WaveSpeedVideo to videoComing soon

wavespeed-ai/ltx-2-19b/control

Name: wavespeed-ai/ltx-2-19b/control
Brand: WaveSpeed

wavespeed-ai/ltx-2-19b/control is a video to video tool from WaveSpeed 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` required	URL or file	—	The video for generating the output.
`mode`	one of pose, depth, canny	pose	The control mode for video generation. Pose: skeleton/pose guidance. Canny: edge detection guidance. Depth: depth map guidance.
`seed`	number (whole)	—	The random seed to use for the generation. -1 means a random seed will be used.
`image`	URL or file	—	Optional reference image for appearance guidance. If not provided, the model generates based on the prompt.
`prompt`	text	—	The positive prompt for the generation.
`audio_mode`	one of preserve, generate, none	preserve	Audio handling mode. Preserve: keep original audio from input video. Generate: create new synchronized audio. None: output video without audio.
`resolution`	one of 480p, 720p, 1080p	720p	The resolution of the output 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": "wavespeed",
    "model": "wavespeed-ai/ltx-2-19b/control",
    "input": {
      "video": "<video>"
    }
  }'