ReplicateImage to videoComing soon

prunaai/p-video-2

Name: prunaai/p-video-2
Brand: Replicate

prunaai/p-video-2 is an image to video tool from Replicate 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	—	Text prompt for video generation.
`fps`	JSON	24	Frames per second of the video.
`seed`	number (whole)	—	Random seed. Set for reproducible generation.
`audio`	URL or file	—	Input audio to condition video generation. Supports flac, mp3, wav.
`draft`	true or false	false	Draft mode. Generates a lower-quality preview of the video.
`image`	URL or file	—	Input image to generate video from (image-to-video). Supports jpg, jpeg, png, webp.
`no_op`	true or false	false	Health check mode - returns status without inference.
`duration`	number (whole) 1 to 20	—	Duration of the video in seconds (1-20). Leave empty to let the model choose length from the prompt. Ignored when audio is provided.
`resolution`	JSON	720p	Resolution of the video.
`save_audio`	true or false	true	Save the video with audio.
`aspect_ratio`	JSON	16:9	Aspect ratio of the video. Ignored when an input image is provided.
`last_frame_image`	text	—	Reference image for the last frame of the video. Supports jpg, jpeg, png, webp.
`prompt_upsampling`	true or false	true	Use prompt upsampling to enhance the prompt.

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": "replicate",
    "model": "prunaai/p-video-2",
    "input": {
      "prompt": "<prompt>"
    }
  }'