share_log

云从科技:从容大模型支持通过文本和音频生成图像和视频

Cloud Cong Technology: Calmly large model supports image and video generation from text and audio

Breakings ·  Feb 19 17:45
OpenAI's video generation model Sora has attracted attention. The relevant person in charge of Yuncong Technology said that Yuncong technology has accumulated a lot in terms of vision. Currently, the Calmness Model has used generative technology such as diffusion and GAN to model character images and video data, and generate, control, and edit images and video content through text and audio. In terms of application, Yuncong Technology is jointly developing PortGPT, a major port model with Tianjin Port and Huawei. The core is the AI agent Tiantian, which generates interactive images through AI and collaborates with data analysis to improve port operation efficiency and safety. In addition, it is also actively deploying in cross-modal fields such as Wensheng images and videos, including publishing digital human competency platforms to generate AI videos; collaborating with China Telecom to generate AI marketing posters. (Science and Technology Innovation Board Daily)

The translation is provided by third-party software.


The above content is for informational or educational purposes only and does not constitute any investment advice related to Futu. Although we strive to ensure the truthfulness, accuracy, and originality of all such content, we cannot guarantee it.
    Write a comment