Creative Technology · Computer Vision

AI-Powered Image Classification

Pick a tested example or upload your own image. Then choose a pretrained classifier and let AI answer: what is this image mainly about?

Task Image classification Data ImageNet labels or custom candidates Models ResNet · ViT · CLIP

Choose an image

Start with a tested example, or try a photo of your own.

Start here · Example images

Four images are drawn at random from example images.

or try your own

Upload an image

PNG, JPEG, or WebP works best.

Choose classifier

Predictions to display 5

Top-k changes how many high-scoring labels are shown.

Choose an example or upload your own image.

AI prediction

What did the classifier predict?

Waiting

Choose an image first. It will appear here before classification.

No predictions yet.

Rank	Label	Score
Run the classifier to see details.

What you are doing

Use a learned AI capability instead of rebuilding the traditional task from scratch.

ResNet and ViT choose from 1,000 fixed ImageNet classes. CLIP compares the image with descriptions that you provide. Keep the image fixed, change one setting, and explain why the output changes.

Example or your image→ Selected pretrained classifier→ Labels + scores

Compare models: keep the image fixed, switch classifier, and observe how labels, scores, and speed change.

Comparison log

Keep one image fixed and compare model decisions.

Each successful run is added below. This makes the classroom comparison visible without reloading the page.

Run	Image	Model	Top prediction	Score	Time
Run two models on the same image to start a comparison.