Ad
Skip to content

KLING AI video generator allows users to train their own AI video characters

Image description
kling.kuaishou.com

KLING, an AI video generator, is testing a new feature called "Custom Models" that significantly improves character consistency in generated videos.

The Chinese AI video generator KLING introduced the "Custom Models" feature that lets users train their own video characters and use them consistently across different scenes.

Early testers on X demonstrate that users can train characters by uploading 10 to 30 videos, each at least 10 seconds long. Unlike traditional image models, KLING uses video footage for training. The training material can include AI-generated videos from KLING itself.

After training, users tag the trained character model in the prompt and describe the desired scene. The system then generates videos with consistent character representation, whether in 360-degree rotations or more complex scenes with time-shifted facial shots and various camera angles. Creator Halim Alrasihi showcases examples of these capabilities on X.

Ad
DEC_D_Incontent-1

KLING establishes itself in the AI video market

Developed by Chinese company Kuaishou, KLING launched its international version in July 2023. The current KLING 1.5 version supports 1080p HD resolution videos and offers various formats including landscape (16:9, 4:3), portrait (9:16, 3:4), and square (1:1).

Beyond the new Custom Models feature, one of KLING's key functions is the "Motion Brush." This tool allows users to precisely define the movement of individual elements within an image. Users can register with an email address and receive 66 free daily credits for video creation.

AI News Without the Hype – Curated by Humans

As a THE DECODER subscriber, you get ad-free reading, our weekly AI newsletter, the exclusive "AI Radar" Frontier Report 6× per year, access to comments, and our complete archive.

Source:
  • The KLING AI video generator introduces 'Custom Models' a feature that allows users to train their own video characters. Users upload between 10 and 30 videos of at least 10 seconds in length.
  • The system uses video footage instead of images for training and can consistently display the trained characters in different scenes - from 360-degree rotations to complex shots with different camera angles.
  • Developed by Chinese company Kuaishou KLING version 1.5 offers 1080p HD video multiple image formats and a 'Motion Brush' for precise motion control.