GETTING STARTED
Vidu currently provides multiple models including: ViduQ2, ViduQ1, Vidu2.0 — covering video generation, audio generation, and audio-video direct output. Their parameters and capabilities are listed below:
Model | viduq3-pro | viduq3-turbo |
|---|---|---|
Overview | Supports simultaneous audio and visual output, and supports intelligent mirror cutting | Supports simultaneous audio and visual output, and supports intelligent mirror cutting |
Resolution | 540p, 720p, 1080p | 540p, 720p, 1080p |
Frame Rate | 24fps | 24fps |
Duration | 1-16S | 1-16S |
Image to Video | ✔️ | ✔️ |
Reference to Video | - | - |
Start End to Video | ✔️ | ✔️ |
Text to Video | ✔️ | ✔️ |
Templates | - | - |
Model | viduq2-pro-fast | viduq2-turbo | viduq2-pro | viduq2 | viduq1 | viduq1-classic |
|---|---|---|---|---|---|---|
Overview | Fast speed, low price, stable effect | New model, fast speed | New model, rich details | New model, rich details | Clear visuals | Stable, cinematic camera motion |
Resolution | 720p, 1080p | 540p, 720p, 1080p | 540p, 720p, 1080p | 540p, 720p, 1080p | 1080p | 1080p |
Frame Rate | 24fps | 24fps | 24fps | 24fps | 24fps | 24fps |
Duration | 1–10S | 1–10S | 1–10S | 1–10S | 5S | 5S |
Image to Video | ✔️ | ✔️ | ✔️ | ✔️ | ✔️ | ✔️ |
Reference to Video | - | - | ✔️ support reference videos | ✔️ | ✔️ | - |
Start End to Video | ✔️ | ✔️ | ✔️ | - | ✔️ | ✔️ |
Text to Video | - | - | - | ✔️ | ✔️ | - |
Templates | - | - | - | - | ✔️ | - |
Model | vidu2.0 |
|---|---|
Overview | Fast generation speed |
Resolution | 360p, 720p, 1080p |
Frame Rate | 32fps |
Duration | 4S, 8S |
Image to Video | ✔️ |
Reference to Video | ✔️ |
Start End to Video | ✔️ |
Text to Video | - |
Templates | ✔️ |
Capability/Model | viduq1 | viduq2 |
|---|---|---|
Text to Image | - | ✔️ |
Image Edit | - | ✔️ |
Reference to Image | ✔️ | ✔️ |
Templates | ✔️ | ✔️ |
Resolution | 1080p | 1080p,2K,4K |
Supported Image Count | 1-7 images | 0-7 images |
Aspect Ratio | 16:9, 9:16, 1:1 | 16:9,9:16,1:1, 3:4,4:3,21:9,2:3,3:2,auto |
Capability | Supported |
|---|---|
Text to Audio | ✔️ |
Timing to Audio | ✔️ |
Text to Speech | ✔️ |
Voice Clone | ✔️ |
Duration | 2-10S |
Capability | Supported | Description |
|---|---|---|
Lip Sync | ✔️ | Generate lip-sync videos driven by text or audio |
Digital Human | ✔️ | Generate digital-human speech or broadcast videos from an image |
Video Extension | ✔️ | Extend video duration from 1～7s |
Multi-Frame | ✔️ | Generate long, high-quality videos using multiple keyframes |
Audio-Video Direct Output | ✔️ | Directly generate synchronized audio–video output |
Smart Super-Resolution - Premium | ✔️ | Enhance video resolution, supports 1080p, 2K, 4K |
Templates | ✔️ | Stitch multiple effects into a standard video template |
Recommended Prompts | ✔️ | Based on 1–7 input images, recommend suitable prompts |