Integrate Prodia's `inference.minimax.h3.fast.txt2vid.v1` using https://docs.prodia.com/llms.txtAPI request
curl -X POST https://inference.prodia.com/v2/job \
-H "Authorization: Bearer $PRODIA_TOKEN" \
-H "Content-Type: application/json" \
-H "Accept: video/mp4" \
-d '{
"type": "inference.minimax.h3.fast.txt2vid.v1",
"config": {
"prompt": "a dancing cat under moonlight",
"duration": 6,
"aspect_ratio": "16:9",
"resolution": "768P"
}
}'Input
Description of the desired video and audio.
Duration of the video in seconds. Rounded up to the model's frame grid (4 s returns 4.46 s, 15 s returns 15.08 s).
Controls the approximate aspect ratio of the resulting video.
Only 768P is supported: the canvas targets a 768px short edge with a 768x1344 pixel area cap and 32px rounding; exact width and height follow the selected aspect ratio.
Seed for reproducible generation. Random when omitted.
Output
Elapsed0.00s