nysa-liu/Digital-Life-DL-B

本次开源为DL-B,是一个基于ChatGLM、Wav2Lip、So-VITS组建的数字形象方案。可以在此基础之上增加其他组件达到数字生命的效果。This open source is DL-B, which is a digital image scheme based on ChatGLM, Wav2Lip and So-VITS. On this basis, other components can be added to achieve the effect of digital life.

41
/ 100
Emerging

This project helps create a talking digital avatar from scratch. You provide text for the avatar to speak, an audio input (likely your voice), and a video of a person's face. The system then generates a video of the digital avatar speaking your text with synchronized lip movements and a voice that matches the provided audio. This is ideal for content creators, educators, or anyone looking to produce personalized digital presenters without complex animation.

105 stars. No commits in the last 6 months.

Use this if you need to quickly generate a video of a digital character speaking custom text with a specific voice and synchronized lip movements.

Not ideal if you're looking for a user-friendly, plug-and-play solution that doesn't require manual model training and setup, as this project demands significant technical effort.

digital-avatar-creation virtual-presenter synthetic-media content-production AI-video-generation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 16 / 25

How are scores calculated?

Stars

105

Forks

16

Language

Python

License

GPL-3.0

Last pushed

May 24, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/nysa-liu/Digital-Life-DL-B"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.