Alibaba Releases Wan3.0: Generates 30-Second Videos, Accepts Document Inputs
xiaohu · x · 2026-08-06
Alibaba has officially released the Wan3.0 video generation model, achieving a breakthrough of generating up to 30 seconds of video in a single run.
Key Features:
- Native 30s Video Generation: Features realistic-level rendering.
- Universal Reference Inputs: Beyond text, image, audio, and video, it now supports documents, spreadsheets, slides, web pages, and more.
- Multi-format Support: Compatible with doc, xls, ppt, pdf, txt, md, url, etc.
Pricing:
- 480p: $0.05 / sec
- 720p: $0.10 / sec
Related event: Alibaba Releases Wan3.0 Video Model with Native 30-Second Generation(5 posts)→
More from Models
- OpenAI Reportedly Set to Launch New 'Astra' Model Next Week — rohanpaul_ai · 2026-08-06
- DeepSeek Funding Docs Leaked: V4-Pro Matches Claude, Runs on Ascend — xiaohu · 2026-08-06
- Why Do GPT Models Love Generating Comma-Separated Lists? — mariofilhoml · 2026-08-06
- Kimi K3 vs Grok 4.5: Which Model Better Completes Unfinished Sketches? — CodeByPoonam · 2026-08-06
- Unsloth's Gemma 4 mmproj Breaks with Newer llama.cpp, Causing Silent Multimodal Failures — Top_Speaker_7785 · 2026-08-06
- t0-alpha Released: Open-Source Foundation Model for Time-Series Forecasting — fpedregosa · 2026-08-06