Wan 3
Generate cinematic videos up to 30 seconds from a text prompt or a starting image with Alibaba’s Wan 3, in 480p, 720p or 1080p with adaptive framing.
5 s · 720p
$0.7437 credits
from $0.16 · all options
- ✓ No subscription
- ✓ Pay per generation
- ✓ Credits valid 12 months
Pricing
What Wan 3 costs
You pay per generation. The app shows the exact price as you change the settings, before you click Generate.
| Setting | 5 s | 10 s | 15 s |
|---|---|---|---|
| 480p | $0.38 · 19 credits | $0.74 · 37 credits | $1.10 · 55 credits |
| 720p | $0.74 · 37 credits | $1.46 · 73 credits | $2.18 · 109 credits |
| 1080p | $1.46 · 73 credits | $2.90 · 145 credits | $4.34 · 217 credits |
Reference files and editing modes can add to the price. Credit packs from $4.99 for 200 credits. No monthly plan. See all packs
How to Use the App
Here’s what you get when you open the app: a short form, one run button, your results — no nodes, no setup.
Wan 3
App previewFill in the form
Prompt
RequiredType your prompt…
Aspect Ratio
adaptive
Duration
Enable Prompt Expansion
On by default
Image
Add images or files
+2 more options in the app
≈ 8–434 credits / run
Get your result
Real output generated with this app
What This App Does
Wan 3 is Alibaba’s video generation model. Describe a scene and it produces a short clip with cinematic motion and camera movement, or give it a starting image and it animates that frame following your prompt. Clips run from 2 to 30 seconds, long enough for a complete shot rather than a fleeting loop.
Key capabilities
Text to video — turn a written description into a video clip
Image to video — animate a first-frame image, guided by the prompt
Three output resolutions — 480p for drafts, 720p, and 1080p for final delivery
Long clips — any duration from 2 to 30 seconds
Adaptive framing — let the model choose the aspect ratio, or set 16:9, 9:16, 1:1, 4:3 or 3:4
Prompt expansion — short prompts are automatically expanded and optimized
Sound included — videos come with a generated audio track
Core inputs
prompt (text, required) — the video you want, ideally with subject, action, setting and camera movement
image (image, optional) — first frame to animate (jpg, png, bmp or webp); when provided, the aspect ratio follows the image
negative_prompt (text, optional) — what to keep out of the video
resolution — 480p, 720p or 1080p (default 1080p)
aspect_ratio — adaptive (default), 16:9, 9:16, 1:1, 4:3 or 3:4; ignored when an image is provided
duration — 2 to 30 seconds (default 5)
enable_prompt_expansion — on by default
seed (optional) — fix it to reproduce a result
The cost depends on the resolution and the duration: draft at 480p with short clips, then render the final version at 1080p.
Other Video models
Compare before you generate
Remix this appFor builders: open the workflow behind it to swap the model, chain steps, run batches or call it from the API.
Under the Hood
Want more control?
This app is powered by a fully editable AI-Flow workflow. Change the model, prompts, layout, resolution — or connect it to other steps.
Prompt
A small paper boat drifting across a calm misty lake at dawn, soft golden light on the water, slow cinematic dolly-in, mountains in the background
Image
Negative Prompt
Wan-3
How to Use This Template
Step 1: Enter your text in 'Prompt' Node
Fill the 'Prompt' node with the required text.
No example available.
Step 2: Upload your file
In the 'Image' node, upload the file you want to process.
No example available.
Step 3: Enter your text in 'Negative Prompt' Node
Fill the 'Negative Prompt' node with the required text.
No example available.
Step 4: Run the Flow
Click the 'Run' button to execute the flow and get the final output.
Frequently Asked Questions
Do I need a subscription to use Wan 3?
No. Buy a credit pack once, generate, and come back whenever you want. Purchased credits stay valid 12 months, and every new purchase extends them.
What is Wan 3?
Wan 3 is Alibaba’s video generation model. It turns a text prompt, or a starting image plus a prompt, into a video clip with cinematic motion and camera movement.
Can I animate an existing image?
Yes. Add an image and it becomes the first frame of the video; the prompt then describes how the scene should move.
How long can the videos be?
Any duration from 2 to 30 seconds. The default is 5 seconds.
Which resolutions are available?
480p, 720p and 1080p. 1080p is the default; 480p is the most economical choice for testing prompts.
How do I choose the format of the video?
Leave the aspect ratio on adaptive to let the model pick, or choose 16:9, 9:16, 1:1, 4:3 or 3:4. When you provide a starting image, the video follows the image’s format.
What drives the price of a run?
The resolution and the duration: the cost is charged per second of video, and higher resolutions cost more per second.
What does prompt expansion do?
When enabled, which is the default, Wan 3 rewrites short prompts into richer descriptions before generating. Turn it off when you want your prompt followed literally.
How can I keep unwanted elements out of the video?
Describe them in the negative prompt, for example blur, text overlays or distorted hands.
Can I reproduce a result?
Yes. Set the same seed with the same inputs to get a closely matching video.
How should I write a good prompt?
Start with the subject and the action, then add the setting, the camera movement (dolly in, aerial pan, tracking shot), the lighting and the mood.
How do I know what a generation will cost?
The app shows the exact price on the Generate button and updates it as you change the settings, before anything is billed.
Is there a free trial available?
Yes, AI-FLOW offers a free trial to get you started. After that, you can purchase credits as needed—no subscription or long-term commitment required.