People are generating entire short films using a new artificial intelligence application

Minimax, a Chinese startup backed by Alibaba and Tencent and one of the “tigers of artificial intelligence,” has launched its Video-01 text-to-video model, which can generate highly accurate representations of human beings, including their hand movements. Minimax unveiled the new tool on Saturday at its inaugural developer conference in Shanghai.

Another Chinese ‘Sora’: a new AI-powered video tool launched today by Minimax, backed by major investors Alibaba Group and Tencent.
Check out their official Magic Coin AI movie, created entirely with text to video.
Try it for free now: https://t.co/Kl1avPXkFL photo.twitter.com/df14ZVq1Es

— Junie Lau (@JunieLauX) August 31, 2024

Video-01 allows users to create 6-second videos at 1280 x 720 resolution at 25 frames per second (fps) using text prompts, reportedly in about 2 minutes. At the conference, Minimax CEO Yan Junjie noted that this is just the first version of the model and that future updates will include the ability to generate videos from images and edit those generated videos, according to the company. The South China Morning Post “We have really made significant progress in video model generation, and based on internal evaluations and scores, our performance is better than Runway in video generation,” he told reporters.

To try out Video-01 for yourself, head over to the Video-01 website. As I was writing this article, the site was flooded with users, so the video generation process took close to 5 minutes, but it didn’t require you to enter a mobile number or log in to use it. As with other leading video AIs like Kling and Runway, you can dictate cinematic camera movements into your text message. The quality of the resulting video was quite good, surprisingly realistic and didn’t feature any significant visual hallucinations commonly found in similar free AI tools. The video can also be downloaded as a .MP4 file.

Video-01 joins an increasingly crowded video generation market, even without the long-awaited arrival of OpenAI’s Sora. Two other “Tigers,” Shengshu AI and Zhipu AI (both valued at over $1 billion), launched their own text-to-video tools in July, as did Kaishou Industries with Kling.AI. Byte Dance also recently launched its Jimeng text-to-video app on the Apple and Android app stores, though it’s only available to users in China. In the US, Minimax will have to compete with Luma Labs’ Dream Machine and Runway’s Gen-3.