Kling 2.6 i2v

Kuaishou Kling 2.6 image-to-video with start/end frames, motion brush, camera control, and native audio.

Kling 2.6 i2v is an image-to-video model from Kuaishou’s Kling series, available through AnyFast API. Transform images into video with start/end frames, camera movements, motion brushes, and native audio.

Key capabilities

• Image-to-Video — Generate videos from first frame and/or end frame reference images
• Camera Control — Preset and custom camera movements (pan, tilt, zoom, roll)
• Motion Brush — Static and dynamic brush masks for precise motion control
• Native audio — Generate synchronized audio or reference reusable voices
• Standard & Pro Modes — Choose between cost-effective standard or high-quality professional output

Quick example

cURL

curl https://www.anyfast.ai/kling/v1/videos/image2video \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model_name": "kling-2.6",
    "image": "https://example.com/photo.jpg",
    "prompt": "The person smiles and waves to the camera",
    "duration": "5",
    "mode": "std"
  }'

Parameters

Parameter	Type	Required	Description
model_name	string	No	Must be kling-2.6
image	string	Conditional	First frame image (Base64 or URL)
image_tail	string	Conditional	End frame image (Base64 or URL)
prompt	string	Conditional	Text prompt (max 2500 chars)
negative_prompt	string	No	Negative prompt (max 2500 chars)
mode	string	No	std or pro. Default: std
duration	string	No	5 or 10 seconds. Default: 5
voice_list	object[]	No	Up to two Voice Management IDs
camera_control	object	No	Camera movement control
sound	string	No	on or off. Default: off (V2.6+ only)

API Reference

View the interactive API playground for Kling 2.6 i2v.