falVideo to videoComing soon

fal-ai/depth-anything-video

fal-ai/depth-anything-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 usage

Pricing

$0.052 per second. Measured from the input file. 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

FieldKindDefaultDescription
video_url requiredURL or file—URL of the input video to estimate depth for.
modelone of
VDA-Small, VDA-Base, VDA-Large
VDA-LargeDepth estimation model size. VDA-Large = best quality, VDA-Small = fastest.
colormapone of
grayscale, turbo, inferno, magma, viridis
grayscaleColormap for depth visualization. 'turbo' (recommended) shows near=warm, far=cool. 'grayscale' for raw normalized depth. 'inferno'/'magma' for perceptually uniform. 'viridis' for colorblind-friendly.
resolutionone of
auto, 360p, 480p, 720p, 1080p
autoOutput resolution. 'auto' preserves input (max 1080p). Options: 'auto', '360p', '480p', '720p', '1080p'.
max_framesnumber (whole)—Max frames to process (max 2400). None = up to 2400.
output_fpsnumber—Output video FPS. None = same as input.
side_by_sidetrue or falsefalseOutput original | depth comparison video.
include_raw_depthstrue or falsefalseExport raw float32 depths as .npz file with: 'depths' [N,H,W], 'min_depth', 'max_depth', 'fps', 'model', 'shape'.

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": "fal-ai/depth-anything-video",
    "input": {
      "video_url": "https://v3b.fal.media/files/b/0a8fb1c1/xNTrr7wtczzLBkJdyE5_f_7JTYCmQe.mp4"
    }
  }'