A team from Alibaba has launched a new video generation tool called Tora011 Archives emphasizing its “excellence” in achieving high-motion fidelity, as buzz around OpenAI’s text-to-video generator Sora drives Chinese companies to develop similar AI models. In dozens of video clips posted by the team and produced via Tora, the model’s trajectory-oriented diffusion transformer for video generation ensures that the generated motion follows the specified trajectory drawn in advance. According to the Tora introduction paper, the team said Sora-like models are limited in “effectively generating videos with controllable motion,” while claiming that Tora is the first trajectory-oriented diffusion transformer framework. The work has not yet been finalized, said the paper, noting that Tora would be added to the official Alibaba repository once it has received company approval. [Tora]
(Editor: {typename type="name"/})
NYT Strands hints, answers for June 21
Bird Buddy's new nature camera smashes Kickstarter goal
Nintendo forecasts a huge first year for Switch 2 sales
Nintendo forecasts a huge first year for Switch 2 sales
How to make a hook in a TikTok video
Best TV deal: Get the LG UR9000 4K TV for 21% off at Amazon
MotoGP 2025 livestream: Watch France Grand Prix for free
Ultrahuman aims to make all US ring orders in America
England vs. India 2025 livestream: Watch Test 1 of India Tour of England for free
Wahoo seemingly buries tariff fees in cycling TRACKR Radar shipping costs
What Sa Nguyen uses to film TikToks that feel like FaceTime
100 Americans vs. 100 Brits: TikTok’s latest debate is uniting America
接受PR>=1、BR>=1,流量相当,内容相关类链接。