WAN 2.7 is a video generation model from Alibaba. It turns a written prompt or a still image into video: 15 second clips at 1080p.

Can WAN 2.7 turn a photo into a video?

Yes. Upload a still image, describe the movement you want, and WAN 2.7 animates it. It also works from a written prompt alone.

When was WAN 2.7 released?

Alibaba released WAN 2.7 on 3 April 2026. You can run it on Enhance AI now, along with every other video model on one account.

What is new in WAN 2.7 compared to WAN 2.6?

Compared with WAN 2.6, WAN 2.7 accepts an end frame. Both run on the same account, so you can pick whichever fits the shot and the budget.

How long can a WAN 2.7 clip be?

WAN 2.7 produces clips from 2 to 15 seconds. Longer runs cost more, because video is billed by length rather than by generation.

What resolution does WAN 2.7 output?

WAN 2.7 renders at 720p or 1080p. You pick the resolution before you render, and a lower one costs less.

Is WAN 2.7 free to try?

For images, yes: every new account gets free tokens on signup, no card required, and they cover WAN 2.7 images. For video, no: video is paid per clip from your wallet, and a new account starts with an empty wallet, so there are no free WAN 2.7 clips. Wallet top ups start at $5.

What does it cost to run WAN 2.7?

It costs $1.00 for a 5 second clip at 720p. WAN 2.7 renders are billed from your wallet by clip length and resolution, 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. WAN 2.7 images are billed in tokens instead, and you see that cost before you generate too.

Alibaba

WAN 2.7 AI video generator

Alibaba's WAN 2.7 model. High quality 720p or 1080p Image to Video with customizable aspect ratios.

$1.00 for a 5 second 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.

Try WAN 2.7 Browse all models

Example videos made on Enhance AI

These videos come from related models on the same account. The model that made each one is named under it.

A wolf pack moving through fresh snow at dusk, breath steaming, birch trees bare. Slow orbit around the subject, golden hour light, warm colour grade. Cinematic and photorealistic, natural motion. Photographic, natural, no text, no lettering, no captions, no subtitles, no watermark, no logo, no brand names, no product labels, no user interface, no screens, no recognisable fictional characters, no celebrities or recognisable real people.
Generated with MiniMax H3 Max
A sand dune ridge at sunrise, wind lifting sand grains off the crest, a caravan of camels far below. Aerial view gliding forward, backlit with a soft lens flare, hazy air. Cinematic and photorealistic, natural motion. Photographic, natural, no text, no lettering, no captions, no subtitles, no watermark, no logo, no brand names, no product labels, no user interface, no screens, no recognisable fictional characters, no celebrities or recognisable real people.
Generated with MiniMax H3 Max
Monsoon rain hammering a tin roof, children running for cover across a muddy courtyard. Smooth tracking shot moving alongside the subject, harsh midday sun, deep shadows. Cinematic and photorealistic, natural motion. Photographic, natural, no text, no lettering, no captions, no subtitles, no watermark, no logo, no brand names, no product labels, no user interface, no screens, no recognisable fictional characters, no celebrities or recognisable real people.
Generated with MiniMax H3 Max
A high speed train streaking past rice paddies, reflections on the flooded fields. Crane shot rising from ground level, crisp clear daylight, vivid colours. Cinematic and photorealistic, natural motion. Photographic, natural, no text, no lettering, no captions, no subtitles, no watermark, no logo, no brand names, no product labels, no user interface, no screens, no recognisable fictional characters, no celebrities or recognisable real people.
Generated with MiniMax H3 Max
A grandmother kneading dough in a sunlit farmhouse kitchen, flour dust floating in the light. Gentle handheld camera, blue hour, cool tones with warm highlights. Cinematic and photorealistic, natural motion. Photographic, natural, no text, no lettering, no captions, no subtitles, no watermark, no logo, no brand names, no product labels, no user interface, no screens, no recognisable fictional characters, no celebrities or recognisable real people.
Generated with MiniMax H3 Max
A descending view toward a waterfall in a jungle gorge, rainbows in the spray. Steady shoulder level follow shot, moody low key lighting, fine film grain. Cinematic and photorealistic, natural motion. Photographic, natural, no text, no lettering, no captions, no subtitles, no watermark, no logo, no brand names, no product labels, no user interface, no screens, no recognisable fictional characters, no celebrities or recognisable real people.
Generated with MiniMax H3 Max

Key features

WAN 2.7 turns a written prompt and a still image you upload into video inside Enhance AI. It produces clips from 2 to 15 seconds at 720p or 1080p. On top of that it renders 16:9, 9:16, 1:1, 4:3 and 3:4. WAN 2.7 is built by Alibaba. On Enhance AI it runs on the same account as every other model, with no separate subscription.

Clip length

WAN 2.7 renders clips from 2 to 15 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 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

Start from a written prompt or from a still image. Text to video gives WAN 2.7 the most freedom; image to video locks the first frame, so a product, a face or a location stays as you shot it while the motion is generated around it.

End frame control

WAN 2.7 accepts an end frame as well as a first one. Give it where the shot should finish and it renders the motion between the two, which is how you get a clean transition into the next clip or a shot that lands on a product.

Aspect ratios

WAN 2.7 renders 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.

Specifications

Provider: Alibaba
Price: $1.00 for a 5 second clip at 720p
Type: Video and Image
Released: 3 April 2026
Resolution: 720p or 1080p
Modes: Text to image, Text to video, Image to video
Duration: 2 to 15 seconds
Aspect ratio: 16:9, 9:16, 1:1, 4:3, 3:4

WAN 2 models on Enhance AI

ModelModesLengthResolutionPrice

WAN 2.5 ExtendVideo extension5 to 10 seconds480p to 1080p$1.00 for a 5 second clip at 720pView
WAN 2.7 Video EditVideo editingNot listed720p or 1080p$2.00 for a 5 second source clip at 720pView
WAN 2.5 ProText to video, Image to video5 to 10 seconds1080p$1.00 for a 5 second clipTry
WAN 2.5 FastText to video, Image to video5 to 10 seconds1080p$1.00 for a 5 second clipTry
WAN 2.6Text to video, Image to video5 to 15 seconds1080p$1.00 for a 5 second clipTry
WAN 2.6 FlashImage to video5 seconds720p$1.00 for a 5 second clip at 720pTry
WAN 2.6 Flash ReferenceReference to video5 to 10 seconds1080p$1.00 for a 5 second clipTry
WAN 2.6 ExtendVideo extension5 to 10 seconds720p or 1080p$1.00 for a 5 second clip at 720pTry
WAN 2.6 ReferenceReference to video5 to 10 seconds1080p$2.00 for a 5 second clipTry
WAN 2.7 ProText to imageNot listedNot listedFrom 17 tokens an imageTry
WAN 2.7 ExtendVideo extension2 to 10 seconds720p or 1080p$1.00 for a 5 second clip at 720pTry
WAN 2.7 ReferenceReference to video5 to 10 seconds720p or 1080p$2.00 for a 5 second clip at 720pTry
WAN 2.2 480pText to video, Image to video5 to 8 seconds480p$0.30 for a 5 second clipTry
WAN 2.2 720pText to video, Image to video5 to 8 seconds720p$0.60 for a 5 second clipTry

How to use WAN 2.7 on Enhance AI

1
Sign in and pick WAN 2.7
Press Try on this page to open the Video Studio with WAN 2.7 selected. Video is paid per clip from your wallet, which starts empty, so top it up first.
2
Describe the clip or upload a frame
Write a prompt that says what is in the shot, where it is and how the camera moves, or upload a still image to animate as the first frame. Then pick a length from 2 to 15 seconds, a resolution and an aspect ratio.
3
Generate, then download or extend
Press Generate. You see the price before you confirm, and the clip lands in your history, ready to download, upscale or extend.

Common questions

What is WAN 2.7?: WAN 2.7 is a video generation model from Alibaba. It turns a written prompt or a still image into video: 15 second clips at 1080p.
Can WAN 2.7 turn a photo into a video?: Yes. Upload a still image, describe the movement you want, and WAN 2.7 animates it. It also works from a written prompt alone.
When was WAN 2.7 released?: Alibaba released WAN 2.7 on 3 April 2026. You can run it on Enhance AI now, along with every other video model on one account.
What is new in WAN 2.7 compared to WAN 2.6?: Compared with WAN 2.6, WAN 2.7 accepts an end frame. Both run on the same account, so you can pick whichever fits the shot and the budget.
How long can a WAN 2.7 clip be?: WAN 2.7 produces clips from 2 to 15 seconds. Longer runs cost more, because video is billed by length rather than by generation.
What resolution does WAN 2.7 output?: WAN 2.7 renders at 720p or 1080p. You pick the resolution before you render, and a lower one costs less.
Is WAN 2.7 free to try?: For images, yes: every new account gets free tokens on signup, no card required, and they cover WAN 2.7 images. For video, no: video is paid per clip from your wallet, and a new account starts with an empty wallet, so there are no free WAN 2.7 clips. Wallet top ups start at $5.
What does it cost to run WAN 2.7?: It costs $1.00 for a 5 second clip at 720p. WAN 2.7 renders are billed from your wallet by clip length and resolution, 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. WAN 2.7 images are billed in tokens instead, and you see that cost before you generate too.