The AI Video Generation Landscape: Tencent’s Follow-Your-Click Falls Short of OpenAI’s Sora

The artificial intelligence (AI) landscape is rapidly evolving, with tech giants and startups alike racing to develop the most advanced AI models. In a recent development, Tencent Holdings unveiled its latest AI video creator, Follow-Your-Click, in collaboration with two top universities. However, industry insiders claim that the model still lags behind OpenAI’s Sora, a text-to-video generator.

Tencent’s Follow-Your-Click is an image-to-video model that allows users to click on a certain area of an image and make objects move for a few seconds with prompts such as “turn head,” “smile,” “sad,” and “launch.”

The demo video showcases the model’s capabilities, but it’s clear that Chinese companies still have a long way to go to catch up with their overseas counterparts. According to a technical professional who studies AI applications, domestic image generation tools are roughly one version behind their overseas counterparts, with a gap of about six months to a year.

Despite the gap, startups are not lacking in ambition or funding. Shengshu-AI, a local developer of large language models, recently secured hundreds of millions of yuan in funding and claims to be catching up with Sora by December.

AISphere, another text-to-video startup, has also wrapped up its Series A1 round of financing worth 100 million yuan. Founder Wang Changhu is confident that the company will surpass the latest version of Sora in three to six months.

Even ByteDance, the parent company of TikTok, is joining the fray with its text-to-video model, MagicVideo-V2, and a tool called Boximator, which allows users to reshape their videos by moving objects in isolation.

As the AI video generation landscape continues to evolve, one thing is clear: the competition is heating up, and only time will tell who will emerge as the leader in this space.

“Domestic image generation tools are roughly one version behind their overseas counterparts, with a gap of about six months to a year.” - Technical professional

The race to develop the most advanced AI models is on, and it’s anyone’s game. Stay tuned for further updates on the latest developments in the AI video generation landscape.