TinyClick GUI Automation

Discover TinyClick GUI Automation, a compact vision-language model for effortless interaction. Discover how this AI model can transform your workflow!

Platform: Replicate

GUI AutomationVision-Language ModelClick Agent

28 runs

L40S

Commercial

🚀Function Overview

A compact vision-language model for GUI automation that identifies and clicks on specified UI elements based on screenshot images and text commands.

Key Features

Executes GUI actions with low latency (0.27B parameters)
Processes both visual (screenshot) and textual (command) inputs
Returns precise screen coordinates for interaction
Optimized for single-turn GUI operations

Use Cases

•Automating software testing workflows
•Creating accessibility tools for UI navigation
•Developing bot assistants for app interactions

⚙️Input Parameters

image

string

GUI screenshot image

text

string

Command to perform on the GUI screenshot

💡Usage Examples

Example 1

Input Parameters

{
  "text": "click on accept and continue button",
  "image": "https://huggingface.co/Samsung/TinyClick/resolve/main/sample.png"
}

Output Results

{ "action": "click", "click_point": [ 133, 538 ], "execution_time_seconds": 0.72 }

Quick Actions

Use NowView Documentation

Technical Specifications

Hardware Type: L40S
Run Count: 28
Commercial Use: Supported
Platform: Replicate