Concerns have been raised regarding the potential for deepfake video generation, particularly involving influential figures.

MiniMax, a Shanghai-based AI startup backed by Alibaba and Tencent, has launched a new text-to-video generation model called Video-01, unveiled at their first developer conference.

The Video-01 service allows users to create six-second videos by inputting text prompts, with the generation process taking about two minutes.

This innovative tool effectively captures human movement and offers high-quality rendering, making it a notable competitor in the AI video generation market.

Video-01 supports various styles, including 'cartoon' and 'cyberpunk,' showcasing its flexibility in creating diverse video content.

Accessible to users worldwide, Video-01 generates videos at a resolution of 1280x720 pixels and 25 frames per second.

Future updates for Video-01 are planned to include longer video generation capabilities and features like picture-to-video and video editing.

The startup aims to enhance the model with version-02, which will introduce improvements and new features.

However, the platform's performance may vary due to high user traffic, and there are undisclosed limits for free users.

MiniMax is positioning itself alongside major players like Microsoft and Runway, as the demand for text-to-video technology continues to grow.

The founder, Yan Junjie, believes that the gap between domestic AI models and OpenAI's GPT-4 is narrowing, indicating a competitive landscape.

MiniMax is recognized as one of China's 'AI tigers,' alongside other notable companies like Zhipu AI and Baichuan.