The interface is localized. Skill descriptions and documents are machine-translated by AI into your language; code, commands, paths and technical terms stay in the original, and the author's document governs.
Explore skills
Productivity · SKILL.md

wan-v2-2-14b-animate-move

wan-v2-2-14b-animate-move

Wan | v2.2 14B | Animate | Move. Animate images with motion transfer from reference video using Wan v2.2 14B. Triggers: wan, animate, move, motion transfer, image animation, wan 14b

Independent GitHub snapshot · Automated classification · Original documentation governs

Skill documentation

GitHub

name: wan-v2-2-14b-animate-move description: "Wan | v2.2 14B | Animate | Move. Animate images with motion transfer from reference video using Wan v2.2 14B. Triggers: wan, animate, move, motion transfer, image animation, wan 14b" allowed-tools: Bash(curl *), WebFetch

Wan | v2.2 14B | Animate | Move

Animate still images with motion patterns transferred from reference videos using the Wan v2.2 14B model. The subject in the image adopts the movement from the reference video.

Quick Start

Requires an each::labs API key. Get one at eachlabs.ai.

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "model": "wan-v2-2-14b-animate-move",
    "version": "0.0.1",
    "input": {
      "image_url": "https://example.com/person-standing.jpg",
      "video_url": "https://example.com/dance-reference.mp4",
      "resolution": "720p",
      "num_inference_steps": 20,
      "video_quality": "high"
    }
  }'

Parameters

ParameterTypeDefaultDescription
enable_safety_checkerbooleanfalseIf true, input data will be checked for safety
image_urlstringURL of the input image to animate
num_inference_stepsinteger20Number of inference steps. Higher = better quality, slower
resolutionstring480pResolution of the generated video. enum: 480p, 580p, 720p
seedintegerRandom seed for reproducibility
shiftnumber5Shift value for the video (1.0 to 10.0)
video_qualitystringhighOutput video quality. enum: low, medium, high, maximum
video_urlstringURL of the reference motion video
video_write_modestringbalancedOutput video write mode. enum: fast, balanced, small

Examples

High-quality dance animation:

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "model": "wan-v2-2-14b-animate-move",
    "version": "0.0.1",
    "input": {
      "image_url": "https://example.com/character-portrait.jpg",
      "video_url": "https://example.com/choreography.mp4",
      "resolution": "720p",
      "num_inference_steps": 30,
      "video_quality": "maximum",
      "shift": 5,
      "seed": 42
    }
  }'

Quick preview animation:

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "model": "wan-v2-2-14b-animate-move",
    "version": "0.0.1",
    "input": {
      "image_url": "https://example.com/figure.jpg",
      "video_url": "https://example.com/walking-motion.mp4",
      "resolution": "480p",
      "num_inference_steps": 15,
      "video_quality": "medium",
      "video_write_mode": "fast"
    }
  }'

Related Models

Documentation

Saved skills