WaveSpeedImage to videoComing soon

wavespeed-ai/wan-2.1-14b-vace

Name: wavespeed-ai/wan-2.1-14b-vace
Brand: WaveSpeed

wavespeed-ai/wan-2.1-14b-vace is an image 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: 3600s
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	—
`seed`	number (whole)	—	The random seed to use for the generation. -1 means a random seed will be used.
`size`	one of 832480, 480832, 1280720, 7201280	832*480	The size of the generated media in pixels (width*height).
`task`	one of depth, pose, face, inpainting, none	depth	Extract control information from the provided video to guide video generation.
`image`	URL or file	—	URL of the first image.
`video`	URL or file	—	The video for generating the output.
`images`	list	—	URL of ref images to use while generating the video.
`duration`	number (whole) 5 to 10	5	The duration of the generated media in seconds.
`flow_shift`	number 0 to 30	16	The shift value for the timestep schedule for flow matching.
`last_image`	URL or file	—	URL of the last image.
`mask_image`	URL or file	—	URL of the mask image.
`mask_video`	text	—	URL of the mask video.
`context_scale`	number 0 to 2	1	Controls how close you want the model to stick to the reference context.
`guidance_scale`	number 0 to 20	5	The guidance scale to use for the generation.
`negative_prompt`	text	—	The negative prompt for the generation.
`num_inference_steps`	number (whole) 1 to 40	30	The number of inference steps to perform.

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/wan-2.1-14b-vace",
    "input": {
      "prompt": "<prompt>"
    }
  }'