Wan 3.0 · Clipia

Wan 3.0 longer scenes, more inputs

Create clips from text, frames or references. Choose an available mode, Standard or Prime, duration and sound.

duration: up to 30 s
variants: Standard / Prime
Clipia status: available

In brief

What is Wan 3.0 Video?

Wan 3.0 combines text generation, start and end frames, and multimodal references. Text mode can also take a document. Prime is a faster variant of the same model.

2–30 s: duration
up to 1080P: resolution
T2V / I2V / R2V: model modes
Prime: faster option

Standard · T2V

An alpine train at sunrise

An uninterrupted eight-second shot tracks an emerald train over a stone viaduct, then reveals mountains, morning mist and warm light in the windows. The clip includes an audio track.

How to direct the scene

Specify one continuous tracking move beside the train before widening to reveal the viaduct and valley. Call out believable railway geometry, sunrise light and the desired sound atmosphere.

Open this mode

Prime · T2V

Glass and crimson silk

Prime produces an eight-second product shot: a clear bottle stays in focus as crimson silk curls around it. Lighting brings out glass refraction; the clip includes an audio track.

How to direct the scene

Describe one uncut macro shot of a bottle on dark stone, a smooth half-orbit, flowing silk and crisp reflections. Specify the desired sound atmosphere separately.

Open this mode

Image → video

A basketball court comes alive

A source frame of a woman near the court becomes a six-second moving shot: she lowers her phone and turns toward the game as the camera reveals a basket. The clip includes an audio track.

How to direct the scene

Preserve the subject, clothes and evening light from the source image. In one shot, have her turn toward the game as the camera slides to the hoop; specify natural ball physics and the desired sound atmosphere.

Open this mode

Open an available model mode. The editor shows settings and pricing.

Create with Wan 3.0

Parameter	Value	Note
Duration	2–30 seconds or Auto	Input video duration plus the new clip cannot exceed 30 seconds
Resolution	480P, 720P, 1080P	Three levels in both Standard and Prime contracts
Modes	T2V, I2V, R2V	The same inputs for Standard and Prime
Audio	Native generation	The audio option can be switched on or off
Aspect ratio	adaptive and 5 fixed ratios	16:9, 4:3, 1:1, 3:4, 9:16
Inputs	Up to 10 images, 5 videos, 5 audio clips	Text mode accepts one document up to 100 MB and 50 pages. Video and audio references each have a 15-second total limit.

Text to video

The prompt describes the scene; optionally attach a document.

Open this mode

Start and end frames

A starting frame is required in I2V; an end frame is optional.

Open this mode

Multimodal references

Combine images, video clips and audio tracks in one request.

Open this mode

Standard and Prime

The speed choice selects a faster variant of the same model.

Open this mode

Parameter	Standard	Prime
T2V / I2V / R2V	All three mode groups	The same three mode groups
Speed	Base processing queue	Faster processing
Clipia price and status	Exact price unpublished; disabled	Exact price unpublished; disabled

Choose a mode

Text, a starting frame or a reference set.

Prepare the inputs

Upload frames or media; text mode can also use a document.

Set speed and length

Choose Standard or Prime, 2–30 seconds or Auto, resolution and sound.

Choose Standard or Prime with the speed selector in the editor.

Create with Wan 3.0

Open the mode and choose your settings to see the quote before generation.

Auto reserves the amount for up to 30 seconds. After successful generation, the unused portion is returned.

Write scene beats

Describe what happens at the start, middle and end of a longer clip.

Name your references

Use Image1, Video1 and Audio1 in the same order as the uploads.

Keep input modes separate

Start/end frames and universal references are different input modes.

Short advertisement

Up to 30 seconds lets a scene develop without an outside edit.

Storyboard transition

Start and end frames guide the arc of a clip.

Brief adaptation

A document, link and media can inform a future request.

Check the required mode in the catalog and request a quote before generation. Parameters vary by mode.

Clipia documentation

FAQ

Are Standard and Prime available in Clipia?

Yes. Use the generation links to open available modes. Each mode is enabled after verification; the editor shows the current selection.

Is Prime a separate model or mode?

It is the faster Wan 3.0 variant. Standard and Prime both support T2V, I2V and R2V; Prime adds no separate creative input.

How long can a video be?

Choose 2–30 seconds or Auto to let the model choose. Input video duration plus the new clip cannot exceed 30 seconds.

How many credits are Standard and Prime?

The exact credit cost is calculated for your selected settings and shown in the editor before generation.

Where are the real Wan 3.0 samples?

Yes. The demos show Standard and Prime from text and Standard from a source image. A multimodal reference demo has not been published yet.

Can I use Wan 3.0 through the Clipia API?

Yes, for modes marked active in the Clipia catalog. Check the parameters and quote before creating a task.

Create video

Create your scene with Wan 3.0

Open an available mode, describe your scene and choose settings. The quote appears before generation.

Create with Wan 3.0

Wan 3.0 Video demo

Watch the clip and explore its motion, detail, and camera work.

Watch demo

Open Wan 3.0 Video in the editor

Wan 3.0 Video — русская версия

Wan 3.0 · Clipia

Wan 3.0 longer scenes, more inputs

Create clips from text, frames or references. Choose an available mode, Standard or Prime, duration and sound.

Create with Wan 3.0 See examples

duration: up to 30 s
variants: Standard / Prime
Clipia status: available

In brief

What is Wan 3.0 Video?

Wan 3.0 combines text generation, start and end frames, and multimodal references. Text mode can also take a document. Prime is a faster variant of the same model.

2–30 s: duration
up to 1080P: resolution
T2V / I2V / R2V: model modes
Prime: faster option

Standard · T2V

An alpine train at sunrise

An uninterrupted eight-second shot tracks an emerald train over a stone viaduct, then reveals mountains, morning mist and warm light in the windows. The clip includes an audio track.

How to direct the scene

Specify one continuous tracking move beside the train before widening to reveal the viaduct and valley. Call out believable railway geometry, sunrise light and the desired sound atmosphere.

Open this mode

Prime · T2V

Glass and crimson silk

Prime produces an eight-second product shot: a clear bottle stays in focus as crimson silk curls around it. Lighting brings out glass refraction; the clip includes an audio track.

How to direct the scene

Describe one uncut macro shot of a bottle on dark stone, a smooth half-orbit, flowing silk and crisp reflections. Specify the desired sound atmosphere separately.

Open this mode

Image → video

A basketball court comes alive

A source frame of a woman near the court becomes a six-second moving shot: she lowers her phone and turns toward the game as the camera reveals a basket. The clip includes an audio track.

How to direct the scene

Preserve the subject, clothes and evening light from the source image. In one shot, have her turn toward the game as the camera slides to the hoop; specify natural ball physics and the desired sound atmosphere.

Open this mode

Open an available model mode. The editor shows settings and pricing.

Create with Wan 3.0

Parameter	Value	Note
Duration	2–30 seconds or Auto	Input video duration plus the new clip cannot exceed 30 seconds
Resolution	480P, 720P, 1080P	Three levels in both Standard and Prime contracts
Modes	T2V, I2V, R2V	The same inputs for Standard and Prime
Audio	Native generation	The audio option can be switched on or off
Aspect ratio	adaptive and 5 fixed ratios	16:9, 4:3, 1:1, 3:4, 9:16
Inputs	Up to 10 images, 5 videos, 5 audio clips	Text mode accepts one document up to 100 MB and 50 pages. Video and audio references each have a 15-second total limit.

Text to video

The prompt describes the scene; optionally attach a document.

Open this mode

Start and end frames

A starting frame is required in I2V; an end frame is optional.

Open this mode

Multimodal references

Combine images, video clips and audio tracks in one request.

Open this mode

Standard and Prime

The speed choice selects a faster variant of the same model.

Open this mode

Parameter	Standard	Prime
T2V / I2V / R2V	All three mode groups	The same three mode groups
Speed	Base processing queue	Faster processing
Clipia price and status	Exact price unpublished; disabled	Exact price unpublished; disabled

Choose a mode

Text, a starting frame or a reference set.

Prepare the inputs

Upload frames or media; text mode can also use a document.

Set speed and length

Choose Standard or Prime, 2–30 seconds or Auto, resolution and sound.

Choose Standard or Prime with the speed selector in the editor.

Create with Wan 3.0

Open the mode and choose your settings to see the quote before generation.

Auto reserves the amount for up to 30 seconds. After successful generation, the unused portion is returned.

Write scene beats

Describe what happens at the start, middle and end of a longer clip.

Name your references

Use Image1, Video1 and Audio1 in the same order as the uploads.

Keep input modes separate

Start/end frames and universal references are different input modes.

Short advertisement

Up to 30 seconds lets a scene develop without an outside edit.

Storyboard transition

Start and end frames guide the arc of a clip.

Brief adaptation

A document, link and media can inform a future request.

Check the required mode in the catalog and request a quote before generation. Parameters vary by mode.

Clipia documentation

FAQ

Are Standard and Prime available in Clipia?

Yes. Use the generation links to open available modes. Each mode is enabled after verification; the editor shows the current selection.

Is Prime a separate model or mode?

It is the faster Wan 3.0 variant. Standard and Prime both support T2V, I2V and R2V; Prime adds no separate creative input.

How long can a video be?

Choose 2–30 seconds or Auto to let the model choose. Input video duration plus the new clip cannot exceed 30 seconds.

How many credits are Standard and Prime?

The exact credit cost is calculated for your selected settings and shown in the editor before generation.

Where are the real Wan 3.0 samples?

Yes. The demos show Standard and Prime from text and Standard from a source image. A multimodal reference demo has not been published yet.

Can I use Wan 3.0 through the Clipia API?

Yes, for modes marked active in the Clipia catalog. Check the parameters and quote before creating a task.

Create video

Create your scene with Wan 3.0

Open an available mode, describe your scene and choose settings. The quote appears before generation.

Create with Wan 3.0

Wan 3.0 longer scenes, more inputs

What is Wan 3.0 Video?

Two sides of Wan 3.0

An alpine train at sunrise

Glass and crimson silk

A basketball court comes alive

Wan 3.0 specifications

What can feed Wan 3.0?

Text to video

Start and end frames

Multimodal references

Standard and Prime

Standard or Prime

How to create with Wan 3.0

Choose a mode

Prepare the inputs

Set speed and length

Pricing in Clipia

How to prompt Wan 3.0

Write scene beats

Name your references

Keep input modes separate

When to choose Wan 3.0

Short advertisement

Storyboard transition

Brief adaptation

Integration through the Clipia API

Wan 3.0 questions

Create your scene with Wan 3.0

Wan 3.0 Video demo

Related Models

Wan 3.0 longer scenes, more inputs

What is Wan 3.0 Video?

Two sides of Wan 3.0

An alpine train at sunrise

Glass and crimson silk

A basketball court comes alive

Wan 3.0 specifications

What can feed Wan 3.0?

Text to video

Start and end frames

Multimodal references

Standard and Prime

Standard or Prime

How to create with Wan 3.0

Choose a mode

Prepare the inputs

Set speed and length

Pricing in Clipia

How to prompt Wan 3.0

Write scene beats

Name your references

Keep input modes separate

When to choose Wan 3.0

Short advertisement

Storyboard transition

Brief adaptation

Integration through the Clipia API

Wan 3.0 questions

Create your scene with Wan 3.0