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
food gpt-4o-image

Food photography — artisan sourdough bread

Overhead food photography of a freshly baked round sourdough boule on a rustic wooden cutting board. The bread has been sliced to reveal the open, airy crumb structure with large irregular holes. A bread knife with a dark wood handle rests beside it. Scattered flour dusts the board and surrounding dark slate countertop. A small ceramic bowl of salted butter sits in the upper right corner. Natural side lighting from a kitchen window creates long soft shadows. Warm tones, high detail on the crust texture showing deep caramelization and ear scoring patterns.

View API Code
curl -X POST https://runapi.ai/api/v1/gpt_4o_image/text_to_image \
  -H "Authorization: Bearer $RUNAPI_KEY" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'JSON'
{
  "model": "gpt-4o-image",
  "prompt": "Overhead food photography of a freshly baked round sourdough boule on a rustic wooden cutting board. The bread has been sliced to reveal the open, airy crumb structure with large irregular holes. A bread knife with a dark wood handle rests beside it. Scattered flour dusts the board and surrounding dark slate countertop. A small ceramic bowl of salted butter sits in the upper right corner. Natural side lighting from a kitchen window creates long soft shadows. Warm tones, high detail on the crust texture showing deep caramelization and ear scoring patterns."
}
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.