Lobe Vidol

Experience the magic of virtual idol creation with Lobe Vidol. Enjoy our exquisite UI design, support for MMD dance content, and seamless conversations with characters—all integrated into one cohesive platform.

^{Anyone can create a virtual idol}

English · 简体中文 · 日本語 · Docs · Changelog · Report Bug · Request Feature

Lobe Vidol is actively under development. If you have any requests or questions, feel free to submit [issues][issues-link].

	No installation or registration required! Visit our website for a quick experience.
	Join our Discord community! This is where you can interact with developers and other enthusiastic LobeHub users.

Star History

Streamed responses provide a smooth conversational experience. You can set the dialogue context by placing character actions and expressions in parentheses () and the ongoing events or scenes in square brackets [] to create an immersive experience.

You can enhance the dialogue by setting a background image that fits the context:

With a built-in library of Mixamo character actions and poses, you can have characters strike the desired poses or perform actions during conversations:

The meticulously designed interface features an elegant appearance and smooth interaction effects, supporting both light and dark themes, and is optimized for mobile devices. It also supports PWA, providing an experience closer to that of a native application.

Using the character editor, you can create your own virtual idol, set touch responses, upload VRM models to the site, and interact with them.

With the support of mmd-parser, you can dance with your favorite idols using vmd files; Just Dance!

We have added a stage loading feature with a rich selection of stages, allowing characters to dance with different stage styles:

By clicking on different body parts of the character, they will respond differently. You can also edit the character's touch responses to create unique interactive effects:

The LobeVidol character marketplace gathers a variety of meticulously designed characters, allowing you to experience different contexts and interactions, providing a unique companionship experience. Our marketplace is not just a display platform but a collaborative space where everyone can contribute their imagination and share their personally designed characters.

The LobeVidol dance marketplace features a rich collection of MMD dance resources, creating a wealth of visual experiences. You can combine different characters, stages, music, and dances to create a unique viewing experience.

LobeVidol supports Text-to-Speech (TTS) and Speech-to-Text (STT) technologies, enabling our application to convert text information into clear voice output. Users can interact with our conversational assistant as if they were talking to a real person. Users can choose from a variety of voices to match their assistant with the appropriate sound source. Additionally, for those who prefer auditory learning or want to obtain information while busy, TTS provides an excellent solution.

In LobeVidol, we have carefully selected a range of high-quality voice options (OpenAI Audio, Microsoft Edge Speech) to meet the needs of users from different regions and cultural backgrounds. Users can select suitable voices based on personal preferences or specific scenarios to achieve a personalized communication experience.

NPM	Repository	Description	Version
@lobehub/ui	lobehub/lobe-ui	An open-source UI component library designed for building AIGC web applications
@lobehub/icons	lobehub/lobe-icons	A collection of SVG logos and icons for mainstream AI / LLM models and companies
@lobehub/tts	lobehub/lobe-tts	A React Hooks library for AI TTS / STT voice synthesis / recognition
@lobehub/lint	lobehub/lobe-lint	LobeHub code style guidelines for ESlint, Stylelint, Commitlint, Prettier, Remark, and Semantic Release

• Vidol market - This is the Market Index of Vidol Chat. Vidol accesses index.json from this repo to show users the list of available agents and dances.
• Vidol agent sample - Vidol character data template
• Vidol dance sample - Vidol dance data template

You can use GitHub Codespaces for online development:

Or use the following commands for local development:

$ git clone https://github.com/lobehub/lobe-vidol.git
$ cd lobe-vidol
$ bun install
$ bun dev

We warmly welcome contributions in various forms. If you're interested in contributing code, please check out our GitHub Issues and [Projects][github-project-link] to showcase your creativity and skills.

Every bit of support is incredibly valuable, coming together to form the brilliant galaxy we support! You are like a shooting star that lights up our path forward in an instant. Thank you for your trust — your support acts like a guiding star, repeatedly illuminating the way for the project.

• 🤖 Lobe Chat : An open-source, extensible (Function Calling) plugin system, modern design ChatGPT/LLMs chat application and development framework. Supports one-click free deployment of your private ChatGPT/LLMs application.
• 🅰️ Lobe SD Theme: A modern theme for Stable Diffusion WebUI, featuring exquisite interface design, highly customizable UI, and efficiency-enhancing features.
• ⛵️ Lobe Midjourney WebUI: Midjourney WebUI, capable of quickly generating a rich variety of images based on text prompts, inspiring creativity and enhancing dialogue.
• 🌏 Lobe i18n: Lobe i18n is an automation tool for the i18n (internationalization) translation process powered by ChatGPT. It supports automatic splitting of large files, incremental updates, and customizable options for OpenAI models, API proxies, and temperature.

• mmd-parser - https://github.com/takahirox/mmd-parser
• three-vrm - https://github.com/pixiv/three-vrm
• tts-vue - https://github.com/LokerL/tts-vue

Copyright © 2024 lobehub.
This project is Apache 2.0 licensed.