WAN 3.0 long-form AI video generator in DaVinci

Alibaba's WAN 3.0 is one of the video models DaVinci brings together from different AI providers. Create longer videos with sound from a prompt, an image, or mixed references, steady across the full take.

Why creators choose WAN 3.0 in DaVinci

Start Creating

Thirty seconds, one take in DaVinci

Longer runtimes generated in a single pass rather than assembled from fragments in DaVinci. No seams where one clip ends and the next begins, and no drift in the subject halfway through.

Every kind of reference in DaVinci

Bring in up to ten images, five video clips, and five audio clips at once inside DaVinci. Images hold the subject, video carries the movement, audio shapes the sound.

First and last frame in DaVinci

Define where the clip opens and where it closes, then let the model build the movement in between through DaVinci. The result lands where you planned it.

Sound with the picture in DaVinci

Audio is produced as part of the same generation rather than added later, so the clip arrives complete instead of silent in DaVinci.

How to create with WAN 3.0 in DaVinci

Start creating with Alibaba’s WAN 3.0 by following a few simple steps directly inside the DaVinci AI Toolkit.

Start Creating

Who WAN 3.0 is for in DaVinci

WAN 3.0 by Alibaba suits creators who need longer, sound-complete video with real control over subject and motion through DaVinci.

Try WAN 3.0
DaVinci for content creators

DaVinci for content creators

Fill a whole short-form slot with one generation instead of cutting three together in DaVinci. Keep the same character and the same setting from the first second to the last.

DaVinci for agencies and brands

DaVinci for agencies and brands

Produce full-length concept spots rather than fragments inside DaVinci. Feed in product shots and a reference clip and get something close to a finished cut back.

DaVinci for filmmakers and creative teams

DaVinci for filmmakers and creative teams

Explore a scene at its real length through DaVinci. Set the opening and closing frames, hand over reference footage for the camera move, and watch the whole beat play out.

Try WAN 3.0 in DaVinci

Enter a text prompt, upload an image, or add references, and generate a video with sound in seconds in DaVinci.

Start Creating

Powerful features in DaVinci

Inside DaVinci, WAN 3.0 brings together long single-pass generation, multimodal references, and native audio to produce video from text or images.

Start Creating

Text, image, and reference in DaVinci

In DaVinci, generate from a written prompt, animate a single still, or guide the result with images, video clips, and audio referenced directly in the prompt.

Extended single-pass duration in DaVinci

Inside DaVinci, longer clips generated in one go, so movement and identity stay consistent across the full runtime instead of resetting at every cut.

Native audio generation in DaVinci

Sound is created alongside the visuals as part of the same pass, covering effects, ambience, and speech inside DaVinci.

Keyframe control in DaVinci

Inside DaVinci, set a starting image and an ending image and the model generates the transition between them, giving the clip a defined beginning and end.

Frequently Asked Questions

DaVinci’s Video composer has a text prompt, Start Image, End Image, and Add References controls. With WAN 3.0 selected, add the source that defines the opening frame or subject and describe the movement. Check the preview before generating.

Yes. In DaVinci, add clear opening and ending frames for WAN 3.0, then describe the movement connecting them. Keep the same subject and compatible framing in both images; review the transition for jumps or changing features.

Yes. DaVinci’s WAN 3.0 listing marks audio output. Include dialogue, music, or sound effects in the prompt, then listen to the full clip for timing and unwanted sounds.

In DaVinci’s Video workspace, select WAN 3.0, enter the subject, action, setting, and camera move, then set duration and aspect ratio. Add a Start Image for an image-led clip; review the credit cost before generating.

Give WAN 3.0 one clear shot: subject, action, setting, camera move, and light. Example: “A street musician begins playing as the market opens; steady wide shot, then a slow move toward the performer.” Add dialogue or sound only when needed, then revise one instruction after reviewing the result.

Before generating with WAN 3.0, check the prompt’s subject and action, any Start Image or End Image, framing, aspect ratio, duration, resolution, and displayed credit cost. Add audio direction only when you want sound. These checks happen before the clip is made.

In DaVinci’s Video workspace, add the photo as the Start Image and describe the movement you want—for example, “slow push-in; the subject turns toward camera.” Select WAN 3.0, review the image preview and settings, then generate and check that the subject stays recognizable.

DaVinci shows 2–10 seconds duration, 480p–720p resolution, audio output. Choose the aspect ratio in Video settings, review the credit cost, and set the duration and resolution before generating.

Play the entire WAN 3.0 clip once at normal speed and once with attention to transitions. Check motion continuity, subject identity, framing, text, and visible artifacts. If the model includes audio, listen for timing and pronunciation before exporting.

Yes. Write a new WAN 3.0 prompt that changes only the camera move—for example, “replace the orbit with a slow dolly-in; keep the subject action and lighting.” Compare the two clips for unintended changes.

Design with DaVinci

Create with momentum. Bring your vision to life.

Sign Up