AI Video Generator
Models
Sora Series

OpenAI's latest video generation model with enhanced quality

10 credits
10s/15s
Portrait/Landscape
Veo Series

Google's latest model with exceptional quality output

150 credits
Up to 8s
16:9/9:16
Seedance Series

30-second multimodal video generation with precise reference control and native audio

0 credits
Up to 30s
7 Aspect Ratios
10s
Public Visibility

When this option is enabled, the output video may be selected by AI Generate and published to the Explore.

Notification
This is a notification message
Sample Videos

Wan 3.0 Video · Lovart ME

Wan 3.0 Video AI Video Generator

2–30s · 480P / 720P / 1080P

Build a video with the standard Wan 3.0 endpoint. Start from text, first and last frames, or visual and audio references. Select 480P, 720P or 1080P and a fixed output duration between 2 and 30 seconds.

2–30s
Duration
480P / 720P / 1080P
10
Reference images
Use a clean source image and describe the protected details, requested changes and final composition.
480P / 720P / 1080P
Resolution
480P: 8/s · 720P: 16/s · 1080P: 32/s
3
Text and image inputs
Create in Lovart ME, then review the result in your history.

01 / MODEL

What you can make · Wan 3.0 Video

Create in Lovart ME, then review the result in your history.

A continuous shot from text

Describe a single scene or a small number of clearly ordered beats. Specify camera movement, subject actions, transitions and whether an audio track belongs in the result.

First and last frames

Use one image to anchor the opening, or a pair to set opening and ending compositions. This mode is separate from reference mode; it does not mix frame anchors with reference video or audio.

Multimodal reference direction

Reference mode accepts up to 10 images, 5 videos and 5 audio clips. Refer to them as Image1, Video1 and Audio1 in the prompt and explain which appearance, motion or sound they should guide.

A shared input and output time limit

Reference videos have a combined limit of 15 seconds. Input video duration plus requested output duration must stay within 30 seconds. Choose a fixed duration so the price is known before submission.

02 / INPUTS

Choose the input that carries useful direction

Build a video with the standard Wan 3.0 endpoint. Start from text, first and last frames, or visual and audio references. Select 480P, 720P or 1080P and a fixed output duration between 2 and 30 seconds.

Text and image inputs

Use text for a new scene. Upload references only when they provide useful visual direction.

Reference images

10 · Use a clean source image and describe the protected details, requested changes and final composition.

Prompt

State the action or edit, composition and lighting. Give each reference one role.

03 / OUTPUT

Set the output before generating

Choose a supported resolution, ratio and duration where available. Review the full cost before submitting.

Resolution

480P / 720P / 1080P

Credits

480P: 8/s · 720P: 16/s · 1080P: 32/s Credits

Aspect ratios

adaptive, 16:9, 4:3, 1:1, 3:4, 9:16

04 / PROMPTS

Wan 3.0 Video · Prompts for practical production tasks

Use a clean source image and describe the protected details, requested changes and final composition.

Narrative scene

Adapt the subject, setting and protected details to your own brief.

PromptCreate an eight-second 16:9 scene in a quiet bookshop at closing time. A shopkeeper stacks two books, turns off one lamp and walks toward the door. One slow camera pan, warm interior light, no captions.

Working note Use a clean source image and describe the protected details, requested changes and final composition.

Frame transition

Adapt the subject, setting and protected details to your own brief.

PromptMove from the supplied first frame to the last frame over six seconds. Keep the architecture and lighting consistent. A slow dolly forward links the two views without a cut.

Working note Use a clean source image and describe the protected details, requested changes and final composition.

Reference-directed motion

Adapt the subject, setting and protected details to your own brief.

PromptImage1 defines the subject and clothing. Video1 guides camera motion only. Create an eight-second continuous shot of the subject crossing a courtyard. Preserve the subject appearance and avoid extra people.

Working note Use a clean source image and describe the protected details, requested changes and final composition.

05 / WORKFLOW

How to use Wan 3.0 Video

Create in Lovart ME, then review the result in your history.

  1. 01

    Choose text, frames or references

    Use text for a new scene. Upload references only when they provide useful visual direction.

  2. 02

    Describe the subject and what must stay fixed

    State the action or edit, composition and lighting. Give each reference one role.

  3. 03

    Set output and review the displayed price

    Choose a supported resolution, ratio and duration where available. Review the full cost before submitting.

  4. 04

    Generate, inspect and revise

    Inspect details and continuity, then change one or two instructions per attempt. Your job remains available in history.

06 / FAQ

Wan 3.0 Video · Questions before you generate

Create in Lovart ME, then review the result in your history.

What can I create with Wan 3.0 Video?

Build a video with the standard Wan 3.0 endpoint. Start from text, first and last frames, or visual and audio references. Select 480P, 720P or 1080P and a fixed output duration between 2 and 30 seconds.

Which output settings are available?

Resolution: 480P / 720P / 1080P. Duration: 2–30s. Aspect ratios: adaptive, 16:9, 4:3, 1:1, 3:4, 9:16.

How is the price calculated?

Output-only rates: 8 / 16 / 32 credits/s at 480P / 720P / 1080P. First/last-frame and reference modes are separate. Each reference video is 1–15 seconds; total reference video duration is at most 15 seconds. The workbench supports text, frames and media references. File and webpage inputs and automatic duration are not offered here.

What should reference uploads contain?

First/last-frame and reference modes are separate. Each reference video is 1–15 seconds; total reference video duration is at most 15 seconds. The workbench supports text, frames and media references. File and webpage inputs and automatic duration are not offered here.

How long does generation take?

Generation has no fixed completion time. Queue load, output settings and upstream availability affect the wait.