Jun 07, 2024 05:04 AM
BUSINESS
Kuaishou Unveils a Rival to Sora That Produces Video From Text
00:00/00:00
Listen to this article
1x
Subscribe now
Listen to the full version
Listen to the full version
Kuaishou’s Kling can generate 1080p high-definition videos lasting up to 2 minutes
China’s short-video platform Kuaishou Technology unveiled its text-to-video model “Kling” on Thursday, joining other Chinese tech firms in the race to rival OpenAI’s Sora with artificial intelligence-powered video generation.
Using technology similar to Sora, Kling can generate 1080p high-definition videos lasting up to 2 minutes, Kuaishou said. The model is capable of producing large-scale realistic motions, simulating physical world characteristics and combining concepts and imagination.
You've accessed an article available only to subscribers
VIEW OPTIONS
Unlock exclusive discounts with a Caixin group subscription — ideal for teams and organizations.
Subscribe to both Caixin Global and The Wall Street Journal — for the price of one.
- RELATED
Share this article
Open WeChat and scan the QR code
- DIGEST HUB
Digest Hub
Back
Explore the story in 30 seconds
- Kuaishou Technology launched its text-to-video model "Kling" to compete with OpenAI's Sora, producing 1080p videos up to 2 minutes long.
- Kling is in invitation-only testing and showcases realistic and surreal videos like "an astronaut running on the Moon."
- Chinese firms like ByteDance’s Dreamina and Shengshu’s Vidu are racing to develop advanced video generation models despite high costs and regulatory challenges.
AI generated, for reference only
Who’s Who
- Kuaishou Technology
- Kuaishou Technology, a Chinese short-video platform, launched a text-to-video model called "Kling" capable of generating 1080p high-definition videos up to 2 minutes long. Kling combines realistic and imaginative visual elements and is currently undergoing invitation-only testing on Kuaishou's video editing app. Kuaishou has posted numerous sample videos showcasing Kling's capabilities, including complex motions and surreal scenes.
- ByteDance Inc.
- ByteDance Inc. is a Chinese tech company that supports Dreamina, a web-based AI platform. In late March, Dreamina unveiled its text-to-video model capable of generating footage lasting three to six seconds. ByteDance is taking part in the competition to develop advanced AI video generation technologies in China.
- Shengshu Technology
- Shengshu Technology, a Beijing-based generative AI startup, released a text-to-video model called Vidu in late April. Vidu is notable for being China's "first long-duration, high-consistency, and highly dynamic video generation model" and can produce high-definition videos lasting up to 16 seconds. Investors have been heavily supporting Shengshu and similar startups, aiming to catch up with OpenAI's Sora in the video generation technology race.
AI generated, for reference only
What Happened When
- February 2024：
- OpenAI unveiled its text-to-video model named Sora.
- Late March 2024：
- Dreamina, backed by ByteDance Inc., unveiled its text-to-video model.
- Late April 2024：
- Beijing-based generative AI startup Shengshu Technology unveiled its model called Vidu.
- Thursday, June 6, 2024：
- Kuaishou Technology unveiled its text-to-video model Kling.
AI generated, for reference only
- PODCAST
- MOST POPULAR
Sign in with Google
Sign in with Facebook
Sign in with 财新