# Omni-Avatar/OmniAvatar

Repository: https://github.com/Omni-Avatar/OmniAvatar
Canonical: https://ross.abutalabs.com/products/omniavatar
Homepage: https://omni-avatar.github.io/
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2025-08-06T15:17:03+00:00

## Health v2 (maintenance only)
Score: 34/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 35, release rhythm 35, longevity 31
- inputs: {"age_days": 442, "days_push": 392, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1859, forks 167 (observed 2026-08-28T04:05:45.227952+00:00)

## What it is
OmniAvatar is an audio-driven full-body avatar video generation model built on Wan2.1 text-to-video diffusion models with LoRA-based audio conditioning. It generates lifelike speaking avatar videos with accurate lip-sync, natural body animation, and prompt-controlled backgrounds and actions.

## Use cases
- generate talking avatar videos from audio and a prompt
- create lip-synced podcast or singing videos from speech audio
- animate a full-body digital human driven by voice
- control avatar background and movement via text prompts
- produce digital human videos for content creation

## When to choose
- you need audio-driven full-body avatar video generation with lip-sync
- you want prompt control over scene, background, and body motion
- you have GPU resources and want an open-source Wan2.1-based avatar model

## When to avoid
- you only need lightweight real-time face swap or talking-head on CPU
- you need a hosted SaaS avatar service without model setup
- you lack the GPU memory for 1.3B/14B diffusion inference

## Facets
- artifact type: library
- maturity: active
- function: video-processing, audio-processing, machine-learning, deep-learning, llm-inference
- domain: artificial-intelligence, computer-vision, deep-learning
- platform: python
- tags: audio-driven-avatar, talking-head, lip-sync, video-generation, diffusion-model, lora, wan2-1, wav2vec, digital-human, audio, video, linux, gpu

## Member repositories
- Omni-Avatar/OmniAvatar (main) score 34

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:45.227952+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:15:58.257471+00:00, confidence not recorded.
  - readme: https://github.com/Omni-Avatar/OmniAvatar (fetched 2026-08-28T04:05:45.227952+00:00, sha 570e388c0cf1)
  - homepage: https://omni-avatar.github.io/ (fetched 2026-08-29T10:55:06.316483+00:00, sha cec30fb6ec87)
- Data as of 2026-08-30T08:39:29.467469+00:00.