falImage to jsonComing soon

fal-ai/vggt-1b

Name: fal-ai/vggt-1b
Brand: fal

fal-ai/vggt-1b is an image to json tool from fal that runs in the background and returns structured JSON. Coming soon: listed with its price, not yet open to runs.

This tool is listed but not yet available to run.

Price pending

Pricing

Price pending.

Limits

Runs: In the background
Returns: json
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
`image_urls`	URLs or files	—	Input images to reconstruct. Accepts JPEG, PNG, WEBP and the other formats Pillow decodes. Images are padded to a square and resized so the longest side is 518 pixels.
`video_url`	URL or file	—	Optional input video. Frames are sampled every `frame_sampling_rate`-th frame (the first and last frames are always included) and appended after `image_urls`.
`frame_sampling_rate`	number (whole) 1 to 1000	24	Sample every n-th frame of `video_url`. The first and last frames of the video are always included. Ignored when no video is given.
`alpha_blend_onto`	one of keep, white, black, mean	white	How to handle images with an alpha channel. 'white'/'black' composite onto that background, 'mean' composites onto the ImageNet mean RGB, and 'keep' discards alpha and keeps the original pixel values.
`export_prediction_data`	true or false	true	Return one JSON file per frame with the raw model outputs (camera pose encoding, depth, depth confidence, mask).
`export_depth_maps`	true or false	true	Return one 16-bit grayscale PNG depth raster per frame. Pixel values map linearly from `depth_range` onto 0-65535.
`export_point_cloud`	true or false	true	Return a GLB scene holding the fused coloured point cloud plus a cone mesh per estimated camera.
`array_encoding`	one of base64, list	base64	How arrays are encoded inside the prediction JSON files. 'base64' emits {data, shape, dtype} objects; 'list' emits nested JSON lists, which are far larger.
`exclude_keys`	list	—	Keys to omit from each prediction JSON file.
`confidence_percentile`	number 0 to 100	50	Drop this percentage of the lowest-confidence points before building the point cloud. 0 keeps every point.
`max_points`	number (whole) 1000 to 5000000	250000	Upper bound on the number of points written to the GLB. Points above the default 250,000-point budget are evenly subsampled to limit GLB serialization and upload latency.

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/vggt-1b",
    "input": {}
  }'