An image-to-video tool is launched by a Chinese AI startup, challenging OpenAI's Sora.

• Shengshu Technology, based in Beijing, announced on Wednesday that its AI-powered text-to-video tool, Vidu, now has the capability to create videos from images.
• Shengshu stated that Vidu's new AI feature can combine three images, such as a shirt, person, and moped, into a video of the person wearing the shirt and driving the moped through a scene.
• Jiayu Tang, co-founder and CEO of Shengshu, stated in Mandarin that the AI video generator is currently generating revenue from advertisers, animators, and other businesses, as reported by CNBC's translation.

Beijing-based Shengshu Technology announced that its AI-powered text-to-video tool Vidu has been updated to generate videos using images.

Although Vidu enables users globally to produce 8-second videos based on textual prompts, OpenAI, the developer of ChatGPT, has not yet made its AI model Sora's one-minute video generation publicly available.

Shengshu stated that Vidu's new AI feature can merge three images, such as a shirt, person, and moped, into a video of the person wearing the shirt and riding the moped through a scene.

While other platforms assert that they can create videos from text or images using AI, the quality of the output can vary. However, Shengshu boasts a revolutionary feature: the ability to seamlessly merge three distinct images into a single AI-generated video with consistent visuals.

Fan Bao, chief technology officer at Shengshu, stated in Mandarin, "We identified [visual consistency] as the issue early on and aimed to solve it thoroughly." (Translated by CNBC)

In April, Vidu was launched and its feature of creating lifelike videos of people hugging from two profile photos went viral on TikTok.

Shengshu co-founder and CEO Jiayu Tang stated in Mandarin that the AI video generator is already generating revenue from advertisers, animators, and other businesses. He added that monthly usage rates per customer can range from 100,000 yuan to 1 million yuan ($13,871 to $138,711).

Tang suggested that a company could enter into a deal with an artist to enable the AI to replicate the artist's painting style for an advertisement. He stated that he was not aware of any significant legal cases concerning consumers' use of images.

Tang stated that Vidu prohibits the public from generating content using images of celebrities or "sensitive" individuals, and also bans nudes and violent images. In terms of personal photos, Tang revealed that Vidu complies with the general data protection regulation, a global standard.

Last year, Shengshu was established with the support of investors such as Baidu Ventures, Ant Group, Zhipu AI, Qiming Venture Partners, and Beijing city, as reported by PitchBook.

Vidu's AI operates on leased cloud servers located in China and other countries, as stated by Tang.