← All models
AlibabaVideo
Wan 2.7
Flexible video generation — text, image, or multi-reference to video
Try Wan 2.7About
Wan 2.7 is Alibaba's video generation family, supporting text-to-video, image-to-video, and reference-to-video modes based on your inputs. It produces smooth, coherent video up to 15 seconds long at 720p or 1080p, with support for up to 5 reference images. A dedicated video editing mode lets you apply style transfers, replace elements, or modify content with text instructions.
How to prompt
- Describe motion and pacing: "slow motion", "time-lapse", "smooth tracking shot", "handheld camera"
- For image-to-video, provide a strong first frame — the model animates forward from it
- Use multiple reference images to keep characters or products consistent across the clip
- Longer durations (10–15s) work best with simple, continuous actions
- Specify aspect ratio to match your platform: 16:9 for YouTube, 9:16 for TikTok/Reels
Best for
Social media video, product animation, character-consistent clips, video editing and style transfer, longer-form generation
Good to know
No native audio — pair with a separate audio workflow. The Pro reference mode costs the same but uses a higher-quality base model.
Ready to create with Wan 2.7?
Open Lyvia