vista-gui-grounding / README.md
multimodalart's picture
multimodalart HF Staff
Upload folder using huggingface_hub
bee93a7 verified
|
Raw
History Blame Contribute Delete
523 Bytes
---
title: VISTA GUI Grounding
emoji: 🎯
colorFrom: blue
colorTo: pink
sdk: gradio
sdk_version: 6.19.0
app_file: app.py
short_description: GUI grounding with VISTA-9B predict click coordinates
python_version: "3.12"
startup_duration_timeout: 30m
---
VISTA-9B GUI grounding demo. Upload a GUI screenshot and a natural-language instruction; the model predicts the click coordinate and marks it on the image.
Based on [VISTA: View-Consistent Self-Verified Training for GUI Grounding](https://arxiv.org/abs/2606.14579).