Wan Reference to Video Online - RefVid
Turn your own photos into videos in minutes · Your first video is free, no watermark
First video free, no card
Wan reference to video online, with no GPU and no ComfyUI workflow: the box above is set to Wan 3.0, Alibaba's newest Wan model.
Add 1 to 10 photos of a product or a character, write what happens, and Wan 3.0 makes a 3- to 30-second clip at 720p or 1080p that keeps your subject, with sound on or off. RefVid runs it through fal.ai's Wan 3.0 reference-to-video endpoint.
AERO 1: 3 photos
What it is
- Reference to video is the Wan mode that takes reference images, and on Alibaba's API also reference videos and audio, of the subjects that must appear, and generates a new clip around them. The references say who and what is on screen; your prompt says what happens.
- Wan 3.0, which Alibaba launched officially on August 24, 2026, takes up to 10 reference images, 5 reference videos and 5 audio clips and makes 2 to 30 seconds at 480p, 720p or 1080p, according to Alibaba Cloud's documentation. In RefVid you send it up to 10 photos of one subject.
Wan 2.6 reference to video vs Wan 3.0
- Most Wan reference to video guides and ComfyUI workflows were written for Wan 2.6 and 2.7. Wan 3.0 is the newer model: Alibaba says it roughly doubles the longest clip from Wan 2.7's 15 seconds to 30, and grows references from 5 images and videos combined, plus one voice, to 10 images, 5 videos and 5 audio clips. It also adds a sound switch and 480p.
- RefVid runs Wan 3.0 only, so a clip made here uses the newer model. On fal.ai, Wan 3.0 reference to video costs $0.10 a second at 720p and $0.20 at 1080p (read November 4, 2026).
Run it online in 3 steps
- 1. Add 1 to 10 photos of your product or character in the box at the top of this page. It is already set to Wan 3.0 and 720p, and the photos are saved as one subject for the next clip.
- 2. Write the actions in order, one per sentence, for example: "Hands cut the tape, lift the lid, take the shoe out and turn it toward the camera; the camera stays close." Settings changes the length (3 to 30 seconds), the shape (16:9, 9:16 or 1:1), 1080p and sound.
- 3. Press Generate. If you are not signed in, you sign in first and the clip starts right after. A clip usually takes 2 to 10 minutes, and we email you when it is ready.
What a Wan 3.0 clip costs on RefVid
- Every clip is priced in credits per second, with sound at the same price on Wan 3.0, and the studio shows the total before anything runs. New accounts get free credits for a first clip, with no watermark. After that, single videos start at $2.99, one-time credit packs at $9.90 and monthly plans at $10. A failed clip refunds its credits automatically.
More on AI video models
Reference to video →
Frequently asked questions
Can I run Wan reference to video online without ComfyUI?
Yes. The box at the top of this page runs Wan 3.0 on fal.ai's servers: add photos, write the scene, press Generate. No GPU, no download, no workflow to set up.
Is Wan 2.6 reference to video still the newest?
No. Wan 3.0 followed it, with clips up to 30 seconds and up to 10 reference images, 5 videos and 5 audio clips, according to Alibaba Cloud. RefVid runs Wan 3.0.
How many reference images does Wan 3.0 take?
Wan 3.0 takes up to 10 reference images on Alibaba's API, plus up to 5 reference videos and 5 audio clips. On RefVid you add up to 10 photos of one subject.
Is Wan reference to video free?
New accounts get 180 free credits for a first clip, with no card and no watermark. After that, a single video costs from $2.99, a credit pack from $9.90 and a plan from $10 a month, and a failed clip gives its credits back.
Can Wan 3.0 use photos of real people?
Yes. On RefVid, Wan 3.0 takes photos of people as well as products, pets and illustrated characters.