Open-Source Motion2MixamoRig Retargets Video Motion to Mixamo Rigs, Hits 1.1k Stars
CSProfKGD · x · 2026-10-15
Motion2MixamoRig is a new open-source project (1.1k GitHub stars) that transfers human motion from a video—or a pose from a single photo—onto an Adobe Mixamo-rigged 3D character, outputting a skinned .glb file ready for Blender or Unity.
Highlights:
- Accepts video or a single still photo as input
- Ships a Blender 4.2+ extension panel plus a command-line pipeline
- Runs locally on CPU, CUDA, or Apple Silicon
- Reuses one take on other characters in tens of seconds
- Apache-2.0 licensed
Aimed at game developers: feed it a single-person action clip and a Mixamo character, and it produces preview videos plus a ready-to-use animated asset. The project is experimental (v0.1.0).
Related event: Open-Source Motion2MixamoRig Transfers Video Motion to 3D Characters(2 posts)→
More from Multimodal
- Midjourney v8.2 style test: bold flat-ink illustration looks, sref code included — azed_ai · 2026-10-15
- Sarvam AI launches Bulbul V4 Flash, a faster compact TTS model for Indian languages — CurieuxExplorer · 2026-10-15
- Maya-2 debuts as open-weight Indic voice model, ranks #2 on Hindi TTS leaderboard — CurieuxExplorer · 2026-10-15
- PixText fixes text in generated images: 83% glyph pass rate vs 37% for baselines — ATH-MaaS · 2026-10-15
- TextVerifier catches flawed Chinese glyph rendering with F1 0.844, far above OCR and VLMs — ATH-MaaS · 2026-10-15
- AI Video Creators: 'Amazing Visuals Are Solved — Unique IP and Characters Are What's Left' — AIandDesign · 2026-10-15