Examples for using gpt-image-2 through RunAPI from agent tools or API calls. Copy a prompt, then use it in Claude Code, Codex, Cursor, Windsurf, or your backend.
Wuxia style swordswoman portrait, cold and sharp phoenix eyes, porcelain-white skin, long straight black hair wet and windswept across her face, soaked dark martial arts outfit clinging to her form, ancient sword held at her side with blue qi energy glow emanating from the blade, moonlit bamboo forest background with fog, 8K masterpiece quality, dramatic rim lighting from the moon. 9:16 vertical.
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": "Wuxia style swordswoman portrait, cold and sharp phoenix eyes, porcelain-white skin, long straight black hair wet and windswept across her face, soaked dark martial arts outfit clinging to her form, ancient sword held at her side with blue qi energy glow emanating from the blade, moonlit bamboo forest background with fog, 8K masterpiece quality, dramatic rim lighting from the moon. 9:16 vertical."
}
JSON
Create one pitch-deck slide titled 'Market Opportunity' that looks like a real Series A fundraising slide from a YC-backed startup. Clean white background, modern sans-serif typography like Inter, crisp minimal layout. Show a TAM/SAM/SOM nested circle diagram with dollar figures, a key insight callout box, and a footnote source citation. No decorative elements. 16:9.
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 one pitch-deck slide titled 'Market Opportunity' that looks like a real Series A fundraising slide from a YC-backed startup. Clean white background, modern sans-serif typography like Inter, crisp minimal layout. Show a TAM/SAM/SOM nested circle diagram with dollar figures, a key insight callout box, and a footnote source citation. No decorative elements. 16:9."
}
JSON
Create a horizontal Chinese blockbuster movie poster for a fantasy adventure film titled '天机启明' with subtitle '失落的文明'. The poster features a dramatic ensemble cast composition with five to six realistic character headshots arranged in a pyramid formation. Behind them, a glowing ancient tower emits golden circular energy rings against a dramatic stormy sky. Burning ruins and traditional Chinese architecture visible in the middle ground. The title rendered in large stylized golden Chinese calligraphy. Format badges for 3D, IMAX, and Dolby visible at the bottom.
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 horizontal Chinese blockbuster movie poster for a fantasy adventure film titled '天机启明' with subtitle '失落的文明'. The poster features a dramatic ensemble cast composition with five to six realistic character headshots arranged in a pyramid formation. Behind them, a glowing ancient tower emits golden circular energy rings against a dramatic stormy sky. Burning ruins and traditional Chinese architecture visible in the middle ground. The title rendered in large stylized golden Chinese calligraphy. Format badges for 3D, IMAX, and Dolby visible at the bottom."
}
JSON
Science encyclopedia vertical card based on the theme of deep-sea bioluminescent creatures. Beautiful main visual of a glowing anglerfish in the deep ocean. Detail close-up insets showing the bioluminescent organ structure. Rounded modular information sections with facts about depth range, diet, and size. Clear title hierarchy with the creature name prominent. Information-dense but not crowded layout, like a publishable museum card. Dark ocean blue background.
curl -X POST https://runapi.ai/api/v1/gpt_image_2/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "gpt-image-2",
"prompt": "Science encyclopedia vertical card based on the theme of deep-sea bioluminescent creatures. Beautiful main visual of a glowing anglerfish in the deep ocean. Detail close-up insets showing the bioluminescent organ structure. Rounded modular information sections with facts about depth range, diet, and size. Clear title hierarchy with the creature name prominent. Information-dense but not crowded layout, like a publishable museum card. Dark ocean blue background."
}
JSON
Dating app match success screen mockup. Two profile cards colliding with a glowing heart effect between them. Headline text 'It's a Match!' in bold white. Pink 'Chat Now' button and lighter 'Continue Browsing' button below. Dark purple gradient background with floating translucent heart particles. Glassmorphism frosted glass edges on the profile cards. Realistic mobile app UI with proper spacing. 9:16.
Solarpunk cityscape with extensive rooftop gardens and elevated transit lines connecting green towers, bright optimistic mood, clean vector illustration style with defined shapes and limited gradients, ample negative space in the upper-left quadrant for text overlay, 16:9 ratio, warm golden sunlight, no text
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": "Solarpunk cityscape with extensive rooftop gardens and elevated transit lines connecting green towers, bright optimistic mood, clean vector illustration style with defined shapes and limited gradients, ample negative space in the upper-left quadrant for text overlay, 16:9 ratio, warm golden sunlight, no text"
}
JSON
Interior corridor of a massive orbital space station. The hallway curves gently following the station's ring structure, with floor-to-ceiling windows on the outer wall revealing Earth's cloud-covered surface far below. Cool blue-white LED strips line the ceiling joints. The floor is polished dark composite material reflecting the window light. A lone figure in a gray utility jumpsuit walks away from camera, their silhouette small against the panoramic view. Hard science fiction aesthetic — no fantasy elements, functional industrial design inspired by ISS modules scaled up.
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": "Interior corridor of a massive orbital space station. The hallway curves gently following the station's ring structure, with floor-to-ceiling windows on the outer wall revealing Earth's cloud-covered surface far below. Cool blue-white LED strips line the ceiling joints. The floor is polished dark composite material reflecting the window light. A lone figure in a gray utility jumpsuit walks away from camera, their silhouette small against the panoramic view. Hard science fiction aesthetic — no fantasy elements, functional industrial design inspired by ISS modules scaled up."
}
JSON
Clean infographic comparing four coffee brewing methods side by side: French Press, Pour Over, Espresso, and Cold Brew. Each method is represented by a simplified cross-section diagram of its equipment showing water flow and coffee grounds interaction. Below each diagram: brew time, grind size, water temperature, and strength rating shown as icon-based data points. The layout is a single horizontal row on a cream background. Color coding uses warm browns and subtle orange accents. Typography is modern sans-serif. The overall design is editorial and information-dense without feeling cluttered.
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": "Clean infographic comparing four coffee brewing methods side by side: French Press, Pour Over, Espresso, and Cold Brew. Each method is represented by a simplified cross-section diagram of its equipment showing water flow and coffee grounds interaction. Below each diagram: brew time, grind size, water temperature, and strength rating shown as icon-based data points. The layout is a single horizontal row on a cream background. Color coding uses warm browns and subtle orange accents. Typography is modern sans-serif. The overall design is editorial and information-dense without feeling cluttered."
}
JSON
Add festive winter holiday decorations to this storefront. Wrap warm white string lights around the window frame and door frame. Place a small evergreen wreath with a red ribbon on the door. Add a light dusting of snow on the window ledge and awning. Keep the existing signage and architecture completely unchanged. The additions should look naturally integrated with realistic lighting — the string lights should cast a soft warm glow on nearby surfaces.
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": "Add festive winter holiday decorations to this storefront. Wrap warm white string lights around the window frame and door frame. Place a small evergreen wreath with a red ribbon on the door. Add a light dusting of snow on the window ledge and awning. Keep the existing signage and architecture completely unchanged. The additions should look naturally integrated with realistic lighting — the string lights should cast a soft warm glow on nearby surfaces."
}
JSON
FAQ
Using gpt-image-2 prompts
What is %{model}?
%{model} is available through RunAPI as part of the unified model catalog. These prompts show practical input patterns that agents and backend services can reuse.
How do I use these prompts?
Copy any prompt and paste it into Claude Code, Codex, Cursor, or Windsurf after installing the RunAPI MCP Server. Developers can also copy the API example and send the prompt directly.
Do these prompts cost money to browse?
Browsing and copying prompt examples is free. Generation requests only cost money when you call a RunAPI model with your API key.
Can I adapt the prompts for production?
Yes. Treat each prompt as a starting point, then add your brand rules, output dimensions, safety constraints, and application-specific context before using it in production.