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-o3-pro-reference-to-video

kling-o3-pro-reference-to-video

Kling | o3 | Pro | Referance to Video. Pro-quality video generation from reference images with start/end frame control. Triggers: reference to video, kling, o3, pro, reference, video

Independent GitHub snapshot · Automated classification · Original documentation governs

Documentation de la Skill

GitHub

name: kling-o3-pro-reference-to-video description: "Kling | o3 | Pro | Referance to Video. Pro-quality video generation from reference images with start/end frame control. Triggers: reference to video, kling, o3, pro, reference, video" allowed-tools: Bash(curl *), WebFetch

Kling | o3 | Pro | Reference to Video

Generate high-quality videos using reference images for style with start/end frame control. Pro tier delivers superior quality for reference-guided generation.

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-o3-pro-reference-to-video",
    "version": "0.0.1",
    "input": {
      "prompt": "A warrior marching through a battlefield in the style of @Image1",
      "image_urls": ["https://example.com/epic-painting.jpg"],
      "start_image_url": "https://example.com/warrior-start.jpg",
      "duration": "8",
      "aspect_ratio": "16:9"
    }
  }'

Parameters

ParameterTypeDefaultDescription
aspect_ratiostring16:9Aspect ratio. enum: 16:9, 9:16, 1:1
durationstring5Video duration in seconds (3-15s). enum: 3-15
elementsarrayfalseElements (characters/objects). Reference as @Element1, @Element2.
end_image_urlstringfalseImage for the last frame.
generate_audiobooleanfalseWhether to generate native audio.
image_urlsarrayfalseReference images. Reference as @Image1, @Image2.
multi_promptarrayfalseList of prompts for multi-shot generation.
promptstringfalseText prompt. Either prompt or multi_prompt required.
shot_typestringcustomizeMulti-shot generation type. enum: customize
start_image_urlstringfalseImage for the first frame.

Examples

Reference-guided cinematic video:

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "model": "kling-o3-pro-reference-to-video",
    "version": "0.0.1",
    "input": {
      "prompt": "A fantasy dragon flying over mountains in the visual style of @Image1",
      "image_urls": ["https://example.com/fantasy-art.jpg"],
      "duration": "12",
      "aspect_ratio": "16:9",
      "generate_audio": true
    }
  }'

Transition between frames with reference style:

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "model": "kling-o3-pro-reference-to-video",
    "version": "0.0.1",
    "input": {
      "prompt": "A smooth scene transition from forest to ocean in @Image1 painterly style",
      "image_urls": ["https://example.com/impressionist.jpg"],
      "start_image_url": "https://example.com/forest.jpg",
      "end_image_url": "https://example.com/ocean.jpg",
      "duration": "10"
    }
  }'

Related Models

Documentation

Skills enregistrées