Pictured here is an AI-generated snippet from Vidu’s website. The tool can create videos from text or image prompts.
Evelyn Cheng | CNBC
BEIJING – Beijing-based Shengshu Technology said Wednesday that its artificial intelligence-powered text-to-video tool Vidu can now generate videos by combining images.
Vidu already allows users worldwide to create 8-second clips based on written instructions. While OpenAI — the creator of ChatGPT – revealed in February that its AI model Sora could generate one-minute videos from text, but has yet to release that publicly.
Vidu’s new AI feature can combine three images — such as a shirt, a person and a moped — into a video of the person wearing the shirt and riding the moped through a scene, Shengshu said.
Other platforms claim to be able to convert text or images into videos using AI, but the quality of the output varies. The breakthrough Shengshu claims is the ability to take three unique images and integrate them into an AI-generated video with visual consistency.
‘We knew it very early on [visual consistency] as the problem, and wanted to solve it well,” Fan Bao, head of technology at Shengshu, said in Mandarin, as translated by CNBC.
Vidu launched in April and its ability to turn two profile photos into lifelike videos of people hugging went viral on TikTok.
The AI video generator is already making money from advertisers, animators and other companies, Jiayu Tang, co-founder and CEO of Shengshu, said in Mandarin, according to a CNBC translation. He said monthly usage fees per customer can range from 100,000 yuan to 1 million yuan ($13,871 to $138,711).
To address copyright issues, Tang said a company might make a deal with an artist that would allow the AI to mimic the artist’s painting style for an advertisement. He said he had not seen any significant lawsuits surrounding consumer use of images.
Tang added that Vidu does not allow the public to generate content with images of celebrities or “sensitive” people. He said the AI tool also bans nude photos and violent images. As for personal photos, Tang said Vidu destroys the data in accordance with general data protection regulations – a global benchmark.
According to PitchBook, Shengshu was founded last year with partners including Baidu Ventures, Alibaba affiliate Ant Group, Chinese startup Zhipu AI, Qiming Venture Partners and the city of Beijing.
Tang said Vidu’s AI runs on leased cloud servers in China and abroad.