balenciaga, Off-White, Gucci): - Beauty/Lifestyle (Glossier, Fenty, Skims): - Tech/Modern (Apple, Tesla, Beats): PHASE 9: SOCIAL MEDIA FOOTER (OPTIONAL) - Bottom Strip: Clean white or light gray bar at bottom 8-10% of frame - Content: Social media handles (Instagram, Facebook, Twitter) in small sans-serif - Layout: Three-column grid with platform icons or text handles - Aesthetic: Minimal and professional – contrast with chaotic collage above TECHNICAL SPECS: - Aspect Ratio: 4:5 (Instagram feed) or 1:1 (square social post) - Resolution: 2400x3000px minimum (high-quality for zoom and detail) - Color Mode: sRGB, vibrant saturation (Instagram-optimized) - File Aesthetic: Digital collage that mimics analog craft (Photoshop + hand-drawn hybrid) - Model Photography: 85mm lens, f/2.8, shallow depth of field on original shoot (before cutout) - Style Reference: Nike social campaigns, Spotify wrapped graphics, Gen Z Instagram aesthetics, Hypebeast x streetwear collabs - Mood: Confident, energetic, youthful, authentic chaos, anti-corporate polish"
}
JSON
常见问题

查找并使用 RunAPI prompts

RunAPI prompts 是什么?

RunAPI prompts 是面向图像、视频、音乐和音频模型的精选输入示例。每个 prompt 都配有模型 slug 和 endpoint 路径,开发者可以复制到 agent,也可以放进后端调用。

可以按模型或分类筛选 prompts 吗?

可以。用模态和分类链接缩小范围,再打开模型页查看某个模型 slug 对应的示例。模型页会把 prompt 卡片、安装步骤和 API 示例放在一起。

浏览 prompts 需要 API key 吗?

不需要。浏览、筛选和复制 prompt 文本都是公开的。只有当你让 agent 或应用调用模型并创建生成任务时,才需要 RunAPI key。

agent 应该如何使用这些 prompts?

在 Claude Code、Codex、Cursor 或 Windsurf 中安装 RunAPI MCP Server,然后粘贴页面上的 prompt 指令。agent 可以选择匹配的 RunAPI 工具,并带上页面列出的模型。