Tencent launches AI video creation tool

Chinese internet corporation Tencent introduced an artificial intelligence (AI) model on March 15 called Follow-Your-Click .

A new animation tool called Follow-Your-Click appears on Microsoft's open source site GitHub. This tool allows users to create short animated videos by clicking on parts of images and converting them into animated videos.

Some images and videos created by Follow-Your-Click. (Photo: AIbase)

This project is the result of collaboration between Tencent's Hunyuan team, Hong Kong University of Science and Technology and China's Tsinghua University.

Tencent is expected to release the full source code for the tool in April, but a trial version is already available on GitHub.

Follow-Your-Click was created to solve the problems faced by other image-to-video models on the market that tend to move the entire scene instead of focusing on specific objects. in the photo.

Other AI models ask users to provide detailed descriptions of how and where they want the image to move.

'Our framework provides simpler yet more precise user control and produces better performance than previous approaches,' the researchers wrote in the arXiv post .

Creating videos from text has become a hot topic since OpenAI introduced Sora on February 15.

Previously, in January, Tencent introduced the open source video creation and editing tool VideoCrafter2, capable of creating videos from text. This is an updated version of VideoCrafter1, released in October 2023 but limited to 2-second videos.

Tencent's Chinese rivals have also joined the race. Alibaba Group recently launched a portrait video creation tool called EMO, which turns images and audio prompts into singing and talking videos.

At roughly the same time, ByteDance released its MagicVideo-V2 text-to-video model.