Product reveals
Start on a lifestyle shot and end on the packshot, so the ad lands exactly on your product.
Wan3 AIWan 3.0 Image to Video Generator
Overview
What Is Wan 3.0 Image to Video?
In image to video, your picture becomes the exact first frame of the clip and Wan 3.0 generates the motion that follows. Add a second picture and it becomes the exact last frame; the model then plans the movement between the two.
Alibaba calls these modes first frame and first-and-last-frame to video. They cannot be combined with reference images in the same request, which is why Reference to Video has its own page. With the adaptive aspect ratio, the clip keeps the shape of your first frame.
Wan3 AI is an independent site, not an Alibaba product. We call Wan 3.0 through a third-party API and show the credit cost of every clip before you generate it.
Image to video on Wan3 AI
- Input
- 1 image (first frame) or 2 images (first and last frame), plus an optional prompt
- Image files
- JPG, PNG or WEBP, up to 10 MB each
- Clip length
- 2–30 seconds
- Resolution
- 480p, 720p or 1080p
- Aspect ratio
- Adaptive (follows the first frame), 16:9, 9:16, 1:1, 4:3 or 3:4
- Audio
- Generated with the video; can be switched off at the same price
- Lowest cost
- 14 credits (5 s at 480p)
Facts checked on 11 October 2026 against Alibaba's documentation.
How it works
Image to Video in Three Steps
- 01
Upload the first frame
Image 1 is used as the exact opening frame. Add a second image if the clip has to end on a specific picture.
- 02
Describe the motion
Say what moves, how the camera travels and what we should hear. With two frames, describe the change from the first to the last.
- 03
Set the format and generate
Choose length, resolution and aspect ratio (adaptive keeps the shape of your photo), check the credit cost and generate.
Use cases
What to Make With Image to Video
Photos that move
Add wind, a slow push-in or a subtle gesture to a portrait, a landscape or a product photo.
Character animation
Animate an illustration or a generated character from a fixed starting pose.
Planned transitions
Set where a shot begins and ends, for example a closed and an open box, and let Wan 3.0 fill in the change.
Prompt tips
Better Results From Your Frames
Describe motion, not the picture
The image already sets subject, style and light. Spend the prompt on what moves and how the camera travels.
Keep the two frames related
First and last frame work best when they share the subject, framing and light; describe the change between them rather than repeating what they show.
Use the adaptive ratio
Adaptive keeps the aspect ratio of your first frame, so nothing important gets cropped.
FAQ
Wan 3.0 Image to Video FAQ
What is the difference between Image to Video and Reference to Video?
Image to Video uses your pictures as the exact first and last frames. Reference to Video uses up to 9 pictures as a guide for characters, products or places without forcing any of them to appear as a frame. Wan 3.0 does not accept both in one request.
Is the last frame required?
No. One image gives a clip that starts on that picture; a second image is optional and sets the last frame.
Do I need a prompt?
The prompt is optional, but describing the motion and the camera gives you much more control than leaving it empty.
Which images can I upload?
JPG, PNG or WEBP up to 10 MB each. Alibaba accepts images between 240 and 8,000 pixels per side with an aspect ratio of up to 8:1.
How much does it cost?
A 5-second clip costs 14 credits at 480p, 28 at 720p and 55 at 1080p; 30 seconds at 1080p costs 329. The form shows the exact cost for your settings before you generate, and failed generations are refunded automatically.
Animate Your First Frame
Upload a photo, describe the motion and check the credit cost before you generate.