June 10 (Bloomberg) - ByteDanceVolcano EngineThe official public website announced today that it will be released on June 11thall-newBean curdVideo Generation Model.
According to reports, the new beanbag video generation model has a number of "hardcore capabilities", 1AI with examples as follows:
- Supports seamless multi-camera narrativesThat is, through efficient model structure, multimodal positional coding and multitask unified modeling, the model can support unique and stable multicamera representations.
- Supports multi-movement and on-the-fly mirroringThe video is a rich set of scenes, subjects and behavioral actions, which can respond more accurately to users' fine-grained commands, and smoothly generate complex video content with multiple subjects, multiple actions and random camera movements.
- Supports stable motion and true aestheticsThat is to say, the picture and subject dynamics are more natural, better structured, with a lower crash rate, and different styles of video content can be generated according to the instructions, such as realism, animation, film and television, and advertisements.
statement:The content of the source of public various media platforms, if the inclusion of the content violates your rights and interests, please contact the mailbox, this site will be the first time to deal with.