Tencent-Hunyuan/HunyuanVideo-Avatar

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

2156 stars · 347 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

HunyuanVideo-Avatar is Tencent's open-source model and inference code for high-fidelity audio-driven human animation, generating talking avatar videos of one or multiple characters from an image and audio input. It includes pretrained checkpoints, multi-GPU and low-VRAM (10GB) single-GPU inference, and a Gradio demo server.

Use cases

• generate a talking avatar video from a photo and audio clip
• animate multiple characters lip-synced to dialogue audio
• create AI presenter videos from a single portrait image
• run audio-driven human animation on a single 10GB GPU
• build a demo web app for avatar video generation with Gradio

When to choose

• you need high-fidelity, multi-character audio-driven avatar video generation
• you have GPU hardware and want open-source weights with inference code
• you want low-VRAM inference options for talking-head video synthesis

When to avoid

• you need real-time streaming avatar generation
• you need a ComfyUI integration or polished end-user application
• you require a permissive license for commercial use without review

Facets

library · maturity active

video-processing audio-processing machine-learning deep-learning llm-inference artificial-intelligence deep-learning computer-vision python audio-driven-animation talking-head avatar-generation video-generation hunyuan diffusion-models gradio video audio linux gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="Tencent-Hunyuan/HunyuanVideo-Avatar")