Wan 3 is a video-generation model in Alibaba's Wan model family. FastMoro AI provides supported text-to-video, image-to-video, and reference-to-video workflows.

How long can a Wan 3 video be?

Set a generated duration from 2 to 30 seconds. When you include reference videos, their combined duration plus the output duration must not exceed 30 seconds.

Which resolutions and aspect ratios are available?

Wan 3 supports 480P, 720P, and 1080P. Choose adaptive, 16:9, 4:3, 1:1, 3:4, or 9:16 framing in the Studio.

Does Wan 3 generate audio?

Yes. Audio is enabled by default and can be turned off before generation. Include sound, dialogue, or ambience in the prompt when it matters to the shot.

Can I animate an image with Wan 3?

Yes. Image-to-video accepts a start frame and an optional end frame. Use the prompt to describe the motion between them.

What reference media can I upload?

Reference-to-video accepts up to 10 images, 5 video clips, and 5 audio clips. FastMoro AI does not currently provide document or webpage references for Wan 3.

How should I write a Wan 3 prompt with references?

Identify each asset by order and role: say that Image 1 defines the product, Image 2 defines the location, and Video 1 provides the movement reference.

Is FastMoro AI the official Wan website?

No. FastMoro AI is an independent AI creation platform that provides access to supported Wan 3 video workflows.

FastMoro AI

Wan 3 AI Video Generator

Create a Wan 3 video from a prompt, a start frame, or reference media. Choose a 2–30 second duration, 480P, 720P, or 1080P output, a shot ratio, and whether to generate audio with the video.

Wan 3 Video Controls at a Glance

Choose the input workflow, then set the duration, output quality, framing, and audio controls that fit the shot.

Text, Image, and Reference Workflows

Start from a prompt, animate an image with an optional end frame, or use reference media when the shot needs more visual, motion, or audio direction.

Open Video Studio

Live Preview

Set a 2–30 Second Duration

Choose an integer duration from 2 to 30 seconds. A longer duration can give an action, camera move, and sound cue more room to develop.

Open Video Studio

Live Preview

Use Purposeful Reference Media

Reference-to-video accepts up to 10 images, 5 video clips, and 5 audio clips. Name the role of each item in the prompt so the requested shot is clear.

Open Video Studio

Live Preview

Configure the Output Before Generation

Select 480P, 720P, or 1080P; a supported aspect ratio; and whether audio should be generated with the video before starting the task.

Open Video Studio

Live Preview

Wan 3 Video Examples

Explore sample clips for visual direction and prompt ideas; generation results vary with the prompt, references, and selected controls.

How to Create with Wan 3 in FastMoro AI

Use the workflow that matches the amount of direction your shot needs, then set the output controls before generation starts.

Text to Video

Describe the subject, action, camera movement, lighting, framing, and sound. Start with one direct shot sentence, then add only the details that matter to the result.

Image to Video with an Optional End Frame

Upload a start image to animate a still. Add an end frame when you want to guide where the shot finishes, and use the prompt to explain the motion between them.

Reference to Video for Richer Direction

Use up to 10 reference images, 5 video clips, and 5 audio clips. Identify their roles in the prompt—for example, Image 1 for the product and Video 1 for movement.

Duration, Resolution, Ratio, and Audio

Choose 480P, 720P, or 1080P; an integer duration from 2 to 30 seconds; adaptive through 9:16 framing; and whether the generated video includes audio.

Plan a Complete Shot

A longer duration gives an action, camera move, and sound cue more room to develop. When using reference video, input duration plus output duration must remain within 30 seconds.

Describe Sound with the Action

Audio is enabled by default. Include dialogue, ambience, or a sonic beat in the prompt when sound matters to the requested scene.

What to Create with Wan 3

Wan 3 is useful when a text-only idea or single still needs more deliberate visual and audio direction.

Product Demonstrations

Use a product image as the start frame, then state the material, hand action, camera distance, and sound you want to explore.

Vertical Social Concepts

Choose 9:16 and specify a mobile-first framing, subject movement, and sound environment for a feed-ready video concept.

Shot Previsualization

Test an establishing move, action beat, or close-up by naming the lens feel, blocking, lighting, and camera path before a larger production.

Campaign Scenes

Combine approved visual references with a concise brief to explore an advertising scene while retaining the intended subject and setting.

Character and World Concepts

Use character, environment, and prop references to describe a specific moment for a game-world concept, trailer, or pitch.

Mood and Style Films

Pair a style image with audio or motion references and a clear prompt that names the atmosphere, pace, and focal detail.

Choose the Wan 3 Workflow for Your Starting Point

All three workflows use Wan 3 controls in FastMoro AI. Pick the one that best matches the inputs you already have.

Choose the Wan 3 Workflow for Your Starting Point
Workflow	Text to Video	Image to Video	Reference to Video
Starting input	Available A written scene or shot prompt.	Available A start image, with an optional end frame.	Available Images, video clips, and audio clips with a prompt.
Reference media	Not used Not required.	Optional One start image; an end frame is optional.	Available Up to 10 images, 5 videos, and 5 audio clips.
Duration	Available Choose 2–30 seconds.	Available Choose 2–30 seconds.	Available Choose 2–30 seconds; reference-video duration plus output must not exceed 30 seconds.
Output controls	Available 480P–1080P, aspect ratio, and audio.	Available 480P–1080P, aspect ratio, and audio.	Available 480P–1080P, aspect ratio, and audio.
Best when	Available You are creating the scene from a written brief.	Available You need the shot to begin from a specific still.	Available You need several media assets to guide the shot.

Starting input

Text to VideoAvailable

A written scene or shot prompt.

Image to VideoAvailable

A start image, with an optional end frame.

Reference to VideoAvailable

Images, video clips, and audio clips with a prompt.

Reference media

Text to VideoNot used

Not required.

Image to VideoOptional

One start image; an end frame is optional.

Reference to VideoAvailable

Up to 10 images, 5 videos, and 5 audio clips.

Duration

Text to VideoAvailable

Choose 2–30 seconds.

Image to VideoAvailable

Choose 2–30 seconds.

Reference to VideoAvailable

Choose 2–30 seconds; reference-video duration plus output must not exceed 30 seconds.

Output controls

Text to VideoAvailable

480P–1080P, aspect ratio, and audio.

Image to VideoAvailable

480P–1080P, aspect ratio, and audio.

Reference to VideoAvailable

480P–1080P, aspect ratio, and audio.

Best when

Text to VideoAvailable

You are creating the scene from a written brief.

Image to VideoAvailable

You need the shot to begin from a specific still.

Reference to VideoAvailable

You need several media assets to guide the shot.

A practical Wan 3 workflow

Plan the Shot, Then Give Wan 3 the Right Inputs

The clearest requests explain what the viewer sees, what changes over time, how the camera moves, and which references define the important details.

Start with a Shot Sentence

Name the subject, action, place, time of day, camera treatment, and sound in one direct sentence before adding visual detail.

Give Every Reference a Role

Keep uploaded media purposeful. Tell the model whether each item defines a character, product, location, movement cue, or audio mood.

Match Controls to the Deliverable

Pick the ratio, duration, resolution, and audio option before generating so the first version is aligned with the review or publishing context.