antgroup/echomimic_v2
An audio-driven deep learning model that generates semi-body human animations and talking-head videos from audio input.
Not currently ranked — collecting fresh signals.
star history
EchoMimicV2 is a neural network model for generating animated human videos from audio. It uses audio input to drive facial expressions, head movements, and upper body gestures to produce realistic talking-head and body animation sequences. The model is designed to simplify previous approaches while maintaining quality for portrait and semi-body animation generation.
Frequently asked
- What is antgroup/echomimic_v2?
- An audio-driven deep learning model that generates semi-body human animations and talking-head videos from audio input.
- Is echomimic_v2 open source?
- Yes — antgroup/echomimic_v2 is open source, released under the Apache-2.0 license.
- What language is echomimic_v2 written in?
- antgroup/echomimic_v2 is primarily written in Python.
- How popular is echomimic_v2?
- antgroup/echomimic_v2 has 4.6k stars on GitHub.
- Where can I find echomimic_v2?
- antgroup/echomimic_v2 is on GitHub at https://github.com/antgroup/echomimic_v2.