Information
Vision Agent Tools Vision Agent Tools Documentation Vision Agent Tools Documentation CLIPMediaSim Controlnet-Aux Depth-Anything-V2 FlorenceQA Florence2Sam2 Florence-2 Flux1 InternLM-XComposer-2.5 NSFW (Not Safe for Work) classification LOCA (Low-shot Object Counting network with iterative prototype Adaptation). OWLv2 Open-World Localization QR Reader Qwen2-VL Shared Model Manager SigLIP This repository contains tools that solve vision problems. This tools can be used in conjunction with the vision-agent.