Open-source Duix-Avatar hits 15.8k GitHub stars for offline digital human video
sven_ai · x · 2026-10-10
Duix-Avatar, a truly open-source AI digital human toolkit, has reached 15.8k stars on GitHub. It runs offline — photos and voice stay on your machine — and users report natural lip sync and convincing voice cloning for use cases like course narration, product intros, and short-video batches. Commenters note it could crush the once tens-of-thousands-yuan pricing for digital human production, though creators warn against impersonation and unauthorized source material.
More from Multimodal
- MiniMax-H3 hailed as favorite open release of the year, runs fully local — AdinaYakup · 2026-10-23
- Michal Malewicz experiments with depth maps in his creative workflow — michalmalewicz · 2026-10-23
- One-Shot Tunable Style Transfer on Flux3 Via Reference Latent + Node — Winter_unmuted · 2026-10-23
- PhysVidBench accepted at EMNLP 2026: do video gen models grasp physical commonsense? — aykuterdemml · 2026-10-23
- EMNLP 2026 paper teaches multimodal LLMs to get cartoons via incongruity-resolution supervision — aykuterdemml · 2026-10-23
- A gorgeous Midjourney style: sref code 820221253 for dreamy lavender watercolor looks — umesh_ai · 2026-10-23