Skip to main content
Kling 1.6 mi2v is a multi-image-to-video generation model from Kuaishou’s Kling series, available through AnyFast API. Upload up to 4 reference images and combine them with a text prompt to generate a cohesive video featuring all the referenced subjects.

​
Key capabilities

  • Multi-Image Input — Use up to 4 reference images as character/scene sources
  • Text-Guided — Combine images with a text prompt to control the video narrative
  • Flexible Duration — Generate 5 or 10 second videos
  • Aspect Ratios — Support for 16:9, 9:16, and 1:1 output formats
  • Standard & Pro Modes — Choose between cost-effective standard or high-quality professional output

​
Quick example

curl https://www.anyfast.ai/kling/v1/videos/multi-image2video \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model_name": "kling-v1-6",
    "image_list": [
      {"image": "https://example.com/person1.jpg"},
      {"image": "https://example.com/person2.jpg"}
    ],
    "prompt": "The two people shake hands and smile at each other",
    "duration": "5",
    "mode": "std",
    "aspect_ratio": "16:9"
  }'

​
Parameters

ParameterTypeRequiredDescription
model_namestringNoMust be kling-v1-6
image_listarrayYesReference images (1–4). Each item: {"image": "url_or_base64"}
promptstringYesText prompt (max 2500 chars)
negative_promptstringNoNegative prompt (max 2500 chars)
modestringNostd or pro. Default: std
durationstringNo5 or 10 seconds. Default: 5
aspect_ratiostringNo16:9, 9:16, or 1:1. Default: 16:9
callback_urlstringNoWebhook URL for task notifications

API Reference

View the interactive API playground for Kling 1.6 mi2v.