Is China pulling ahead in AI video synthesis? We put Minimax to the test
Briefly

The Minimax video-01 model demonstrates improvements in realism and detail in some outputs, but also retains quirks similar to Gen-3, presenting challenges in synthesis.
The results showcase creative possibilities, such as a muscular barbarian breaking a CRT television, but highlight significant limitations, including unrealistic scenarios and incomplete animations.
Read at Ars Technica
[
|
]