Alibaba launches video model Wan3.0 supporting document-to-video conversion
创业邦 · wechat · 2026-08-25
Alibaba officially launched its video generation large model, Wan3.0. The model supports generating 30-second videos in a single go and introduces the ability to input documents directly (including doc, xls, ppt, pdf, md formats) for video generation, aiming for high-fidelity real-world simulation. It is available on Alibaba Cloud Bailian and Qianwen platforms with limited-time API discounts. Additionally, Feixiang Teacher 3.0 was released, allowing one-click generation of runnable educational apps; Harvey, the highest-valued legal AI unicorn, launched its proprietary model Tenet based on Kimi K3; and Moonshot AI announced that Kimi K2.5 will be decommissioned at the end of this month.
More from Multimodal
- Stunning 3D "Alien v2": metallic tentacled creature with intricate detail — creatoroff · 2026-10-16
- Claude Opus 5.5 makes a surprisingly good unofficial Apple HomeView commercial — john_lam · 2026-10-16
- Curl noise over SDFs: a three.js generative art piece with painterly flow lines — thespite · 2026-10-16
- Stunning scene consistency in AI video — depth maps reveal what's behind the output — jonstephens85 · 2026-10-16
- Dev demos live game modding with fal: speak assets into existence while playing — OdinLovis · 2026-10-16
- fal launches Worlds for real-time creation and interaction with AI-generated worlds — Scobleizer · 2026-10-16