Shulou(Shulou.com)11/24 Report--

Thanks to CTOnews.com netizens for their clue delivery, such as eye clamp, track worker and Mr. Aviation. CTOnews.com March 22 news, recently, Aridamo has been in the AI model community "magic" ModelScope online "text generation video model".

According to the official introduction, at present, the large video model generated by text is composed of three sub-networks: text feature extraction, text feature to video hidden space diffusion model, video hidden space to video visual space. The overall model parameters are about 1.7 billion. Currently, only English input is supported. The diffusion model adopts Unet3D structure and realizes the function of video generation through iterative denoising process from pure Gaussian noise video.

According to the official introduction, the model has a wide range of application and can be inferred based on any English text description to generate video. Some examples of text generation videos are as follows:

A giraffe underneath a microwave. (a giraffe in the microwave)

A goldendoodle playing in a park by a lake. (a golden puppy plays in a park by the lake.) according to CTOnews.com, the model is already online in Chuangxiang and huggingface, so you can experience it directly or refer to this page to build your own. The model requires hardware configuration that is approximately 16GB memory and 16GB GPU memory. Under the ModelScope framework, the current model can be used by calling a simple Pipeline, where the input needs to be in dictionary format and the legal key value is' text', content is a small piece of text. This model only supports reasoning on GPU.

Judging from the results of the trial, most of the videos that can be generated are 2-4 seconds in length, and the waiting time ranges from more than 20 seconds to more than 1 minute.

Welcome to subscribe "Shulou Technology Information " to get latest news, interesting things and hot topics in the IT industry, and controls the hottest and latest Internet news, technology news and IT industry trends.