V

VOXO

Developed by junjuice0
VOXO is a text-to-image diffusion model initially created for personal use, capable of generating virtual YouTuber images.
Downloads 115
Release Time : 2/3/2023

Model Overview

VOXO is a diffusion model focused on generating images of virtual YouTubers (such as Hololive and Nijisanji). The model quality may be limited, but fine-tuned versions may be released in the future.

Model Features

Virtual YouTuber Generation
Capable of generating images of virtual YouTubers such as Hololive and Nijisanji.
Weight Adjustment
It is recommended to assign a weight of approximately 1.2 to names to improve generation results.
Negative Prompt Support
Supports the use of negative prompts (e.g., bad-images or bad-prompt) to optimize generation results.

Model Capabilities

Text-to-Image Generation
Virtual YouTuber Image Generation

Use Cases

Virtual YouTuber Creation
Generate Hololive Virtual YouTuber
Use the model to generate Hololive-style virtual YouTuber images.
Generation results vary by character, with some virtual YouTubers generating better results.
Generate Nijisanji Virtual YouTuber
Use the model to generate Nijisanji-style virtual YouTuber images.
Generation results vary by character, with some virtual YouTubers generating better results.
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
© 2025AIbase