v.2.0.0

daijro/camoufoxv.2.0.0Feb 13, 2025by yadong-lu

AI Summary

This major version update focuses on performance improvements, including a 60% reduction in latency and increased accuracy (39.6%). It introduces OmniTool, a unified agent controller supporting OpenAI, DeepSeek, Qwen, and Anthropic models.

Key Highlights

  • 60% improvement in latency compared to V1
  • 39.6% average accuracy on ScreenSpot Pro
  • Introduction of OmniTool agent
  • Support for OpenAI, DeepSeek, Qwen, and Anthropic models
  • Larger and cleaner icon grounding dataset

New Features

  • Larger icon grounding dataset
  • 60% latency reduction
  • 39.6% accuracy improvement
  • OmniTool support
  • Multi-model support (OpenAI, DeepSeek, Qwen, Anthropic)

Full Release Notes

# What's new in V2.0.0?
- Larger and cleaner set of icon caption + grounding dataset
- 60% improvement in latency compared to V1 [model checkpoints](https://huggingface.co/microsoft/OmniParser-v2.0)
- Strong performance: 39.6 average accuracy on [ScreenSpot Pro](https://github.com/likaixin2000/ScreenSpot-Pro-GUI-Grounding)
- Your agent only need one tool: OmniTool. Control a Windows 11 VM with OmniParser + your vision model of choice. OmniTool supports out of the box the following large language models - OpenAI (4o/o1/o3-mini), DeepSeek (R1), Qwen (2.5VL) or Anthropic Computer Use.