MiniMax Video-01 Platform with AI Video Generation Capabilities Launched

MiniMax, a Chinese artificial intelligence (AI) unicorn startup backed by Alibaba and Tencent, last week released a text-to-video generation tool. The platform, called Video-01, is available to the public, even outside of China. It can generate six-second videos in a wide range of styles. Video-01 joins the company’s existing AI offerings, which include a music generator, generative speech and language translation. The AI ​​video generator will compete with similar tools on the market, such as Runway AI, Pika 1.0 and OpenAI’s soon-to-be-released Sora.

MiniMax Video-01 launched

The AI ​​video generator was launched by MiniMax founder and CEO Yan Junjie at the company’s first developer conference in Shanghai, the South China Morning Post reported reportThe founder is said to have emphasized that Video-01 is the first iteration of a text-to-video generation model and that future updates will allow users to generate videos from image inputs. Video editing capabilities are also said to be added via future updates.

Gadgets 360 employees had access to the platform and generate videos by writing a text prompt in English. The MiniMax Video-01 can generate six-second videos in a resolution of 1280 x 720 pixels at 25 frames per second. The tool can generate videos in a wide range of styles and perspectives.

Enthusiasts do not need to register to use the platform and can generate videos immediately. Video-01 took about five minutes to generate videos in our tests, but this may be due to the large number of users accessing the platform at the same time. There is a limit for free users, but the limit is currently unknown.

A demo of the MiniMax Video-01’s generation capabilities was posted on X (formerly known as Twitter). While the demo shows high-quality rendering, we found the video generation to be on par with Runway and Pika 1.0. Details about the data procurement to train the AI ​​model or the user privacy for the generated videos are not known.

During our testing, we also found that Video-01 generated videos featuring influential people, which could contribute to deepfakes. Whether this will be addressed in future updates is unknown.