ReplicateText to videoComing soon
Replicatewan-video/wan-2.1-1.3b
wan-video/wan-2.1-1.3b is a text to video tool from Replicate 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.
Priced by usagePricing
$0.26 per video.
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
| Field | Kind | Default | Description |
|---|---|---|---|
prompt required | text | — | Text prompt describing what you want to generate |
seed | number (whole) | — | Random seed for reproducible results (leave blank for random) |
frame_num | JSON | 81 | Video duration in frames (based on standard 16fps playback) |
resolution | JSON | 480p | Video resolution |
aspect_ratio | JSON | 16:9 | Video aspect ratio |
sample_shift | number 0 to 20 | 8 | Sampling shift factor for flow matching (recommended range: 8-12) |
sample_steps | number (whole) 10 to 50 | 30 | Number of sampling steps (higher = better quality but slower) |
sample_guide_scale | number 0 to 20 | 6 | Classifier free guidance scale (higher values strengthen prompt adherence) |
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": "replicate",
"model": "wan-video/wan-2.1-1.3b",
"input": {
"prompt": "<prompt>"
}
}'