Wan 3.0 AI Video Generator
Alibaba's Wan 3.0 turns a prompt or a photo into up to 30 seconds of 1080p video with sound. Pick the length to the second, start from an image, or fix both the first and the last frame.
- Text to Video
- Image to Video
- First & Last Frame
- Length
- 2–30s
- Resolution
- 480p · 720p · 1080p
- Audio
- Native, optional
- Modes
- Text · Image · First & Last
- From
- 85 credits
What is Wan 3.0?
Wan 3.0 is the third generation of Alibaba's Wan video models. It writes a richer version of your prompt before it renders (prompt expansion), keeps characters steady across a long take and renders native audio with the picture.
On Trendai.video it runs in the same generator as Seedance 2.5, FLUX 3 Max and MiniMax H3 Max, so you can compare models on one prompt and pay with the same credits.
What you can do with it
- Text to video. Describe the scene and get a finished clip with camera movement and sound.
- Image to video. Upload a photo as the first frame; the video follows its framing.
- First & last frame. Give a start and an end image and Wan plans the motion between them.
- Long takes. Any whole length from 2 to 30 seconds, one of the longest ranges available.
- Six aspect ratios. 16:9, 9:16, 1:1, 4:3, 3:4, or adaptive.
Wan 3.0 pricing
You pay in credits for each video; the price for your exact settings is shown on the Generate button before you start. Failed generations are refunded automatically.
| Resolution | 5s | 10s | 15s | 20s | 30s |
|---|---|---|---|---|---|
| 480p | 213 | 425 | 638 | 850 | 1,275 |
| 720p | 425 | 850 | 1,275 | 1,700 | 2,550 |
| 1080p | 850 | 1,700 | 2,550 | 3,400 | 5,100 |
How to use Wan 3.0
- Open the generator with the model selected (the Try button on this page does it).
- Pick a mode: Text to Video, Image to Video, or First & Last Frame.
- Write the shot: subject, action, camera move, lighting and mood.
- Set the length, resolution and aspect ratio. The price updates as you change them.
- Generate and download the MP4. There is no watermark.
Wan 3.0 prompt ideas
Drone shot gliding over turquoise rice terraces at sunrise, mist rolling between the hills, a lone farmer in a straw hat walking the ridge, the camera tilts up to reveal mountains, birdsong and wind.
A pair of white sneakers lands on wet asphalt in slow motion, water splashing outward, neon reflections, the camera orbits once and pushes in on the logo, punchy bass hit.
Close-up of an old man in a dim workshop as he lifts a finished violin to the window light, dust floating, he smiles and draws the bow once, warm tungsten grade, a single sustained note.
Frequently asked questions
How long can a Wan 3.0 video be?
Any whole number of seconds from 2 to 30. Price scales with length, and the exact price is shown before you generate.
What resolutions does Wan 3.0 support?
480p, 720p and 1080p. 1080p costs twice as much per second as 720p.
Does Wan 3.0 make sound?
Yes, it can generate native audio with the video. You can switch audio off for a silent clip.
Can I animate my own photo?
Yes. Choose Image to Video and upload the photo as the first frame, or choose First & Last Frame to set both ends.
What happens if a generation fails?
The credits are refunded automatically. You are only charged for results you get.
Is adult or 18+ content allowed?
No. Trendai.video is for safe-for-work content only. Nudity, sexual content, real people without their consent and anything illegal are not allowed; prompts and outputs are moderated and accounts that try are removed.
Other models on Trendai.video
- Seedance 2.5ByteDance · Video · 720p · 4–30s · native audio
- FLUX 3 MaxBlack Forest Labs · Video · 1080p · 5–20s · native audio
- MiniMax H3 MaxMiniMax · Video · 1080p · 2–15s
- GPT Image 2.5OpenAI · Image · 4K · edit up to 16 photos
- Nano Banana 2.1Google · Image · 4K · mix up to 14 photos
- GPT Image 2OpenAI · Image · 2K · text to image