Wan 2.6
Animate one start image into a video clip with Wan 2.6 by Alibaba, at 1,378 credits per clip. See its settings, limits and exact prices.
For the complete documentation index, see llms.txt. This page is also available as Markdown.
Wan 2.6 is an Alibaba model that animates one image: it has no text-to-video mode in the Studio, so you must attach a start image. The clip is 5 seconds, follows the shape of your image and has no sound option. It costs 1,378 credits per clip.
#At a glance
- Maker
- Alibaba
- Type
- Video model
- Modes
- Image to video
- Aspect ratios
- Follows the start image
- Outputs per run
- 1 to 4, set with Count
- Start image
- Required: one start image (JPEG, PNG or WEBP, up to 20 MB).
- Length
- 5 s only
- Resolution
- No resolution choice
- Sound
- No sound option
#What it costs
These are credits per clip, as of 2026-10-10. The Studio shows the live quote for your settings before you generate, and the total it charges is that quote multiplied by Count.
| Length | Credits per clip |
|---|---|
| 5 s | 1,378 |
#Use it in Studio
Step 1: Open Animate a Photo
In Studio, open Animate a Photo. Wan 2.6 needs a start image, so it works from this entry point. Sign in when the Studio asks.
Step 2: Choose Wan 2.6
Open the model picker, which groups models by maker, and choose Wan 2.6.
Step 3: Add your image and describe the motion
Attach one start image (JPEG, PNG or WEBP, up to 20 MB), then describe how it should move.
Step 4: Set the output
This model offers no aspect ratio, resolution, length or sound choice. Set Count from 1 to 4.
Step 5: Check the price and generate
The Studio shows the credit price for your settings. Videos run in the background: the card updates in place when the clip is ready, and the clip is saved to your Library.
#Limits
- Image to video only: the Studio says "Add an image to animate" until you attach a start image.
- You need to be signed in to generate. Wan 2.6 is available on every plan, including Free; credits are the limit.
- One start image only. The Studio has no end frame, no multiple reference images and no video-to-video input.
- A video that has not finished within 30 minutes is marked failed and refunded. A failed generation is refunded, and the Studio does not run a different model in its place.