Jin Shi data July 4 news, Shang Tang released the first 'controllable' character video generation model Vimi, which is mainly aimed at C-end users, supporting chat, singing, dancing and other entertainment interactive scenes. Shang Tang said that Vimi can generate single-shot character videos up to 1 minute long, and the picture quality will not deteriorate or distort with the passage of time. Vimi is based on the Shang Tang Riri new large model, which can generate character videos consistent with the target action based on a photo of any style, and can be driven by various elements such as existing character videos, animation, sound, text, etc.
View Original
This page may contain third-party content, which is provided for information purposes only (not representations/warranties) and should not be considered as an endorsement of its views by Gate, nor as financial or professional advice. See Disclaimer for details.
SenseTime, ilk "kontrol edilebilir" karakter video oluşturma modeli olan Vimi'yi piyasaya sürdü
Jin Shi data July 4 news, Shang Tang released the first 'controllable' character video generation model Vimi, which is mainly aimed at C-end users, supporting chat, singing, dancing and other entertainment interactive scenes. Shang Tang said that Vimi can generate single-shot character videos up to 1 minute long, and the picture quality will not deteriorate or distort with the passage of time. Vimi is based on the Shang Tang Riri new large model, which can generate character videos consistent with the target action based on a photo of any style, and can be driven by various elements such as existing character videos, animation, sound, text, etc.