Zhipu AI, a Chinese provider of AI models, has launched Ying, a video generation model capable of creating short videos with text and image prompts.
The model generates six-second video clips within an approximate 30-second time frame. Additionally, it leverages user input in the form of text and images, which can be customized using options like 3D animation, cinematic, or oil painting visuals, and themes such as tension, excitement, or melancholy.
The company claims to utilize its text-to-video model called "CogVideoX" for the new model.
By using this site, you agree to allow SPEEDA Edge and our partners to use cookies for analytics and personalization. Visit our privacy policy for more information about our data collection practices.