Upsampler

Parameters

promptstringrequiredin body

Text prompt describing the video to generate

imagestringoptionalin body

Optional source image URL to animate (image-to-video). When provided, the model animates this image guided by prompt; output dimensions auto-fit the image. Omit for pure text-to-video

modelenumoptionalin body

Model. Only wan (Wan 2.2 5B, fast 4-step) is available. Default wan Values: wan.

durationnumberoptionalin body

Video length in seconds (1-8). Default 2

widthnumberoptionalin body

Output width px, multiple of 32 (256-1024). Default 704

heightnumberoptionalin body

Output height px, multiple of 32 (256-1024). Default 704

seednumberoptionalin body

Seed for reproducibility. Default random

negativePromptstringoptionalin body

Things to avoid in the video. Has a sensible default

stepsnumberoptionalin body

Inference steps (1-8). More steps = higher quality but slower. Default 4

guidancenumberoptionalin body

Guidance scale (0-5). Higher = follow prompt more strictly. Default 0 (recommended for the fast model)

Request

curl -X POST "https://api.zapi.ink/v1/ai:upsampler/generate" \
  -H "x-api-key: zpi_xxxxxxxxxxxxxxxxxxxxxxxx"

Example response

{
  "mode": "text-to-video",
  "seed": 1234567,
  "model": "wan",
  "steps": 4,
  "width": 704,
  "height": 704,
  "prompt": "a red sports car driving on a coastal road at sunset, cinematic motion",
  "status": "completed",
  "videos": [
    {
      "url": "https://<upstream>/file/tmp/abc123/output.mp4",
      "width": 704,
      "height": 704,
      "durationSeconds": 2
    }
  ],
  "duration": 2,
  "guidance": 0,
  "provider": "upsampler",
  "elapsedMs": 41230
}