L’interface est localisée ; les présentations et documents des Skills sont traduits automatiquement par IA dans votre langue. Le code, les commandes, chemins et termes techniques restent en version originale, et le document de l’auteur fait foi.
Explorer les Skills
Productivité · SKILL.md

kling-v3-standard-motion-control

kling-v3-standard-motion-control

Kling | v3 | Standard | Motion Control. Generate videos with motion from reference video and character from reference image. Triggers: motion control, kling, v3, video, animation, character

Independent GitHub snapshot · Automated classification · Original documentation governs

Documentation de la Skill

GitHub

name: kling-v3-standard-motion-control description: "Kling | v3 | Standard | Motion Control. Generate videos with motion from reference video and character from reference image. Triggers: motion control, kling, v3, video, animation, character" allowed-tools: Bash(curl *), WebFetch

Kling | v3 | Standard | Motion Control

Generate videos by combining a reference image (for appearance) with a reference video (for motion). Transfer character actions from a video onto a new character from an image.

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": "kling-v3-standard-motion-control",
    "version": "0.0.1",
    "input": {
      "prompt": "A person dancing gracefully",
      "image_url": "https://example.com/character.jpg",
      "video_url": "https://example.com/dance-reference.mp4",
      "character_orientation": "video",
      "keep_original_sound": true
    }
  }'

Parameters

ParameterTypeDefaultDescription
character_orientationstringvideoControls whether output character orientation matches the reference image or video. enum: image, video
elementsarrayfalseOptional element for facial consistency binding.
image_urlstringfalseReference image URL. Characters and elements in the generated video match this image.
keep_original_soundbooleantrueWhether to keep the original sound from the reference video.
promptstringfalseText prompt describing the desired output.
video_urlstringfalseReference video URL. Character actions in the generated video follow this video.

Examples

Dance motion transfer:

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "model": "kling-v3-standard-motion-control",
    "version": "0.0.1",
    "input": {
      "prompt": "A character performing an energetic hip-hop dance",
      "image_url": "https://example.com/cartoon-character.png",
      "video_url": "https://example.com/hiphop-dance.mp4",
      "character_orientation": "video"
    }
  }'

Motion transfer with image orientation:

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "model": "kling-v3-standard-motion-control",
    "version": "0.0.1",
    "input": {
      "prompt": "A person waving and smiling at the camera",
      "image_url": "https://example.com/portrait.jpg",
      "video_url": "https://example.com/waving-motion.mp4",
      "character_orientation": "image",
      "keep_original_sound": false
    }
  }'

Related Models

Documentation

Skills enregistrées