Southern European hidden side street in late morning light, terracotta walls with layers of peeling cream, ochre, and dusty rose paint, narrow cobblestone lane, clay flower pots on iron-railed windowsills, single vintage bicycle leaning against a weathered wall, bougainvillea creating dappled shadows on the ground, travel photography with 28mm lens at mid-aperture
curl -X POST https://runapi.ai/api/v1/runapi/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"prompt": "Southern European hidden side street in late morning light, terracotta walls with layers of peeling cream, ochre, and dusty rose paint, narrow cobblestone lane, clay flower pots on iron-railed windowsills, single vintage bicycle leaning against a weathered wall, bougainvillea creating dappled shadows on the ground, travel photography with 28mm lens at mid-aperture"
}
JSON
City avenue reclaimed by nature twenty years after human abandonment, cracked asphalt split by tree roots pushing through, retail storefronts with shattered windows and young trees growing through the roofs, afternoon green-filtered light through the overhead canopy, muted greens, grey concrete, rust, and pale sky, quiet melancholy tone, photorealistic post-apocalyptic landscape
curl -X POST https://runapi.ai/api/v1/runapi/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"prompt": "City avenue reclaimed by nature twenty years after human abandonment, cracked asphalt split by tree roots pushing through, retail storefronts with shattered windows and young trees growing through the roofs, afternoon green-filtered light through the overhead canopy, muted greens, grey concrete, rust, and pale sky, quiet melancholy tone, photorealistic post-apocalyptic landscape"
}
JSON
Floating rocky island archipelago above a vast cloud sea, each island hosting a different ecosystem — tropical jungle, walled medieval city, bare windswept cliffs — all connected by precarious rope bridges swaying in the wind, warm late afternoon light from the right, deep blue cloud sea below, saturated greens, warm sandstone, and deep azure sky, epic fantasy concept art
curl -X POST https://runapi.ai/api/v1/runapi/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"prompt": "Floating rocky island archipelago above a vast cloud sea, each island hosting a different ecosystem — tropical jungle, walled medieval city, bare windswept cliffs — all connected by precarious rope bridges swaying in the wind, warm late afternoon light from the right, deep blue cloud sea below, saturated greens, warm sandstone, and deep azure sky, epic fantasy concept art"
}
JSON
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
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.