ainewsblitz.com

Breaking

Alibaba Rolls Out Wan3.0 Beta With 30-Second Video Generation

  • Media Generation
  • Foundation Models

Alibaba has rolled out the beta version of Wan3.0, a video-generation model that can produce clips up to 30 seconds in one generation and accept text, images, audio, video and documents as inputs. An early hands-on evaluation spanning text-to-video, image-to-video and reference-to-video workflows describes a clear quality step over Wan2.7, but independent testing suggests the model still needs work in complex continuity and lip sync.

Continue reading

The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.

$20
Read this article
$29/month
Unlimited — all 27,536 articles, the full archive, and comprehension quizzes
Save 72%
$98/year
≈ $8.17/month
Unlimited, billed once a year