ReplicateImage to videoComing soon

prunaai/p-video-2-pro-avatar

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

prunaai/p-video-2-pro-avatar 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
`image` required	URL or file	—	Portrait of the person who speaks (first frame). Supports jpg, jpeg, png, webp.
`seed`	number (whole)	—	Random seed for reproducible generation.
`audio`	URL or file	—	Speech audio, up to 3 minutes; the video matches its length. Overrides voice_script.
`voice`	JSON	Zephyr (Female)	Gemini TTS voice for voice_script.
`prompt`	text	The person is talking.	What the video should show.
`resolution`	JSON	768p	Video resolution. 1080p, 2k and 4k generate at 768p and upscale it (24 fps kept); 4k is limited to 125 s of audio.
`voice_prompt`	text	Say the following.	Delivery instructions for the TTS voice (tone, pacing, accent, emotion). Not spoken.
`voice_script`	text		Exact words to speak with Gemini TTS. Required when no audio is uploaded.
`voice_language`	JSON	English (US)	Language of voice_script.
`prompt_upsampling`	true or false	true	Let a vision model look at the image and append the scene's own motion (rain, lights, background, body movement) to your prompt. Your words stay unchanged and come first.

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-pro-avatar",
    "input": {
      "image": "<image>"
    }
  }'