AI Video Generator
Alibaba's Wan 2.6 with its Flash tier: the lowest price per second in the Wan family for putting a still in motion.
Output
Four generations of Alibaba's Wan video model run on this site, and a newer one is not always dearer. A five second 720p clip costs 126 credits on Wan 2.6 or 2.7, 150 on Wan 2.5 and 180 on Wan 3.0, so the right pick depends on the length, the size and whether you start from a picture.
September 2025, with a low-cost 480p tier
Five or ten second clips at 480p, 720p or 1080p, from text or from a still. At 480p a five second clip costs 75 credits, the lowest price for a five second Wan clip written from text. From 720p up, Wan 2.6 and 2.7 cost less and do more.
Open the Wan 2.5 pageDecember 2025, with the low-cost Flash tier
Text and image to video in 5, 10 or 15 second clips at 720p or 1080p. Its Flash tier animates a still at 720p for 75 credits with sound or 38 without, the lowest price for a five second Wan clip from a picture.
April 2026, stills and clips from one model
Text and image to video at any whole second from 2 to 15, at 720p or 1080p, for the same price as Wan 2.6. The same page also makes stills: text to image and image to image at 15 credits each.
Open the Wan 2.7 pageThe newest, up to 30 seconds
Text, image and reference to video, where the reference mode takes images and a motion clip. Any length from 2 to 30 seconds, with a switch for sound. A five second clip is 90 credits at 480p; at 720p and 1080p it costs more than Wan 2.7.
Open the Wan 3.0 pageTwo old men at a stone chess table in an autumn park. The camera glides from the wide view to a hand setting down a knight, then across to the opponent, who sighs that he did not see it coming. The prompt named three framings and Wan 2.6 joined them into one unbroken move, ten seconds with the line at the end.
Two old men play chess at a stone table in a city park on an autumn afternoon, leaves drifting down. Shot 1 [0-3s]: wide shot of the table under the trees. Shot 2 [3-6s]: close-up, a weathered hand moves a black knight across the board with a firm click. Shot 3 [6-10s]: close-up of his opponent in a flat cap, who studies the board, sighs and says: "Well. I didn't see that coming." Sound: the click of the piece, rustling leaves, distant children playing, his voice, no music.
A knitted sweater on a hanger by an open window. Flash moves the curtains and the olive leaves while the cable knit stays sharp in every frame. With the sound switched off a Flash clip costs half, made for pages that play muted.
Start frameA soft breeze comes through the open window: the sheer linen curtains billow and the knitted sweater sways gently on its hanger while the olive leaves tremble in the sunlight. Locked-off camera, slow and calm, product video for an online shop.
A soaking wet golden retriever at the edge of a lake shakes itself off, spray flying around its legs, then barks once at the camera. The spray, the bark and the birds come out with the picture and land where they happen, from one first frame at 720p.
Start frameThe wet golden retriever shakes itself off hard from head to tail, water flying from its fur in bright droplets that catch the morning sun, then it looks at the camera and gives one happy bark. The camera holds steady at eye level. Sound: the spray of water, droplets hitting the lake, one bark, birds in the trees, no music.
Turn catalogue stills into short moving shots, silent for autoplay or with sound for social posts.
Animate a batch of product or travel photos with Flash at the lowest price per second in the Wan family.
Pick 15 seconds when one prompt or one frame needs a longer take.
How the model works, based on public documentation and sourced evidence.
Wan 2.6 is the December 2025 generation of Alibaba's Wan (Tongyi Wanxiang) model family, announced on December 16, 2025. The series spans five models: text-to-video, image-to-video, a new reference-to-video model (R2V), and two image models. Earlier open releases in the family (Wan 2.1 and 2.2) documented a diffusion transformer (DiT) design using flow matching with a spatio-temporal Wan-VAE for video compression, but Alibaba has not released open weights for 2.6, which is offered only as a hosted service.
The headline addition is reference-to-video: you upload one to three short reference videos of a person, and the model preserves both their appearance and their voice while generating new scenes from a text prompt. Alibaba describes it as China's first reference-to-video generation model. The 2.6 series also adds intelligent multi-shot storytelling, meaning a single prompt can produce a sequence of cuts with consistent characters, lighting, and sound across shots.
Per Alibaba's documentation, clips can run any whole number of seconds from 2 to 15 at 720p or 1080p, and reference-to-video is capped at 10 seconds. Multi-shot output is a request option that only takes effect when the model is allowed to rewrite the prompt, and you can supply your own audio track of 3 to 30 seconds for the model to sync against. Alibaba also cites improved audio-visual synchronization and stronger instruction following compared with earlier versions.
The main boundary to know: unlike Wan 2.2, the 2.6 weights are not public, so you cannot run it locally or fine-tune it for specialized tasks. Independent head-to-head tests also found its lip sync and audio clarity trailing Google's Veo 3.1 on dialogue-heavy and music clips.
On Vidney, Wan 2.6 runs text to video and image to video in 5, 10 or 15 second clips at 720p or 1080p, and every clip comes back with sound. Prompts are sent as written, so the multi-shot rewrite does not run here: a prompt that describes three shots comes back as one continuous camera move. The Flash tier is image to video only, at the same lengths and sizes, and it is the one with a sound switch; a silent Flash clip costs half. Reference to video, your own soundtrack and lengths other than 5, 10 and 15 seconds are not offered here.
Sources: github.com · wan.video
Wan 2.6 is Alibaba's December 2025 Wan release. On Vidney it makes 5, 10 or 15 second clips at 720p or 1080p, from a prompt or from a photo, and every clip comes back with sound. Its Flash tier is image to video only and is the one with a sound switch: turn the sound off and the clip costs half, which makes Flash the lowest price per second in the family for animating a picture. Shop pages, catalogue stills and social posts that play muted are where it earns its place. Standard Wan 2.6 costs the same as Wan 2.7, so for text to video most people step up to 2.7, which takes any length from 2 to 15 seconds and follows shots written into the prompt.
Create AI video with Wan 2.6 on Vidney in three steps.
Specs side by side with similar models, all runnable on Vidney.
| Wan 2.6 | Vidu Q4 Preview | Grok Imagine Video 1.5 | Grok Imagine Video 1.5 Lite | |
|---|---|---|---|---|
| Task modes | Text to Video · Image to Video | Image to Video · Reference to Video | Text to Video · Image to Video · Reference to Video | Text to Video · Image to Video |
| Duration | 5, 10, 15 seconds | 3–16 seconds | 1–15 seconds | 1–15 seconds |
| Resolution | 720p · 1080p | 540p · 720p · 1080p · 2K · 4K | 480p · 720p · 1080p | 480p · 720p · 1080p (upscaled from 720p) |
| Audio | Supported | Supported | Included, always on | Included, always on |
| Cost | 75–126 credits per generation | 159 credits per generation | 18 credits per generation | 18 credits per generation |
Recurring themes from public reviews, comparisons and creator write-ups. Both the good and the bad.
Creators consistently praise the reference-to-video feature for character consistency: it keeps the same face and even the same voice across newly generated scenes, which reviewers call a genuine unlock for spokesperson videos, talking-head content, and recurring characters.
The multi-shot storytelling mode, where the model rewrites a prompt into a sequence of shots, draws frequent praise for turning one prompt into a coherent multi-scene sequence with matched visuals, lighting and sound, which testers found especially effective for short ads and narrative clips.
Reviewers highlight its dynamic pacing and natural-sounding speech, noting that default outputs feel smooth and production-ready without much tuning.
A common complaint is the shift away from open source: creators who built local workflows around the open-weight Wan 2.2 are frustrated that 2.6 is API-only, with no way to self-host or fine-tune it.
Users also report lip-sync drift and background flicker on longer clips, and comparison tests found its audio clarity and lip sync less dependable than Veo 3.1 or Kling for dialogue-heavy work.
More AI video models you can run on Vidney.
Alibaba's first Wan with sound built in: speech, effects and music come out with the picture, from a low-cost 480p tier.
Up to 30 seconds in one pass, sound included: write the scene, animate a start frame, or cast it from reference images.
Alibaba's Wan 2.7 makes the frame and then moves it: stills, edits and clips with sound from one model family.
Generate AI video with Seedance 2.0: text to video and image to video, all from one Vidney workspace.
Generate AI video with Kling V3 Omni: text to video and image to video, all from one Vidney workspace.
Generate AI video with Kling 3.0: text to video and image to video, all from one Vidney workspace.
Wan 2.6 is an AI video model you can run on Vidney. It supports text to video and image to video from a single workspace.
Wan 2.6 costs 75–126 credits per generation. The exact credit cost is shown on the generate button before you run it. That is about $2.25–$3.78 per run at the Starter plan rate ($0.03 per credit).
Wan 2.6 supports the following aspect ratios: 1:1, 4:3, 3:4, 16:9, 9:16.
Wan 2.6 generates clips of 5, 10, 15 seconds.
Yes. Wan 2.6 can generate video with an audio track, and you can toggle sound on or off before generating.
Not with sign-up credits alone. New accounts get 10 to 30 free credits, and Wan 2.6 costs 75–126 credits per generation, so running it needs a plan. You can spend the free credits on lower-cost models first; the exact cost is always shown on the generate button before you spend a credit.
Yes. The videos you generate with Wan 2.6 on Vidney are yours to use in commercial projects: ads, social posts, client work, and product content. You keep the output; Vidney only handles generation and storage.
Only on the free plan. Free-plan downloads carry a small Vidney watermark; on any paid plan, Wan 2.6 videos download clean, ready to publish or hand to a client. Upgrading also removes the watermark from videos you already made.
The closest Wan 2.6 alternatives on Vidney are Vidu Q4 Preview, Grok Imagine Video 1.5, and Grok Imagine Video 1.5 Lite. They all run in the same workspace from one credit balance, so you can run the same prompt on each and compare the results side by side.
No. Vidney runs Wan 2.6 for you, so there are no API keys to manage and no separate provider account to set up.
