DataLearner logo
VI

VideoBooth

Vision model

VideoBooth

Release date: 2023-12-01Updated: 2023-12-05Views: 571
Live demoGitHubHugging FaceCompare
Parameters
3B
Context length
2K
Multilingual
No data
Reasoning ability
No data

VideoBooth is an AI model published by Shanghai Artificial Intelligence Laboratory, released on 2023-12-01, for Vision model, with 3B parameters, and 2K context length, requiring about 10.04GB storage.

Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology

VideoBooth

Model basics

Reasoning traces
No data
Thinking modes
Thinking modes not supported
Context length
2K tokens
Max output length
No data
Model type
Vision model
Modality (in / out)
No data
Release date
2023-12-01
Model file size
10.04GB
MoE architecture
No
Total params / Active params
3B / Not applicable
Knowledge cutoff
No data
VideoBooth

Open source & experience

Code license
Weights license
Apache 2.0- Commercial use permitted
Hugging Face
N/A
Live demo
N/A
VideoBooth

Official resources

Paper
DataLearnerAI blog
N/A
VideoBooth

API details

API speed
No data
No public API pricing yet.
VideoBooth

Publisher

Shanghai Artificial Intelligence Laboratory
Shanghai Artificial Intelligence Laboratory
View publisher details
VideoBooth

Model Overview

VideoBooth is an AI model published by Shanghai Artificial Intelligence Laboratory, released on 2023-12-01, for Vision model, with 3B parameters, and 2K context length, requiring about 10.04GB storage.

DataLearner on WeChat

Follow DataLearner on WeChat for AI model updates and research notes.

DataLearner WeChat QR code