Alibaba launched Wan3.0, its latest artificial intelligence video generation model, on August 24, with the ability to generate videos of up to 30 seconds from documents, spreadsheets, presentation slides and web pages.
Alibaba Cloud said Wan3.0 supports multiple input types, including text, images, audio and video, as well as business documents and web content. The model is designed to convert existing digital material into video rather than requiring users to create a video prompt from scratch.
The company said the model can turn presentation material into product videos, training content into video courses and spreadsheet data into animated visualisations. Wan3.0 also supports video generation at up to 1080p resolution, according to Alibaba Cloud.
Alibaba Cloud first made Wan3.0 available in public beta on August 6. The company said the model has since been used for short drama and film production, advertising and marketing, tourism promotion and music video creation.
The latest release builds on Alibaba’s broader development of generative AI models. The company also develops the Qwen family of large language models, while Wan focuses on video generation and multimodal content creation.
Reuters reported that the launch came a day after the Chinese technology company announced an HK$80 billion, or about $10.2 billion, share placement to fund its artificial intelligence expansion.
Wan3.0 gives Alibaba another product through which it can apply its growing AI infrastructure, with the model aimed at generating video from text and multimodal inputs as well as existing business and digital content.
Your reaction
Discussion
What's your take on this story?
No comments yet — be the first to share your view.