falVideo to videoComing soon
luma/agent/ray/v3.2/video-to-video
luma/agent/ray/v3.2/video-to-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.
Priced by usagePricing
duration: 5s (default) $0.195, 10s $0.39, otherwise $0.39 per run. The final charge comes from usage.
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 required | text | — | Text prompt describing how to edit the source video. |
video_url required | URL or file | — | URL of the source video to edit. |
user | text | — | Optional opaque identifier for the end user making the request. Used only for abuse attribution; never interpreted by fal. |
start_image_url | URL or file | — | Optional URL of an image to use as the edited video's first frame — e.g. a restyled version of the source's opening frame to steer the look of the edit. Leave unset to let the model derive the first frame from the source video. |
resolution | one of 540p, 720p, 1080p | 540p | Resolution of the edited video. Higher resolutions cost more. |
duration | one of 5s, 10s | 5s | Duration of the edited video. |
edit_strength | one of adhere_1, adhere_2, adhere_3, flex_1, flex_2, flex_3, reimagine_1, reimagine_2, reimagine_3 | — | How closely the edit preserves the source video. 'adhere_*' stays closest to the source, 'flex_*' is balanced, and 'reimagine_*' diverges most. Leave unset to use Luma's default. Cannot be combined with auto_controls. |
auto_controls | true or false | false | Let the model derive the edit conditioning schedule from the source video. Cannot be combined with edit_strength. |
hdr | true or false | false | Generate an HDR-encoded MP4. Requires HDR access on the account and a resolution of 720p or 1080p. |
exr_export | true or false | false | Also export an EXR file alongside the MP4. Requires hdr=true and HDR access. |
controls | JSON | — | Per-signal conditioning controls (pose, depth, normals, trajectory, face) for finer control than edit_strength. Cannot be combined with auto_controls. |
keyframes | list | — | Multi-keyframe edit guide frames: up to 64 image URLs pinned at the source-frame positions given by keyframe_indexes. Mutually exclusive with start_image_url. Provide keyframes and keyframe_indexes together (same length). |
keyframe_indexes | list | — | Source-video frame positions where each keyframes[i] is anchored. Non-negative, unique, and the same length as keyframes. |
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": "luma/agent/ray/v3.2/video-to-video",
"input": {
"prompt": "Restyle the footage as a hand-painted watercolor animation with soft pastel colors.",
"video_url": "https://storage.googleapis.com/falserverless/example_inputs/birefnet-video-input.mp4"
}
}'