Speed when it matters
Prime is tuned for faster generation. Perfect for iterating on concepts, hitting content calendars and testing multiple creative directions in one session.
Alibaba Tongyi Wan AI Video
Ship faster with Wan 3.0 Prime
The high-speed edition of Wan 3.0. Same multimodal inputs — prompts, frames, up to 20 reference assets — and native audio, tuned for quicker turnaround when your schedule matters.
Text to Video / Image to Video
Wan 3.0 Primefirst_frame_url
Click to upload or drag and drop
last_frame_url (Optional)
Click to upload or drag and drop
Describe the shot. Type @ to reference attached media (e.g. @Image1, @Video1, @Audio1). Optional when media is attached.
Click or drop images here
Up to 10 images (JPG/PNG/WEBP), max 20MB eachClick or drop videos here
Up to 5 videos (MP4/MOV), max 100MB each, 15 seconds total; reference video time + output duration must stay within 30sClick or drop audio here
Up to 5 audio files (MP3/WAV), max 15MB each, 15 seconds total. Audio requires at least one reference image or video.Estimated cost 100 gems
Your video will appear here
What is Wan 3.0 Prime?
The high-speed edition of Wan 3.0. Same multimodal inputs — prompts, frames, up to 20 reference assets — and native audio, tuned for quicker turnaround when your schedule matters.
2–30sSingle-pass duration
480p / 720p / 1080pThree quality tiers
High-speedFaster turnaround tier
20 assetsReference images, videos, audio
Why creators use Wan 3.0 Prime
From a first idea to a finished clip, the workflow stays expressive and practical.
The full multimodal toolkit
Up to 10 reference images, 5 reference videos and 5 audio files per request — the same input power as standard Wan 3.0.
Frame-accurate control
Pin the first and last frames of your shot and let Prime handle the motion in between with your composition respected.
Native audio in one pass
Dialogue, ambience and effects are generated together with the picture for in-sync sound without a separate pass.
Rapid iteration loop
Draft at 480p to lock the idea, then re-run the winning prompt at 1080p — the speed tier makes the loop affordable.
Every format you publish
Adaptive framing or locked 16:9, 9:16, 1:1, 4:3 and 3:4 for any channel, from shorts to widescreen.
How to create a video
Steps from idea to downloadable result.
Write the direction
Describe the subject, action, camera and sound. Reference your attached assets with @Image1, @Video1 or @Audio1 tokens in the prompt.
Add visual or audio guidance
Upload a first frame with an optional last frame, or attach reference images, videos and audio. Choose one workflow — frames and references cannot be combined.
Set the shot
Pick resolution, aspect ratio and duration from 2 to 30 seconds. The studio estimates your cost live as you configure the shot.
Generate and review
Start the generation and watch the preview panel. Your clip is saved to My Creation, so you can close the page while it renders.
Iterate with intent
Refine the prompt, adjust duration or swap references. Longer takes benefit from beat-by-beat direction in the prompt.
Publish your best take
Download the finished MP4 and ship it — vertical for shorts, widescreen for the web, square for feeds.
Wan 3.0 Prime FAQ
Answers to common questions about inputs, settings and billing.
What is Wan 3.0 Prime?
Wan 3.0 Prime is the high-speed variant of Alibaba’s Wan 3.0 video model. It accepts the same inputs — text, first/last frames, reference images, videos and audio — and returns finished clips faster than the standard model.
How is Prime different from standard Wan 3.0?
Prime is optimized for speed. The input contract, resolutions, durations and audio support are the same; the trade-off is a higher per-second rate for quicker turnaround on tight deadlines.
What inputs does Wan 3.0 Prime support?
Text prompts, a first frame with optional last frame, and up to 10 reference images, 5 reference videos and 5 reference audio files per request.
How long can Prime videos be?
From 2 to 30 seconds per generation. With reference videos attached, reference duration plus output duration must stay within 30 seconds.
Does Wan 3.0 Prime generate audio?
Yes. A native audio track is generated in the same pass and can be switched off if you need silent footage.
How does billing work?
Cost is a flat per-second rate by resolution (480p, 720p or 1080p) multiplied by output duration. Audio does not change the price; reference media does not add billed seconds.
Need it faster? You found it.
Start with a prompt or upload a frame and generate with the high-speed Wan 3.0 Prime studio.
Start creating with Wan 3.0 Prime