hjLabs AI Playground
Starting the on-device runtime…
ViT-base, ResNet-50 and MobileViT-small are the standard ImageNet-1k classifiers, and all three run here on your GPU. Drop in a photo and get the top-k labels with probabilities — a good reference point when you are comparing architectures, checking how a model behaves on your own data, or teaching what a convolutional network and a vision transformer each get wrong. MobileViT is the one to pick on a phone or an integrated GPU.
image classification onlinevit demoresnet-50 browserimagenet classifier freeidentify object in photo aimobilevit demophoto recognition tool
The 1,000 ImageNet-1k classes. That covers a lot of animals, objects and food, and almost no brand names, people or abstract concepts. For arbitrary labels, use zero-shot image classification with CLIP.
It is free and there is no per-request limit, because we are not paying for the compute — your own GPU is. The only cost is the one-time model download, which your browser caches.
No. The model weights are downloaded from Hugging Face to your browser once, and every inference after that runs on your own GPU through WebGPU. Your text, images and audio are never sent anywhere — hjLabs.in has no inference server and no way to see your input.
Small models do. Recent mobile Chrome and Safari expose WebGPU, but memory is the binding limit — stay under roughly 200 MB of weights on Android, and expect iOS to reclaim the tab sooner. The catalog shows every download size up front so you can pick something that fits.
That depends on the individual model, not on this site. Each model page links to its Hugging Face repository, where the licence is stated — most of the catalog is Apache-2.0 or MIT, a few are research-only. We add nothing on top: hjLabs.in claims no rights over anything you produce here.