Choose a category
3 models available
8 models available
3 models available
2 models available
4 models available
8 models available
Wan 3.0 Image to Video
Start from a still, optionally pin the ending, get up to 30 seconds with sound.
Frames
First frame is required; add a last frame to pin where the shot ends.
Creative Vision
Describe the motion, not the picture — the model can already see it.
Video Parameters
Priced per second — 2 seconds at 480P is 4 credits, 30 seconds at 1080P is 220.
Each step up doubles the price. Draft at 480P, finish at 1080P.
Auto keeps your first frame's shape — usually what you want.
AI audio synced to the video. Does not change the price.
Cinema Preview
Generation History0 records
Wan 3.0 Image to Video Generator
Upload one still and Wan 3.0 moves it — 2 to 30 seconds from a single frame at 480P, 720P or 1080P, with its own audio track. Add a second image and the clip lands on that frame at the end. Aspect ratio defaults to Auto, so the output keeps the shape of the picture you gave it.
Describe the motion, not the picture — the model can already see the picture
Why Choose Wan 3.0 for Image to Video
The image decides what the shot looks like; the prompt decides what happens to it. Wan 3.0 adds two things most image-to-video pages here do not have: an optional last frame that pins where the shot ends, and a length slider that runs all the way to 30 seconds.
First Frame Required, Last Frame Optional
Your upload is the opening frame, exactly as composed. Add a second image and the clip is planned to end on it — the same product from another angle, the same character in a new pose — instead of drifting wherever the motion takes it.
Any Length From 2 to 30 Seconds
A continuous slider, billed per second. Two seconds to check that the model reads your image the way you do; thirty for a full camera move from the same still.
480P, 720P or 1080P
Each step up doubles the price for the same length: five seconds is 9 credits at 480P, 20 at 720P and 40 at 1080P. The resolution is a separate dial from the length, so a long draft stays cheap.
Auto Keeps Your Image's Shape
Aspect ratio defaults to Auto, which matches the first frame — a vertical photo produces a vertical clip. Pick 16:9, 9:16, 1:1, 4:3 or 3:4 explicitly only when a delivery format demands it.
Native Audio, Plus a Reference Track
An AI-generated soundtrack is on by default at no change in price. Attach one mp3 or wav of up to 15 seconds as @Audio1 and its rhythm, music or voice shapes what the generated track and the motion do.
Standard or Prime: Compare One Variable
Both tiers accept the same first frame, optional last frame, prompt, audio, length and resolution; Prime costs about 1.6 times as much. We have not published a controlled same-input benchmark, so standard is the default. To test Prime fairly, reuse the same frames, prompt, seed and output settings.
One Frame In, a Whole Shot Out
Take the last frame of one clip, upload it as the first frame of the next, and you can build a sequence a shot at a time without leaving this page.
How to Use Wan 3.0 Image to Video
Everything you type should be about what changes — movement, camera, light, sound. The still already covers what things look like.
Upload the Opening Frame
JPEG, PNG or WebP up to 20MB. Use the composition you actually want, because with Auto the output takes its shape from this file. If you know where the shot should end, add a last frame as well.
Write the Motion
"The camera drifts left as the steam rises; she looks up and smiles" beats re-describing the frame. Chinese and English both work, and the box holds 20,000 characters. Attach a reference audio clip and mention it as @Audio1 if the pacing matters.
Test at 480P, 2 to 5 Seconds
4 credits for two seconds, 9 for five. This is where you learn whether the model thinks the subject is the person or the room behind them — and whether it reaches your last frame cleanly.
Extend and Raise the Resolution
Push the slider out and switch to 720P or 1080P for the keeper. Set a seed if you want to re-run the same settings and get the same clip. Generation takes a few minutes — longer for 30 seconds at 1080P — and the result lands in your history.
One Dial at a Time
Change the prompt or the length or the resolution between runs, not all three. When a result improves you want to know which change did it.
Wan 3.0 Image to Video
FAQ
Image requirements, the optional last frame, aspect ratio, audio, pricing and how this page differs from Wan 3.0 Video and the Prime tier.
It is Alibaba's Wan 3.0 model, standard tier, driven by a still: you upload a first frame, describe the motion, and it generates 2 to 30 seconds from that starting point with audio. Optionally you add a last frame to fix where the clip ends. FlowVeo3 is an independent platform and is not affiliated with Alibaba.
JPEG, PNG and WebP, up to 20MB each, for both the first and the last frame. The first frame is required and the last is optional. Higher-resolution stills give the model more detail to hold on to across a long clip.
Between 4 and 220 credits, set by length and resolution. Five seconds is 9 credits at 480P, 20 at 720P and 40 at 1080P; the full thirty seconds is 110 credits at 720P and 220 at 1080P. A last frame, a reference audio clip and the audio toggle do not change the price. The exact cost is shown before you submit.
Your image's, by default. The ratio control starts on Auto, which matches the first frame instead of fitting it into a fixed shape. Choose 16:9, 9:16, 1:1, 4:3 or 3:4 explicitly only when the delivery format requires it.
Not here. This page animates one frame, with an optional closing frame. For a prompt plus up to 10 reference images called out as @Image1, @Image2 and so on — a character from one, a set from another — use Wan 3.0 Video. Reference images and a first frame cannot be combined in one run.
Wan 3.0 Image to Video Prime is a separately priced upstream tier with the same public inputs and controls, at roughly 1.6 times the price per second. We do not promise a specific quality or speed advantage without a controlled comparison. Start with standard; to evaluate Prime, repeat the same frames, prompt, seed, length and resolution so the model tier is the only variable.
Usually a few minutes, and longer for 30-second 1080P clips. You can leave the page; the result lands in your history and stays available for seven days, so download anything you want to keep. If the generation fails, the held credits are released back to your balance automatically.
Try Wan 3.0 Image to Video
One still, up to thirty seconds, with sound. Draft it for 4 credits.