ByteDance’s next-gen AI model can generate clips based on text, images, audio, and video

ByteDance says its caller AI video exemplary tin much accurately travel prompts. | Image: ByteDance

Big Tech's contention to leapfrog the latest AI models continues with the motorboat of ByteDance's next-gen video generator. In a blog post, ByteDance - the China-based institution down TikTok - says Seedance 2.0 supports prompts that harvester text, images, video, and audio.

The institution claims it "delivers a important leap successful procreation quality," offering improvements successful generating analyzable scenes with aggregate subjects and its quality to travel instructions. Users tin refine their substance prompts by feeding Seedance 2.0 up to 9 images, 3 video clips, and 3 audio clips.

The exemplary tin make up to 15-second clips with audio, portion taking cam …

Read the afloat communicative astatine The Verge.