- Home
- AI Video Lip Sync Tools
- EchoMimic
On the recordRead 4 Oct 202620 facts
EchoMimic
On the record
- Audio input
- The project page shows audio-driven demos for English, Chinese, and singing.github.com · read 4 Oct 2026
- Deployment
- The repository provides Python inference scripts and instructions for running a Gradio UI.github.com · read 4 Oct 2026
- Hosted demos
- The repository links EchoMimic demos on Hugging Face and ModelScope.github.com · read 4 Oct 2026
- Installation requirements
- The README lists tested CentOS 7.2 or Ubuntu 22.04 environments, CUDA 11.7 or later, Python 3.8, 3.10, or 3.11, and A100, RTX4090D, or V100 GPUs.github.com · read 4 Oct 2026
- Integrations
- The repository links a ComfyUI implementation contributed by a community member.github.com · read 4 Oct 2026
- Intended use
- The project states that it is intended for academic research and says users are solely liable for their generated content and actions.github.com · read 4 Oct 2026
- Interfaces
- The project provides a Gradio UI and links to demos on Hugging Face and ModelScope.github.com · read 4 Oct 2026
- Landmark conditioning
- The project says it was trained with both audio and facial landmarks to support those different driving modes.antgroup.github.io · read 4 Oct 2026
- Landmark control
- EchoMimic supports landmark-driven animation and audio combined with selected landmarks.github.com · read 4 Oct 2026
- License
- The repository's LICENSE file contains the Apache License, Version 2.0.github.com · read 4 Oct 2026
- Maker
- The project page attributes the work to the Terminal Technology Department, Alipay, Ant Group.antgroup.github.io · read 4 Oct 2026
- Motion alignment
- The repository includes a demo for aligning motion between a reference image and a driven video.github.com · read 4 Oct 2026
- Pose control
- The repository includes inference instructions for audio-and-pose-driven and pose-driven animation.github.com · read 4 Oct 2026
- Publication
- The repository says the EchoMimic paper was accepted by AAAI 2025.github.com · read 4 Oct 2026
- Purpose
- EchoMimic generates portrait videos from audio, facial landmarks, or a combination of audio and selected facial landmarks.antgroup.github.io · read 4 Oct 2026
- Requirements
- The repository lists tested environments as CentOS 7.2 or Ubuntu 22.04 with CUDA 11.7 or later, Python 3.8, 3.10, or 3.11, and tested GPUs A100 80G, RTX4090D 24G, or V100 16G.github.com · read 4 Oct 2026
- Research results
- The project page says EchoMimic was compared with alternative algorithms on public and collected datasets and showed superior quantitative and qualitative performance.antgroup.github.io · read 4 Oct 2026
- Support
- The repository provides GitHub Issues as its visible issue-reporting channel.github.com · read 4 Oct 2026
