Wan 2.7
videoAlibaba's Wan 2.7 video model. A clip from a prompt or two frames, or from reference pictures you name. Enhance is optional. There is no sound switch.
What it supports
- Aspect ratios
- 16:9, 9:16, 1:1, 4:3, 3:4
- Resolutions
- 720p, 1080p
- Duration
- 2–15s
- Prompt enhance
- Supported
What it costs
- 720p
- 12 credits per second
- 1080p
- 18 credits per second
Credits come with a Generator plan. The exact cost is shown on the Generate button before anything is spent.
Wan 2.7 is Alibaba's Wan video model for a clip with steady motion and a scene that follows the prompt. Use it from text, from frames you already like, or from several reference pictures.
What it is good at
Alibaba describes Wan 2.7 text-to-video as smooth motion with cinematic control and strong instruction following, and Wan 2.7 reference as a steadier hold on characters, props, and scenes. There is no sound setting on this model.
How to use it on Visxy
Write the shot. Give one picture as the opening frame and an optional second as the closing frame. Enhance is off until you turn it on; it lets the model expand the prompt before it generates. Or open Wan 2.7 Reference, attach two to five pictures, and name them @image1 onward in the prompt.
Where it differs
Wan 3.0 is the later Wan, with a sound switch and a larger set of reference pictures. Wan 2.7 Image makes stills. Wan 2.7 makes the clip.
FAQ
Can I use reference pictures?
Yes. Wan 2.7 Reference takes two to five pictures. Name them @image1, @image2, and so on in the prompt.
Is there sound?
No sound setting. Wan 3.0 is the Wan model with a sound switch.
What does Enhance do?
It expands the prompt before generation. It stays off unless you turn it on.
Can I set a last frame?
Yes. The second picture is the closing frame.
More video models
All video modelsPixVerse V6
PixVerse V6. A clip from a prompt or one opening picture, with sound you can turn on, or a clip guided by several reference pictures.
Grok Imagine Video
xAI's unversioned Grok video model. A clip from a prompt or from one opening picture. It is not the 1.5 model and it is not a still.
Grok Imagine 1.5
xAI's Grok Imagine 1.5 video model. A clip from a prompt or one opening picture, or from several reference pictures without @ tags.
Luma Ray 3.2
Luma's Ray video model on Visxy. A clip from a prompt, or from an opening frame and an optional closing frame. No sound switch.
Kling 2.6 Motion Control
Kuaishou's Kling 2.6 motion transfer. One picture of a subject plus one clip whose motion it copies. A prompt is optional.
Kling 3.0 Motion Control
Kuaishou's Kling 3.0 motion transfer. One picture of a subject plus one clip whose motion it copies. A prompt is optional.