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.
Create a vertical launch poster for a fictional design conference called 'FRAME 2026'. Large headline: 'FRAME 2026'. Subtitle: 'DESIGNING WITH MACHINE IMAGINATION'. Clean Swiss grid layout, off-white textured background, black typography, one red geometric accent shape, generous negative space, perfectly legible text, no extra words, no watermark. Aspect ratio 9:16.
A clean infographic titled 'HOW IMAGE PROMPTS WORK' with five labeled steps arranged horizontally: 'Scene', 'Subject', 'Text', 'Composition', 'Constraints'. Flat editorial icons for each step, directional arrows between them, high contrast design, white background, readable sans-serif labels, consistent spacing throughout, no extra text, no watermark. 16:9 aspect ratio.
A minimalist album cover with the title 'SOFT SIGNALS' in centered elegant serif typography, artist name 'MIRA VALE' in smaller tracking below, muted blue handmade paper texture background, a small silver line illustration of a radio tower centered between the text, elegant spacing throughout, no extra text, no logo. Square 1:1 format.
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 minimalist album cover with the title 'SOFT SIGNALS' in centered elegant serif typography, artist name 'MIRA VALE' in smaller tracking below, muted blue handmade paper texture background, a small silver line illustration of a radio tower centered between the text, elegant spacing throughout, no extra text, no logo. Square 1:1 format."
}
JSON
A bookstore window poster reading 'READ MORE SLOWLY' in large serif type with a smaller line 'SPRING READING WEEK' beneath it, warm evening street reflections visible in the glass surface, cream paper texture, all typography perfectly readable, no extra words, no watermark. 4:5 aspect ratio.
curl -X POST https://runapi.ai/api/v1/gpt_image_2/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "gpt-image-2",
"prompt": "A bookstore window poster reading 'READ MORE SLOWLY' in large serif type with a smaller line 'SPRING READING WEEK' beneath it, warm evening street reflections visible in the glass surface, cream paper texture, all typography perfectly readable, no extra words, no watermark. 4:5 aspect ratio."
}
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
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.