Descript
Descript
9
Edit video by editing text
- Version
- Underlord
- Cost
- Free tier · from $16/mo
- Model
- ChatGPT
Vidu
Shengshu AI · #2 most active of 17 in Video
Vidu's reference-to-video mode conditions on several images at once for consistent characters and props.
100
Trust score · Verified
2 data points checked · 2026-09-13
Current version
Vidu Q3
Entry cost
Free tier with credits. Paid plans are available but pricing is not disclosed in the text.
Changes / 30d
9
The short answers · verified September 16, 2026
- What is the latest version of Vidu?
- The current shipped version of Vidu is Vidu Q3, as of September 16, 2026.
- How much does Vidu cost?
- Vidu has no published flat entry price. Free tier with credits. Paid plans are available but pricing is not disclosed in the text.
- What AI model does Vidu use?
- Vidu runs primarily on GPT2.
Source: Shengshu AI — www.vidu.com · Reusable under CC BY 4.0 — cite Tomorrow
Capabilities
- Multi-image reference
- Anime styles
- Start and end frames
- Audio generation
- Text to Video
- Image to Video
- Reference to Video
- AI Sound Effect Generator
- AI Image Generator
- Start-End2Video
- Video Upscaling
- Multi-Reference Consistency
- Upscale
- First & Last Frames Control
- Voice clone
- Text-to-speech
- Lip sync
- Digital human
- AI Video Generator
- Vidu Claw
- Vidu S1 Stream Model
- Start-End to Video
- Voice Clone
- Lip Sync
- Digital Human
- Video Extension
- Smart upscale
- Anime Art to Video
- Templates
- API Platform
- Upscaling
- Start-End To Video
- Start-End-to-Video
- Video Upscale
- Text to speech
- Text to Speech
- Text to Audio
- Text-to-Speech
- Reference to Image
- Text to Image
- AI Templates
- Audio Generator
- AI Hug Generator
- AI Kissing Generator
Pricing
Free Tier
Free credits provided to users
Free
Entry price over time
1 of 39 points reconstructed from Internet Archive captures (hollow dots) — dated by capture, not by when we first saw the page. View a capture
Geek mode
Models under the hood
- disclosed
GPT2
OpenAI
- disclosed
Vidu Q1
Shengshu AI
- disclosed
Vidu Q1 Image
Shengshu AI
- disclosed
Vidu Q2
Shengshu AI
- disclosed
Vidu Q2 Image
Shengshu AI
- disclosed
Vidu Q3
Shengshu AI
- disclosed
Vidu S1
Shengshu AI
- disclosed
Vidu S2
Shengshu AI
Context window
n/a
Public API
yes
Multi-model routing
yes
Stack signals
- U-ViT architecture
- Public API
Shared model stack
Other tracked products running on the same foundation models — a quick read on how much of the catalog moves when one of these models changes.
- GPT2OpenAI · 1 product
- Vidu Q1Shengshu AI · 1 product
- Vidu Q1 ImageShengshu AI · 1 product
- Vidu Q2Shengshu AI · 1 product
- Vidu Q2 ImageShengshu AI · 1 product
- Vidu Q3Shengshu AI · 1 product
- Vidu S1Shengshu AI · 1 product
- Vidu S2Shengshu AI · 1 product
green disclosed · amber inferred · grey unattributed. Aliases are folded into one model; provider concentration counts only models with an established vendor.
Reported scale
Reference data. Each figure is whatever the source actually said — weekly users, downloads, revenue run-rate — with its own definition and date. These are not comparable between tools and are never used to rank anything.
No public usage figure on record for this product.
Also in Video
All VideoRunway
Runway
8
Creative suite for generated video
- Version
- Gen-4.5
- Cost
- Free tier · from $15 one-time
- Model
- Aleph
Pika
Pika Labs
6
Playful short-form video generation
- Version
- 2.5
- Cost
- Free tier · from $10/mo
- Model
- Pika 2.5
Sora
OpenAI
5
Text-to-video with a social feed
- Version
- Sora 2
- Cost
- from $20/mo
- Model
- Sora 2
Seedance
ByteDanceChina
3
ByteDance's video model behind Jimeng.
- Version
- Doubao Seedance 2.5
- Cost
- from $0.15/mo
- Model
- Doubao Seedance 2.0
Hailuo
MiniMaxChina
2
Fast, cheap video generation with strong character consistency.
- Version
- H3
- Cost
- from $4.99/mo
- Model
- H3
Change history
- capability
New capabilities: AI Hug Generator, AI Kissing Generator
42 tracked44 tracked · +AI Hug Generator, AI Kissing Generator
source - version
- model
Vidu added Vidu S2 to its model stack
GPT2, Vidu Q1, Vidu Q1 Image, Vidu Q2, Vidu Q2 Image, Vidu Q3, Vidu S1GPT2, Vidu Q1, Vidu Q1 Image, Vidu Q2, Vidu Q2 Image, Vidu Q3, Vidu S1, Vidu S2
source - version
- version
- capability
- version
- version
- version
- version
- version
- version
- version
- capability
- version
- version
- version
- version
- capability
New capabilities: Reference to Image, Text to Image
38 tracked40 tracked · +Reference to Image, Text to Image
source - version
- capability
- version
- capability
- version
- capability
- capability
- version
- version
- capability
New capabilities: Start-End-to-Video, Video Upscale
32 tracked34 tracked · +Start-End-to-Video, Video Upscale
source - capability
- version
- capability
- capability
- capability
- version
- capability
New capabilities: Video Extension, Smart upscale
25 tracked27 tracked · +Video Extension, Smart upscale
source - version
- model
Vidu added GPT2 to its model stack
Vidu Q1, Vidu Q1 Image, Vidu Q2, Vidu Q2 Image, Vidu Q3, Vidu S1GPT2, Vidu Q1, Vidu Q1 Image, Vidu Q2, Vidu Q2 Image, Vidu Q3, Vidu S1
source - capability
New capabilities: Start-End to Video, Voice Clone, Lip Sync
21 tracked25 tracked · +Start-End to Video, Voice Clone, Lip Sync, Digital Human
source - model
Vidu added Vidu Q1 Image, Vidu Q2 Image to its model stack
Vidu Q1, Vidu Q2, Vidu Q3, Vidu S1Vidu Q1, Vidu Q1 Image, Vidu Q2, Vidu Q2 Image, Vidu Q3, Vidu S1
source
Vidu compared
Straight head-to-head pages against the busiest products in Video.
How to cite this page
Free to cite and reuse under CC BY 4.0. Permalink: https://tomorrow.aliensquad.ai/tools/vidu
APA
Tomorrow. (2026). Vidu — version, pricing and model stack [Data set entry]. AlienSquad. Retrieved 2026-09-17, from https://tomorrow.aliensquad.ai/tools/vidu
BibTeX
@misc{tomorrow-tools-vidu,
author = {{Tomorrow}},
title = {Vidu — version, pricing and model stack},
year = {2026},
publisher = {AlienSquad},
howpublished = {\url{https://tomorrow.aliensquad.ai/tools/vidu}},
note = {Accessed: 2026-09-17}
}