WAN 3.0: native 30-second AI video generation
WAN 3.0 is the newest model in Alibaba's WAN AI video family, and the first that holds a shot for a full 30 seconds without cutting away. Feed it text, images, audio, video - or a document, or a web page URL - and it reads all of it as reference. 1080p, adaptive ratio, smart duration.
- Build continuous video scenes
- Use multiple reference types
- Guide motion and composition
Generate native 30-second videos in a single take
30 seconds, in one continuous take. The more useful part is that you no longer have to pick the number: describe the action and smart duration reads the pacing you implied, then sets the length to match. Because the clip runs unbroken, light, motion and pacing hold all the way through instead of resetting at a splice. Need longer? Extend any finished clip and keep building from a take that already works.
Point it at a document, or a web page
The 4 references you already use are all here - text, image, audio, video. WAN 3.0 adds two more. Drop in a document (.doc, .pdf, .ppt, .xls) and it reads the thing. Or just give it a URL: a product page, an article, a research paper, your own site. The spec sheet becomes the ad film. The landing page becomes the launch video. Long, multi-part instructions get parsed properly too, so a detailed request survives all the way to the final frame.
What you can create with WAN 3.0
Videos from documents
Hand over the deck, the PDF or the spec sheet you already wrote - or just the product page URL - and let the model build from it instead of starting at a blank prompt box.
Readable text, realistic detail, consistent motion
Put words on screen and WAN 3.0 renders them legibly and accurately, as text you can actually read - which counts for most in busy, information-heavy scenes, where there is the most to get wrong. Detail sits closer to real footage throughout. References hold at pixel level, so characters, objects, scenes, styles and audio all stay themselves across the sequence, and motion and emotion carry more range. Pin the first and last frame, and adaptive ratio shapes everything in between.
WAN 3.0 in Picsart: Find the right model for your video
You can find WAN 3.0 in Picsart's AI Playground, where a single prompt runs against 150+ other models at once and you see the difference before committing. It generates at 1080p, at roughly one to two seconds of render per second of finished video, with every input type in the same panel. WAN 2.7 sits alongside it: 15 seconds in fixed blocks of 5, 10 or 15, up to 5 reference images, and it still holds the 4K advantage. Pick 3.0 for length, input range and readable text. Pick 2.7 when resolution matters most.
Understand video model choices
Learn how to compare video models and choose an output.
Explore more models like WAN 3.0
Compare WAN 3.0 with other video models for motion, ads, and social clips.
WAN 3.0 FAQ
WAN 3.0 is the latest model in Alibaba's WAN AI video family. It generates a single continuous clip of up to 30 seconds at 1080p, accepts text, image, audio, video, document and web page URL references, and supports start and end frame control with adaptive aspect ratio.
Generate AI visuals with WAN 2.7
Pro
Most popularAI tools for everyday creative work.
Ultra
Most powerfulHeavy AI usage for creators & teams.
Enterprise
Custom AI solutions for large organizations.
- Volume discounts on credit rate
- On-demand top-ups