WAN 2.2 Text-to-Video Model (480p)
WAN 2.2 is an advanced text-to-video model provided by Cloud's DashScope platform. This model adopts an innovative MoE (Mixture of Experts) architecture for generating high-quality video content at 480p resolution.
Why it looks great
- Cinematic Aesthetics – professional-level control of lighting, color, and composition, delivering a true film-quality look.
- Natural Motion – restores complex movements with smooth transitions and precise controllability.
- Semantic Precision – understands complex scenes and multi-object interactions, keeping your creative intent intact.
- Multimodal Power – supports both text-to-video and image-to-video, flexible for storytelling, education, and creative content.
Pricing
| Video Length | Cost (USD) |
|---|
| 5 seconds | $0.05 |
How to Use
- Enter your prompt – describe the scene (e.g., camera angle, action, lighting).
- (Optional) Add a negative_prompt – specify what you don’t want in the video.
- Set size – choose output resolution (e.g., 832×480 or 480×832).
- Set seed – use -1 for random results, or fix a number for reproducibility.
- Click Run – preview and download your generated video.