HedraImage to videoComing soon

minimax-h3-max-camera-controls

minimax-h3-max-camera-controls is an image to video tool from Hedra that runs in the background and returns video. Coming soon: listed with its price, not yet open to runs.

This tool is listed but not yet available to run.

Price pending

Pricing

Price pending.

Limits

Runs
In the background
Returns
video
Longest queue wait
3600s
Run deadline
3600s
Largest inline input
1024 KB
Largest input file
500 MB
Largest output
4768 MB
Outputs per run
16

Input

FieldKindDefaultDescription
prompt requiredtext—Generation prompt. From 1 to 50000 characters.
resolution requiredone of
480p, 768p
—Output resolution.
duration_ms requiredone of
5000, 6000, 7000, 8000, 9000, 10000, 11000, 12000, 13000, 14000, 15000
—Duration in ms.
start_image requiredJSON—A file uploaded via POST /v3/files, referenced by the returned url.
camera_trajectory requiredJSON—Camera path through the scene, as poses ordered by strictly increasing `time`. The first pose holds until its `time` and the last holds to the end of the clip; the camera interpolates between them. `time` runs 0 (start) to 1 (end), `azimuth` is the horizontal angle around the subject in degrees, `elevation` the vertical angle in degrees from -90 to 90, and `distance` the distance from the subject in scene units (above 0; 1 is where the input frame sits). Consecutive azimuths may travel at most 32 full turns in total. 2 to 12 items.
num_outputsone of
1
1Number of outputs generated per job. Only 1 is supported.

Same request in code

curl https://api.spiral.ai/v1/runs \
  -H "Authorization: Bearer $SPIRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
    "provider": "hedra",
    "model": "minimax-h3-max-camera-controls",
    "input": {
      "prompt": "<prompt>",
      "resolution": "480p",
      "duration_ms": 5000,
      "start_image": {},
      "camera_trajectory": {}
    }
  }'