[KongchangAI]
Model

LongCat Video Avatar 1.6

An audio-driven digital human video generation model that supports continuous generation of digital human videos.

Timeline (last 90 days)

Nov 18

Meituan open-sourced its new-generation audio-driven digital human model LongCat Video Avatar 1.6 on the ModelScope community under the MIT license, which can extend continuously generated digital human videos to more than 10 minutes, improves lip sync and body movements, and provides INT8 quantized weights.

Unverified60%
Nov 18

LongCat Video Avatar 1.6 ranked second in an Arena human preference blind test with more than 30,000 votes.

Unverified50%

All Facts (2)

Source Articles