p-video-animate

Prerequisites

Install and load these skills before generating (skip if already in context via @pruna):

Or install the full suite once: npx skills add PrunaAI/pruna-skills@pruna -y

Follow each skill's Before generating / craft sections — do not restate guide content here.

Agent habit

In the first reply, name `p-video-animate` in backticks, confirm PRUNA_API_KEY (or stop with signup links from pruna-api), then ask for required inputs. Open intake → generation-diversity clarification intake before the first POST. When drafting optional instruction_prompt, follow Prompt craft (dynamic + faithful) — do not paste skill examples. Redirect when When NOT to use fits better.

Prompt craft (dynamic + faithful)

Appearance comes from image; motion from video. Optional instruction_prompt is surgical — one concrete end beat or pose fix, not a new scene.

Fidelity check (before pay): still the user's still + template video. Repose with p-image-edit when close but not exact — do not compensate with a vague prompt.

Skill boundary

Use p-video-replace for in-place identity swap. Use this skill for motion-transfer showcases and persona variants.

When NOT to use

Use a different skill instead:

HTTP (curl)

Upload source assets

curl -X POST "https://api.pruna.ai/v1/files" \
  -H "apikey: ${PRUNA_API_KEY}" \
  -F "content=@/path/to/source-video.mp4"

curl -X POST "https://api.pruna.ai/v1/files" \
  -H "apikey: ${PRUNA_API_KEY}" \
  -F "content=@/path/to/reference-image.png"

Use each response urls.get in input.video and input.image.

Create (async — recommended)

curl -X POST 'https://api.pruna.ai/v1/predictions' \
  -H 'Content-Type: application/json' \
  -H "apikey: ${PRUNA_API_KEY}" \
  -H 'Model: p-video-animate' \
  -d '{
    "input": {
      "video": "https://api.pruna.ai/v1/files/source-video-abc123",
      "image": "https://api.pruna.ai/v1/files/reference-image-def456",
      "resolution": "720p",
      "target_fps": "original",
      "instruction_prompt": "Animate the reference subject using the motion from the source video."
    }
  }'

Poll and download: follow pruna-api. Output duration follows the source video.

Complete the random seed ritual from generation-diversity before writing prompts.

Create (sync — quick test only)

curl -X POST 'https://api.pruna.ai/v1/predictions' \
  -H 'Content-Type: application/json' \
  -H "apikey: ${PRUNA_API_KEY}" \
  -H 'Model: p-video-animate' \
  -H 'Try-Sync: true' \
  -d '{
    "input": {
      "video": "https://api.pruna.ai/v1/files/source-video-abc123",
      "image": "https://api.pruna.ai/v1/files/reference-image-def456"
    }
  }'

Before generating

1. Complete Prerequisites guide reading order (generation-diversity → video-prompting).
2. Ritual seed → draft optional dynamic + faithful instruction_prompt (section above) → confirm video (motion/audio source), image (subject), resolution, target_fps, and instruction_prompt.
3. Pruna notes: appearance from image, motion from video. Match framing/pose/limb visibility to the template’s first frame; repose with p-image-edit when close but not exact. Leave instruction_prompt blank unless you need one concrete end beat. Runware map: referenceImages[0] → image, referenceVideos[0] → video, positivePrompt → instruction_prompt, settings.preserveAudio → save_audio.

Required input

• video (string URL): source RGB .mp4
• image (string URL): reference subject to animate

Common optional fields

• resolution: 720p (default) or 1080p
• target_fps: original (default), 24, or 48
• instruction_prompt (string)
• save_audio (boolean, default true)
• seed, disable_safety_checker

Typical next steps

Common follow-ons after this skill: