hjLabs AI Playground
Starting the on-device runtime…
GLPN NYU is a 62M-parameter ONNX model that predicts a relative depth value for every pixel of a single ordinary photograph. On this page it runs entirely inside your browser: the 246 MB download comes straight from the Hugging Face repository “Xenova/glpn-nyu” into your browser cache, and every inference after that executes on your own GPU through WebGPU. Expect a download of roughly a minute on a decent connection. It fits comfortably in the browser cache and in the memory of any GPU from the last few years, including laptop integrated graphics.
Trained on NYU indoor scans, so it is unusually good at rooms and unusually poor outdoors. In practice people reach for a model like this for depth-of-field and parallax effects, depth-driven compositing, and feeding the 3D point-cloud viewer.
Available precisions: fp32 (full precision) and q8 (8-bit). fp32 comes first because at this size full precision is both the fastest WebGPU path and the best quality; the quantized variant exists for the WebAssembly fallback and for tight cache budgets. Hugging Face records about 319 downloads a month. It is a specialist choice rather than a default, which is exactly why it is worth trying when the popular model gets your particular input wrong.
Because there is no inference server behind this page, there is nothing to rate-limit and nothing to bill: the only cost of running GLPN NYU here is the one-off 246 MB download, and once that is cached the page keeps working with the network switched off.
glpn nyuglpn nyu onnxglpn nyu browserrun glpn nyu locallyxenova/glpn-nyudepth estimation modelglpn nyu webgpuglpn nyu download sizefree depth estimation modeltransformers.js model
About 246 MB for the fp32 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. Xenova/glpn-nyu 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.