Chinese AI Video Generator Video-01 is the Talk of the Town!

Chinese AI text-to-video generation models have proven their mettle time and again, taking the internet by storm every time a new model is released.

MiniMax, a Chinese AI startup has just released a text-to-video generation model called Video-01. The platform is open to everyone, including those who live outside of China.

According to South China Morning Post, MiniMax Founder and Chief Executive Officer Yan Junjie introduced the AI video generator during the company’s inaugural developer conference in Shanghai.

The model is mainly garnering attention for its capacity to produce incredibly lifelike human footage, complete with precise hand gestures, which other AI generation models have struggled with. Video-01 is the latest of MiniMax’s impressive lineup of models, which also includes generative speech, language, and music generation.

The model supports videos with a resolution of 1280×720 pixels at 25 frames per second. Similar to Kling and Runway, you can depict dramatic camera movements, and although the current version only consists of six-second clips, the goal is to eventually match the 10-second clips produced by top industry players.

“We have indeed made significant progress in video model generation, and based on internal evaluations and scores, our performance is better than that of Runway in generating videos,” said founder Yan Junjie to reporters.

The company has said that this is only the first iteration of the video generation model. They want to keep refining the model by adding new data, algorithms, and usage information, and they intend to release an upgraded version soon. As of right now, the model can only generate text to video. In the future, there will be more upgrades like the ability to create videos from images.

The company has yet to disclose any information about user privacy and specifics about how data is collected and used to train the AI model.