falVideo to videoComing soon
minimax/h3-max/reframe-video
minimax/h3-max/reframe-video is a video to video tool from fal 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 pendingPricing
Price pending.
Limits
- Runs
- In the background
- Returns
- video
- Longest queue wait
- 3600s
- Run deadline
- 1800s
- Largest inline input
- 1024 KB
- Largest input file
- 500 MB
- Largest output
- 4768 MB
- Outputs per run
- 16
Input
| Field | Kind | Default | Description |
|---|---|---|---|
prompt | text | Optional guidance for the new surroundings. Expansion captions the source automatically. | |
video_url required | URL or file | — | Source video, 0.25 to 300 seconds; fitted onto the target canvas with its timeline and audio preserved. |
aspect_ratio | one of 16:9, 9:16, 1:1, 4:3, 3:4, 21:9, 9:21 | 16:9 | Target canvas aspect ratio; the source is contain-fitted and the rest is outpainted. |
resolution | one of 480p, 768p, 1080p | 768p | Target canvas resolution profile. 1080p uses learned latent upscaling from a native 768p reframe. |
seed | number (whole) 0 to 4294967295 | — |
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": "fal",
"model": "minimax/h3-max/reframe-video",
"input": {
"video_url": "<video_url>"
}
}'