Meet Kling, China's Latest Text-To-Video AI Model

Kuaishou, the popular short video app in China, has recently unveiled its latest artificial intelligence (AI) model. Named Kling, this AI model is a text-to-video service similar to OpenAI's Sora. This innovation, which is currently in the trial stage, indicates that tech firms in China are trying to catch up with AI technology to compete with US firms.

According to a report from the South China Morning Post, the Kling AI Model has the capacity to process text into video clips up to 2 minutes long with 1080p resolution. Kuaishou Technology also reportedly said that the AI model is able to interpret prompts to generate videos that mimic the physical world and create imaginative scenes from text instructions. Kling utilizes a diffusion transformer model, which is similar to the ChatGPT maker's Sora. The company has earlier unveiled the KwaiYii large language model (LLM) and text-to-image model Kolors.

Tech giants have made significant progress in developing text-to-video generative AI models that produce hyper-realistic results. Kling is expected to compete with OpenAI's Sora, which is not yet widely available on the market. Sora, launched in February 2024, can create videos up to a minute long based on whatever prompt a user types. During its launch, OpenAI claimed that its AI model understands not only what the user has asked for in the prompt but also how those things exist in the physical world.