# Alibaba's Wan3.0 generates AI videos up to 30 seconds long from text, images, and documents

> Source: <https://the-decoder.com/alibabas-wan3-0-generates-ai-videos-up-to-30-seconds-long-from-text-images-and-documents/>
> Published: 2026-08-24 15:35:03+00:00

# Alibaba's Wan3.0 generates AI videos up to 30 seconds long from text, images, and documents

**Alibaba's video generation model Wan3.0 is now available in beta. It produces videos up to 30 seconds long and accepts text, PDFs, web pages, and PowerPoint files as input.**

That doubles the video length compared to its predecessor, [Wan2.5](https://the-decoder.com/alibabas-wan2-5-preview-lets-users-turn-photos-and-text-prompts-into-videos-with-matching-audio/). The model also recommends the best video length based on the user's prompt and includes an extension tool to make existing videos longer.

Wan3.0 processes text, images, video, and audio at the same time. A single prompt can include up to ten images, five videos, and five audio clips. Web pages and documents like PDFs or PowerPoint presentations also work as input sources, turning static data into dynamic video.

AI-generated videos often suffer from visual drift and distortion, especially in faces and user interfaces. Wan3.0 aims to fix that by keeping details from reference material like characters, props, and spatial layouts more consistent, according to Alibaba.

Wan3.0 is available through the [wan.video website](https://create.wan.video/generate/video/omni?model=wan3.0), [Alibaba Cloud Model Studio](https://modelstudio.console.alibabacloud.com/model-releases/wan3.0-video), or via API on [Qwen Cloud](https://qwencloud.com/models/wan3.0-video). There are two tiers: a Standard version, currently at a 30 percent discount, and a faster Prime version.

| Resolution | Standard (per sec.) | Prime (per sec.) | 30-second clip (Standard) | 30-second clip (Prime) |
|---|---|---|---|---|
| 480p | $0.05 | $0.068 | $1.50 | $2.04 |
| 720p | $0.10 | $0.14 | $3.00 | $4.20 |
| 1080p | $0.20 | $0.28 | $6.00 | $8.40 |

## Alibaba targets everything from film production to robotics training

Alibaba is pitching Wan3.0 for a wide range of uses, from speeding up film production to generating short dramas and social media clips for content creators. Businesses could turn text and images into marketing and training videos, while tech developers could use it to produce realistic simulation footage for training autonomous vehicles and robotics systems.

The launch comes as Alibaba ramps up AI spending. The company just announced the largest share sale by a Hong Kong-listed company to fund its AI push, and last week [reported](https://www.reuters.com/business/retail-consumer/alibaba-beats-quarterly-revenue-estimates-2026-08-20/) a 75 percent year-over-year drop in quarterly profit driven by sharply higher AI investments.

```
AI News Without the Hype – Curated by Humans

					Subscribe to THE DECODER for ad-free reading, a weekly AI newsletter, our exclusive "AI Radar" frontier report six times a year, full archive access, and access to our comment section.				

					Subscribe now
```

[via X](https://x.com/Alibaba_Wan/status/2091725420857369081)