Tencent heats up AI video-generation competition in China with new open-source product
Tencent has intensified competition in China's AI video-generation sector by launching its open-source HunyuanVideo-I2V model for developers. This image-to-video model, building upon Tencent's HunyuanVideo foundation model, enables users to transform static photos into high-resolution, five-second video clips using short text prompts.
The new model is accessible on platforms like GitHub and HuggingFace, and it allows users to add lip-synched voice and background sound effects to their videos. This move comes amid growing competition from companies like Kuaishou, ByteDance, and Alibaba, all vying for dominance in China's burgeoning AI video-generation market, spurred by OpenAI's Sora model. Tencent claims HunyuanVideo is the world's largest open-source model for video generation.
via SCMP Full Text Feed
Tencent has intensified competition in China's AI video-generation sector by launching its open-source HunyuanVideo-I2V model for developers. This image-to-video model, building upon Tencent's HunyuanVideo foundation model, enables users to transform static photos into high-resolution, five-second video clips using short text prompts.
The new model is accessible on platforms like GitHub and HuggingFace, and it allows users to add lip-synched voice and background sound effects to their videos. This move comes amid growing competition from companies like Kuaishou, ByteDance, and Alibaba, all vying for dominance in China's burgeoning AI video-generation market, spurred by OpenAI's Sora model. Tencent claims HunyuanVideo is the world's largest open-source model for video generation.
via SCMP Full Text Feed
