Ali Dharma Online "Text Generation Video Large Model"

Ali Dharma Online text Generation Video

数据猿 | 2023-03-23 21:12

【数据猿导读】 Recently, Ali Dharma Institute has launched the "Text Generation Video Large Model" in the AI

Recently, Ali Dharma Institute has launched the "Text Generation Video Large Model" in the AI model community "Magic" ModelScope. According to the official introduction, the current text generation video large model consists of three sub-networks: text feature extraction, text feature to video latent space diffusion model, video latent space to video visual space, the overall model parameters are about 1.7 billion, currently only supports English input . The diffusion model adopts the Unet3D structure, and realizes the function of video generation through the iterative denoising process from the pure Gaussian noise video.

来源：数据猿

收藏分享

声明：数据猿尊重媒体行业规范，相关内容都会注明来源与作者；转载我们原创内容时，也请务必注明“来源：数据猿”与作者名称，否则将会受到数据猿追责。