Physical Address
304 North Cardinal St.
Dorchester Center, MA 02124
The race by major tech companies to jump on the latest AI models continues with the launch of ByteDance’s next-generation video generator. in Blog postsays ByteDance – the Chinese company behind TikTok Sedan 2.0 Supports prompts that combine text, images, video, and audio.
The company claims it “brings a huge leap in generation quality,” offering improvements in creating complex scenes with multiple themes and its ability to follow instructions. Users can enhance their text prompts by feeding Seedance 2.0 with up to nine images, three videos and three audio clips.
The model can create audio clips up to 15 seconds long, taking camera movement, visual effects and motion into account. It can also reference text-based storyboards, according to ByteDance.
In one example shared by ByteDance, which shows two figure skaters performing a routine together, the company says Seedance 2.0 can “reliably perform a series of highly difficult movements – including synchronized takeoffs, mid-air spins, and precise landings on the ice – while strictly following the laws of real-world physics.”
Users on social media have already begun showing off what the new tool can do, with one person posting a video created by artificial intelligence. With proverbs Brad Pitt and Tom Cruise in a movie fight scene. dead pool Writer Rhett Reese He reposted the video With the caption: “I hate to say it. It’s probably over for us.”
Currently, Seedance 2.0 is only available through ByteDance’s Dreamina AI platform and through its AI assistant Doubao. It’s unclear whether it will make its way to TikTok, especially now that the app is under new ownership in the US.