falVideo to videoComing soon

minimax/h3-max/3d-to-video

Name: minimax/h3-max/3d-to-video
Brand: fal

minimax/h3-max/3d-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.

Price pending

Pricing

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
`video_url` required	URL or file	—	Blender video, up to 15 seconds and 32 shots, at a public HTTPS URL.
`prompt`	text	—	Optional clarification of what your proxies represent or how they move, for example: 'The moving block represents a running person.' Camera, trajectories, timing and object count remain defined by the video.
`reference_image_urls`	URLs or files	—	Optional environment, subject, interior or detail references. When supplied, uses these images directly without visual planning or generating new images; Scene Intent is optional. Without references, automatically creates appearance references within your new-image limit. Camera and movement always come from the video.
`max_generated_reference_images`	number (whole) 1 to 8	2	Maximum NEW images to generate when no reference images are supplied. Ignored when reference images are supplied. Uses fewer when enough views are covered. Uncovered shots stay in the video.
`resolution`	one of 480P, 768P, 1080P	768P	Output quality. Duration is taken automatically from the video.

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/3d-to-video",
    "input": {
      "video_url": "<video_url>"
    }
  }'