Skip to content
Work data is processed in your browser, not stored on our servers.
tools
AI Image Classifier and Automatic Tagger

AI Image Classifier and Automatic Tagger

Classify an image with a ViT model and inspect the five most likely English ImageNet labels with their scores.

Focus mode
Image
Use AI to classify what an image contains. Processing stays in your browser.
Classification results
Top five likely matches (ImageNet, English labels).
Upload an image and select “Analyze image.”

Key features

  • Classifies an uploaded image against ImageNet categories
  • Shows the five highest-scoring English labels as percentages
  • Supports replacing the image or cancelling an analysis
  • Caches the downloaded model in browser storage

How to use

  1. Choose or paste the image you want to classify.
  2. Run the analysis and review the top labels and scores.

Examples

  • Identify a photo's broad category

    Inspect the closest English ImageNet labels and their relative scores.

  • Compare classification candidates

    Review the top five labels to understand how the model interpreted an image.

Privacy

The image is processed inside your browser for model inference. After you consent on first use, ViT model files may be downloaded from Hugging Face and cached in browser storage.

Requirements

The first analysis requires consent to download about 88 MB of model files and a modern browser capable of running the model. Results vary with the image and the model's ImageNet categories.

Common questions

What language and label set does it use?
It shows the five highest-scoring English labels from the ViT model's ImageNet categories. It does not create free-form tags or locate every object in an image.
Does every analysis download the model again?
After first-use consent, model files may be cached in browser storage and reused while that cache remains. Clearing the cache requires another download.

Related tools