Kling is the new text-to-video model launched by Kuaishou Technology, a chinese company known for its short-video platform similar to TikTok.
New Delhi: OpenAI text-to-video model has not even become accessible to users yet and there’s a new video and there’s a new video generation AI model already making headlines, bringing in tough competition for the ChatGPT makers. Kling is the new text-to-video model launched by Kuaishou Technology, a Chinese company known for its short-video platform similar to TikTok.
Kling, a revolutionary text-to-video generative AI model can create incredibly realistic videos from simple text prompts. The emergence of the Kling platform might provide much-needed competition to Open AI’s Sora.
What Can ‘Kling’ Do
Using a similar technology to Sora, Kling can create 1080p high-definition videos in smooth 30 frames per second animation for up to two minutes. Kling can simulate complex realistic motion with a better understanding of the physical world.
Kling, like Sora, utilizes a Diffusion Transformer. The technology reads the prompt and transforms it into visuals starting from a single frame. Kling can produce a video of a panda playing guitar if given the prompt.
The Chinese company released a video demonstrating the abilities of the new text-to-video model. At some instances the video generated by Kling surpassed the output of Open AI’s Sora.
The Kling model also gives freedom to users in terms of aspect ratios. The indigenous Large Language Model (LLM) uses advanced 3D face and body reconstruction backed by the company proprietary technology 3D VAE. This enhances the various characteristic aspects of the video such as realistic expression on face and better limb movement.
Kling: Competition For The West
The unveiling of Kling is a significant development in the artificial intelligence landscape as it shifts the power dynamics toward the east. Kling offers a larger video length, better resolution and accurate results, surpassing OpenAI’s Sora on many criteria.
Moreover, Kling is not the only text-to-video model from China. In April of 2024, Vidu AI was released in China. These latest developments in the eastern part of the world surely shake the dominance of the western companies.
However, China products might suffer to achieve global accessibility as the country has a history of facing restrictions in many countries.