🚀 VLM-FO1 Demo

📋 Instructions

Step 1: Prepare Your Image

Upload an image using the image editor below
Optional: Draw circular regions with the red brush to specify areas of interest
Alternative: If not drawing regions, the detection model will automatically identify regions

Step 2: Configure Your Task

Select a task template from the dropdown menu
Replace [WRITE YOUR INPUT HERE] with your target objects or query
Example: For detecting "person" and "dog", replace with: person, dog
Or: Write your own custom prompt

Step 3: Fine-tune Detection (Optional)

Adjust the detection threshold slider to control sensitivity

Step 4: Generate Results

Click the Submit button to process your request
View the detection results and model outputs below

Image Input

Prompt & Parameters

Prompt Templates

Select the prompt template for the task, or write your own prompt.

Task Prompt

Detection Model Threshold

0 1

Examples

Click on the examples below to quickly load images and corresponding prompts:

Click to load example

Image	Task Prompt	Prompt Templates

Detection Result

VLM-FO1 Result

VLM-FO1 Output

Extracted Detection Output