Baidu Steam Engine Video Generator Upgrades to Version 2.0, Prices Reduced to 70% of Industry Standard.
Baidu's integrated audio-video model, Baidu Steam Engine, has announced an upgrade, becoming the first in the industry to achieve multi-person audio-video integration generation. Its Turbo, Lite, Pro, and Full Voice versions are all open for users to experience by searching "Baidu Steam Engine" on Baidu or logging into the "Hui Xiang" platform. Enterprise users can enjoy high-performance video generation services on the Qianfan platform.
According to reports, Baidu Steam Engine is the world's first Chinese audio-video integrated generation I2V model, featuring innovative multimodal latent space planning technology that can autonomously coordinate multiple role identities, emotions, and interaction logic. It also includes deep Chinese scene adaptation, accurately presenting Chinese voice details and emotional expressions with over 98% fidelity. In terms of effects, it can achieve movie-level high-definition video, realistic environmental sound effects, and synchronous output of natural human voices.
Baidu officials also stated that this series of large models has been applied in various scenarios such as Baidu search and marketing, with pricing set as low as 70% of the industry standard.
Latest