hjLabs AI Playground
Starting the on-device runtime…
Metric3D ViT Small is an 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 151 MB download comes straight from the Hugging Face repository “onnx-community/metric3d-vit-small” 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.
Predicts depth in actual metres rather than a relative 0-1 map — the one to use if you need real distances. 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). 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 140 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 Metric3D ViT Small here is the one-off 151 MB download, and once that is cached the page keeps working with the network switched off.
metric3d vit smallmetric3d vit small onnxmetric3d vit small browserrun metric3d vit small locallyonnx-community/metric3d-vit-smalldepth estimation modelmetric3d vit small webgpumetric3d vit small download sizefree depth estimation modeltransformers.js model
About 151 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. onnx-community/metric3d-vit-small 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.