hjLabs AI Playground
Starting the on-device runtime…
RMBG-1.4 and MODNet produce a clean alpha matte around a subject — hair, fur and semi-transparent edges included — and both run on your GPU here. The practical difference from the popular online tools is that there is no credit system, no watermark, no resolution downgrade on the free tier, and the photo is never transmitted anywhere. Export a transparent PNG, or composite onto a solid colour in one click. BiRefNet is available when you want the highest-quality matte and can wait a little longer.
remove background freebackground remover no watermarkrmbg-1.4 onlinetransparent png makerai background eraserremove.bg alternative freeoffline background removalunlimited background remover
No. There is no credit balance because there is no server cost — your GPU does the work, so process a thousand images if you want to.
RMBG-1.4 is close on typical portraits and product shots. Very fine hair, glass and motion blur are still where commercial pipelines pull ahead. Try BiRefNet on the page for the hardest images.
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.