Gold Ten Data News on July 4th, SenseTime released its first "controllable" character video generation model Vimi. The model is mainly for C-end users and supports various entertainment interactive scenes such as chatting, singing, and dancing. SenseTime said that Vimi can generate single-shot character videos up to 1 minute long, and the visual effects will not deteriorate or distort with time. Vimi is based on SenseTime's daily new large model, and it can generate character videos consistent with the target action based on a photo of any style. It can be driven by various elements such as existing character videos, animations, sounds, and texts.
Ver originales
Esta página puede contener contenido de terceros, que se proporciona únicamente con fines informativos (sin garantías ni declaraciones) y no debe considerarse como un respaldo por parte de Gate a las opiniones expresadas ni como asesoramiento financiero o profesional. Consulte el Descargo de responsabilidad para obtener más detalles.
SenseTime lanza Vimi, el primer gran modelo de generación de videos de personajes 'controlable'
Gold Ten Data News on July 4th, SenseTime released its first "controllable" character video generation model Vimi. The model is mainly for C-end users and supports various entertainment interactive scenes such as chatting, singing, and dancing. SenseTime said that Vimi can generate single-shot character videos up to 1 minute long, and the visual effects will not deteriorate or distort with time. Vimi is based on SenseTime's daily new large model, and it can generate character videos consistent with the target action based on a photo of any style. It can be driven by various elements such as existing character videos, animations, sounds, and texts.