China Alibaba has launched an artificial intelligence model with WAN 2.1 open source, says the website dedicated to the new neuronal network. It is able to generate videos and images.
Author:
https://rb.ru/author/kossakovskaya-astasiya/
Subscribe to RB.ru on Telegram
The company has developed three versions of WAN 2.1-I2V-14B, T2V-14B and T2V-1.3b. The first two support the generation of rollers in resolution of 480p to 720p, the last one, only 480p. The 14B index on behalf of the AI model indicates that it can take into account up to 14 billion parameters when complying with the application.
In addition, the T2V-1.3b requires only 8.19 GB of video memory, which makes it compatible with almost all graphic processors available for the wide consumer, says Alibaba. “Wan 2.1 constantly exceeds existing open source models and modern commercial solutions for several indicators,” said the company.
Wan 2.1 can be downloaded for free on Github and Hugingface platforms.
- At the end of January, Alibaba launched the AI Qwen 2.5-Max model. The company said it exceeds the latest Openai, Deepseek and Meta*models.
- Later, the Chinese company announced plans to invest $ 53 billion in the development of artificial intelligence and cloud technologies, which are the most total investments of Alibaba in these industries in the last 10 years.
- In addition, Alibaba, president of the Board of Directors, Joe Tsai, said the company will join Apple for the introduction of AI technologies in the iPhone in China.
*Meta is recognized as an extremist organization in Russia, its activities are prohibited.
Author:
Anastasia Kossakovskaya
Source: RB
I am a professional journalist and content creator with extensive experience writing for news websites. I currently work as an author at Gadget Onus, where I specialize in covering hot news topics. My written pieces have been published on some of the biggest media outlets around the world, including The Guardian and BBC News.
