Zejun-Yang/AniPortrait

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

5021 stars · 612 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

AniPortrait is a Python framework from Tencent that generates photorealistic portrait animations from an audio clip and a reference image, and also supports face reenactment from a driving video. It ships with pretrained weights, a Gradio demo, and inference scripts for audio-to-video and video-to-video generation.

Use cases

• animate a portrait photo to speak with a given audio track
• create talking head videos from audio
• reenact a face using a source driving video
• generate lip-synced avatar videos for content creation
• control head pose in generated portrait animations

When to choose

• you need audio-driven talking portrait generation with pretrained models
• you want face reenactment driven by a reference video
• you want a research-grade photorealistic animation pipeline you can self-host

When to avoid

• you need real-time animation on consumer hardware without a GPU
• you want a production-ready commercial avatar service with support
• you need lightweight lip-sync only without diffusion-based generation

Facets

application · maturity maintenance

video-processing machine-learning deep-learning image-processing speech-recognition artificial-intelligence computer-vision deep-learning image-processing python self-hosted talking-head face-reenactment audio-driven-animation diffusion gradio photorealistic-portrait video linux gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="Zejun-Yang/AniPortrait")