DEDUPED Hot AI repos. Real use cases. What people build. Get the Monday 5

How to detect objects in an image with one command with Ultralytics

Run a pretrained YOLO26n model on any image from the terminal.

Short answer: Install with pip install ultralytics; then run yolo predict model=yolo26n.pt source='https://ultralytics.com/images/bus.jpg'; Replace the source with your own image path or URL. All steps.

  • Top pick
  • Data and analytics
  • Beginner
  • 10 minutes
  • From the README
  • Claude Code
  • Codex
  • Cursor
  • Gemini CLI

Who it is forA developer who wants to see what a detector finds before writing code.

The problemSetting up a vision model usually takes an afternoon.

The outcomeAn annotated prediction for the image, with boxes and class labels.

What you need first

  • Python 3.8 or newer with pip (PyTorch is installed with the package requirements)
  • A GPU is optional for prediction and recommended for training
  • Images or video to run on, or a dataset config for training

Steps

  1. Install with pip install ultralytics
  2. Run yolo predict model=yolo26n.pt source='https://ultralytics.com/images/bus.jpg'
  3. Replace the source with your own image path or URL
  4. Add arguments like imgsz=640 to tune the run

Prompt for your agent

Using ultralytics/ultralytics, install `pip install ultralytics`, run `yolo predict model=yolo26n.pt source='https://ultralytics.com/images/bus.jpg'` and then on <my image folder>, and summarise which objects were found in each image.

Caveat. The model weights download on first use.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for ultralytics/ultralytics and "Detect objects in an image with one command"

Add Deduped to Claude Code once

claude mcp add --transport http deduped https://dedupedai.com/mcp

Cursor, ChatGPT, others

Share: X LinkedIn Hacker News Email Copy link

Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer