EchoMimicV2 utilizes a reference image, an audio clip, and a sequence of hand pose to generate a high-quality animation video, ensuring coherence between audio content and half-body movements. Project Page: https://antgroup.github.io/ai/echomimic_v2/ GitHub Page: https://github.com/antgroup/echomimic_v2 https://github.com/user-attachments/assets/677dcbeb-8943-43d0-8f9a-cec978e81209 https://github.com/user-attachments/assets/858cea2a-50e1-4151-b6ae-64f617a63937