EchoMimicV3 is a unified multi-modal and multi-task human animation model that generates realistic human videos from audio and/or text prompts. Built upon the Wan2.1-Fun-V1.1-1.3B-InP base model, it supports both talking-head and full-body animation with two versions: preview (standard quality) and flash (optimized for speed and lower VRAM). The system provides Gradio-based interactive demos (app.py, app_mm.py) for real-time video generation from user-uploaded media, command-line inference scripts (infer_flash.py, infer_preview.py, run_flash.sh) for batch processing, and deployment options for ComfyUI, ModelScope, and HuggingFace. Core functionality centers on audio-driven lip-sync and facial animation, with optional text guidance for pose/scene control, leveraging diffusion models, transformer architectures, and multimodal encoders (CLIP for images, T5 for text, Wav2Vec2 for audio).
This repository is a curated 'awesome list' of papers, datasets, and resources for talking head generation, covering image-driven, audio-driven, and NeRF/3D-based approaches. It contains no executable code, data pipelines, or models—only a single README.md with organized tables of references. The repo serves as a research bibliography, not a software project. There are no assets to reproduce or reuse programmatically.