Image Generation

#Code examples

1curl -X POST https://api.navy/v1/images/generations \
2  -H "Authorization: Bearer sk-navy-YOUR_KEY" \
3  -H "Content-Type: application/json" \
4  -d '{
5    "model": "flux",
6    "prompt": "A naval command room at dusk, cinematic lighting",
7    "size": "1024x1024"
8  }'

#Parameters

• model (string, required) — Image model ID such as flux, dall-e-3, gpt-image-1.5
• prompt (string, required) — Text description of the desired image
• size (string, optional) — "1024x1024" or aspect ratio like "16:9"
• image_url (string, optional) — Input/reference image URL or base64 for editing
• negative_prompt (string, optional) — What to avoid in the generated image
• seed (integer, optional) — Random seed for reproducible generation
• quality (string, optional) — "low" or "medium"
• style (string, optional) — DALL·E 3: "vivid" or "natural"
• seconds (number, optional) — Video duration (0–10 seconds)
• sync (boolean, optional) — If false, returns a job ID for async polling
• response_format (string, optional) — "url" or "b64_json"
• aspect_ratio (string, optional) — Alternative to size for some models

#Notes

• Video-capable models often default to async job creation
• Compatible editing models can accept image_url
• The response usually returns a hosted URL or base64 payload
• For async jobs, see the Job Polling section