PROMPTS BY MODALITY

Image Prompts — 1438 curated examples

Prompt examples tuned for Image generation workflows across RunAPI models. Filter by category, copy the prompt, or open the model-specific API code.

IM
Image
architecture nano-banana-pro

Modern architecture — cantilevered concrete house

Architectural photograph of a striking modernist house built into a hillside. The structure features a massive cantilevered concrete volume extending over a slope covered in wild grasses. Floor-to-ceiling glass walls on the underside of the cantilever create a floating living space. Raw board-formed concrete with visible wood grain texture. A narrow infinity pool runs along the front edge, reflecting overcast sky. Surrounded by mature eucalyptus trees. Shot from a low angle emphasizing the dramatic overhang. Architectural Digest editorial style, golden hour lighting.

View API Code
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-pro",
  "prompt": "Architectural photograph of a striking modernist house built into a hillside. The structure features a massive cantilevered concrete volume extending over a slope covered in wild grasses. Floor-to-ceiling glass walls on the underside of the cantilever create a floating living space. Raw board-formed concrete with visible wood grain texture. A narrow infinity pool runs along the front edge, reflecting overcast sky. Surrounded by mature eucalyptus trees. Shot from a low angle emphasizing the dramatic overhang. Architectural Digest editorial style, golden hour lighting."
}
JSON
FAQ

Working with Image prompts

What makes a good %{model} prompt?

A useful %{model} prompt names the subject, style, constraints, and output intent clearly. The examples here are short enough to copy, but specific enough for an agent or backend job to preserve the generation goal.

Can I reuse these prompts across models?

Often, yes. Start with a prompt in this modality, then adjust model-specific fields such as aspect ratio, duration, voice settings, or style controls. The detail page shows any saved parameters next to the prompt text.

Where do I find the right model slug?

Every card shows the RunAPI model slug. Open the model page when you want only examples for one model, or follow the model catalog link for pricing and capability details before making a request.

Can agents call these prompts directly?

Yes. After installing the RunAPI MCP Server, paste the agent instruction from a prompt detail page. The page keeps the prompt text, model slug, and endpoint path together so the agent has enough context.