WAN 3.0 Extend is part of the WAN 3.0 family.
See WAN 3.0Alibaba
WAN 3.0 Extend: AI video extension
Carry a video on past where it ends, keeping the same scene and subject. Source plus new footage must total 30 seconds or less.
$1.25 for a 5 second source clip at 720p. Video is paid per clip from your wallet, no subscription. The studio shows the price before you pay, and top ups start at $5.

Made with WAN 3.0 Extend on Enhance AI
Every clip here was rendered by WAN 3.0 Extend on Enhance AI, with the prompt that made it.
Continue this shot. The deer walks slowly along the trail, stops to look back, then steps into the ferns as the sun rays shift through the trees.
Continues an earlier clip. The new footage starts at 6.6 seconds.
10 seconds · 480p
Use this promptContinue this shot. The flock of flamingos circles low over the pink lake and lands in the shallow water, sending ripples across the reflections.
Continues an earlier clip. The new footage starts at 6.6 seconds.
10 seconds · 480p
Use this promptContinue this shot. The kayaker keeps paddling across the still lake toward the far shore as the mist slowly drifts over the water.
Continues an earlier clip. The new footage starts at 6.6 seconds.
10 seconds · 480p
Use this prompt
Key features
WAN 3.0 Extend turns a video you already have into video inside Enhance AI. It produces clips from 5 to 25 seconds at a resolution you choose, 720p by default. On top of that it renders adaptive, 16:9, 9:16, 1:1, 4:3 and 3:4. WAN 3.0 Extend is built by Alibaba. On Enhance AI it runs on the same account as every other model, with no separate subscription.
Clip length
WAN 3.0 Extend renders clips from 5 to 25 seconds, and you pick the length before you render. Longer clips cost more because video is billed by length, so rough out an idea short and only render the full length once the shot works.
Resolution
Choose 480p, 720p or 1080p before you render. A lower resolution costs less, so test a prompt low and rerender the keeper at the top setting. The studio shows the price for the setting you picked before anything is charged.
Input modes
Upload a video you already have and WAN 3.0 Extend continues it from the last frame, so the new segment matches the light, the framing and the motion of the original. Describe what should happen next and the model carries the shot forward without a visible join.
Aspect ratios
WAN 3.0 Extend renders adaptive, 16:9, 9:16, 1:1, 4:3 and 3:4. Pick the ratio for the platform before you render rather than cropping afterwards: 9:16 for Reels and Shorts, 16:9 for YouTube and 1:1 for feeds. The whole frame is generated for that shape.
Audio
WAN 3.0 Extend can generate sound with the picture, so the clip arrives with audio that matches what is on screen rather than silence you have to fill later. You can still mute it and lay your own voice or music track over the top in any editor.
Specifications
- Provider
- Alibaba
- Price
- $1.25 for a 5 second source clip at 720p
- Type
- Video
- Resolution
- 720p by default
- Duration
- 5 to 25 seconds
- Aspect ratio
- adaptive, 16:9, 9:16, 1:1, 4:3, 3:4
How to use WAN 3.0 Extend on Enhance AI
- 1
Sign in and pick WAN 3.0 Extend
Press Try on this page to open the Video Studio with WAN 3.0 Extend selected. Video is paid per clip from your wallet, which starts empty, so top it up first.
- 2
Upload the clip and say what happens next
Upload the video you want to continue and describe the next beat in plain words, using the same terms as the original prompt so the extension stays consistent. Then pick a length from 5 to 25 seconds, a resolution and an aspect ratio.
- 3
Generate, then download
Press Generate. You see the price before you confirm, and the clip lands in your history, ready to download.
Common questions
- What is WAN 3.0 Extend?
- WAN 3.0 Extend is a video extension model from Alibaba. It turns a video you already have into video: 25 second clips at 1080p with native audio.
- What do I need to upload to use WAN 3.0 Extend?
- A video and a written prompt. Add them in the studio on Enhance AI, check the preview and render. The output lands in your history, ready to download or to pass to another model on the same account.
- How long can a WAN 3.0 Extend clip be?
- WAN 3.0 Extend produces clips from 5 to 25 seconds. Longer runs cost more, because video is billed by length rather than by generation.
- What resolution does WAN 3.0 Extend output?
- WAN 3.0 Extend renders at 480p, 720p or 1080p. You pick the resolution before you render, and a lower one costs less.
- Does WAN 3.0 Extend generate audio?
- Yes. WAN 3.0 Extend can generate sound with the picture, so the clip arrives with audio rather than silence. Mute it and lay your own track over the top if you prefer.
- Is WAN 3.0 Extend free to try?
- No. Video on Enhance AI is paid per clip from your wallet, and a new account starts with an empty wallet, so there are no free WAN 3.0 Extend clips. The free tokens you get on signup, with no card needed, pay for image and audio tools, not video. Wallet top ups start at $5.
- What does it cost to run WAN 3.0 Extend?
- It costs $1.25 for a 5 second source clip at 720p. WAN 3.0 Extend renders are billed from your wallet by clip length, resolution and the length of the file you upload, so a short clip at a lower resolution costs less than a long one at full quality. You see the price for your settings before you render.
More from Alibaba
- WAN 3.0 ReferenceBuild a video from reference images, videos and audio with WAN 3.0, up to 30 seconds at 480p to 1080p with native audio.View
- WAN 3.0 Prime ReferenceThe higher quality tier of WAN 3.0 driven by reference images, videos and audio, up to 30 seconds at 480p to 1080p with native audio.View
- WAN 3.0 PrimeThe higher quality tier of WAN 3.0. Same controls, sharper results: up to 30 seconds with native audio, from 480p to 1080p.View
- WAN 3.0 ProThe high resolution tier of WAN 3.0, from 1080p up to 4k. Up to 30 seconds with native audio.View
- WAN 2.7Alibaba's WAN 2.7 model. High quality 720p or 1080p Image to Video with customizable aspect ratios.View
- HappyHorse 1.1Alibaba HappyHorse 1.1. Cinematic 720p or 1080p video from text or image with smooth motion.View
More from Enhance AI