It's a day that ends in Y, so a new AI video generator joins the growing number of similar tools. Alibaba is the latest to join the field with its new text-to-video model, part of its Tongyi Wanxiang portfolio. Announced at the Alibaba Cloud Apsara Conference, the AI video tool was just part of a flurry of new AI options from the Chinese tech giant, including more than 100 new large language models (LLMs),
Tongyi Wanxiang is Alibaba’s collection of synthetic media generation models, which started with an AI image creator last year. The new tool will produce high-quality videos from text prompts in both Chinese and English and still images. Alibaba executives boasted that the company has one of the most advanced broadcast transformer (DiT) architectures, allowing it to make videos that maintain their quality regardless of the style requested by the user, including realistic live action and many animation styles.
Alibaba didn’t spend much time explaining how it envisions users using the AI-powered video maker, but the company’s emphasis on third-party partnerships is suggestive. The technology could be employed in a variety of marketing and entertainment videos. It could also end up in video games, producing visual references or even entire introductory videos.
Have you seen Sora?
The sheer number of AI video generators that are available or coming soon is astounding, considering there weren’t any at the consumer level until recently. OpenAI brought a lot of attention to the idea with its Sora model. Still, the company’s decision to limit Sora to certain partners left many people looking for alternatives, and companies like Alibaba are happy to fill some of the gaps.
Runway, Stability AI, Pika, Hotshot and Luma Labs’ Dream Machine are just a few of the most prominent examples. And Alibaba is not alone among Chinese competitors. Kling and Jimeng from TikTok owner Bytedance are in the same race. Alibaba has said it will take action, but the final cut with the ultimate winners and losers has yet to be filmed.