hjLabs AI Playground
Starting the on-device runtime…
Face Parsing is an ONNX model that assigns every pixel of an image to a class or an instance mask. On this page it runs entirely inside your browser: the 89 MB download comes straight from the Hugging Face repository “jonathandinu/face-parsing” into your browser cache, and every inference after that executes on your own GPU through WebGPU. That is a one-off download of well under a minute on a normal connection, and small enough that integrated graphics handle it without complaint.
Separate masks for skin, eyes, brows, lips, hair and clothing — the model behind most virtual make-up demos. In practice people reach for a model like this for masking, compositing, selective edits, and measuring how much of a frame a given class occupies.
Available precisions: q8 (8-bit) and fp32 (full precision). q8 comes first because it roughly halves the download at a quality cost you will struggle to measure on this class of model; fp32 is there when you want the reference numbers. Hugging Face records around 140k downloads a month — steady, real usage rather than a one-off research drop.
Because there is no inference server behind this page, there is nothing to rate-limit and nothing to bill: the only cost of running Face Parsing here is the one-off 89 MB download, and once that is cached the page keeps working with the network switched off.
face parsingface parsing onnxface parsing browserrun face parsing locallyjonathandinu/face-parsingimage segmentation modelface parsing webgpuface parsing download sizefree image segmentation modeltransformers.js model
About 89 MB for the q8 build, including the tokenizer and config files the runtime also has to fetch — this is the whole payload, not just the weights file. It is downloaded once and then served from the browser Cache Storage API.
Yes, through the WebAssembly fallback, which is slower but works anywhere. WebGPU (Chrome or Edge 113+, Safari 26+) is what makes it feel interactive. On WASM, prefer the smaller quantized build.
No. jonathandinu/face-parsing is a public repository, so your browser fetches the ONNX files directly over HTTPS. There is no account, no key and no server in between.
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.