NVIDIA LocateAnything-3B vision-language grounding model
@clawhub_openlark/locateanything
By openlark
About this Skill
NVIDIA LocateAnything-3B vision-language grounding model. Covers inference API (detect/ground/point/detect_text/ground_gui), data preparation (JSONL+Recipe 8...
代码生成脚本工具
Skill files and instructions
Read SKILL.md and the other instructions or configuration files published with this Skill.
Loading file list
Details
- Category
- Development
- Source
- clawhub
- Version
- 1.0.0
- Updated
- Sep 23, 2026