Kaminos WebGPU Inference Kit

Run generative and vision models locally in responsive browser applications.

A shared runtime for GPU devices, model loading, queued inference and cooperative scheduling. Try a model below, or use the kit to build your own application.

Try it in your browser

Relight a photograph

Explore three photographs as surfaces under changing light. MoGe provides the shape; SuperMat provides the surface finish. Compare them with the original photograph.

Explore depth & materials Use your photograph locally

Included model results are playable immediately. No model download.

A metallic glowing orb compared as a flat photograph, recovered depth, image-based relighting and inferred materials — One photograph, four synchronized views.

Generate an image with FLUX

Type a prompt and watch FLUX.2 [klein] 4B generate an image on your GPU. The text encoder, four diffusion steps and image decoder all run in the browser.

Generate an image Model guide

First visit: 3.2 GB of weights, cached for later runs. Use a WebGPU-capable browser.

Nine locally generated portraits of a blue toy train in different scenes and levels of jank — Generated in Chrome, 512 by 512 pixels with four steps.

One runtime, different models

MoGe: Depth, surface normals and point maps from a photograph.; Reveal depth · Model guide
SHARP: A Gaussian-splat scene from one image.; Model guide
Stable Fast 3D: A textured, UV-unwrapped GLB mesh from one image.; Model guide
Kimodo: Skeletal motion from a text prompt. Text embeddings use an external server.; Model guide
SAM 3: Instance masks and transparent cutouts from an image and text prompt.; Example guide
TRELLIS 2: A textured 3D mesh from an image, with local tools for preparation and finishing.; Model guide
FLUX.2 [klein] 4B: Images from a prompt, with the full generation pipeline on WebGPU.; Model guide
SuperMat: Albedo, roughness and metallic material maps from an image.; Explore materials · Port source
UniMate: Skeletal animation from a text prompt for different rigged skeletons.; Model guide

Build with the kit

Start with a worked photograph example, then connect a model to the same session, route and invocation lifecycle. Model guides cover weights, device requirements and embedding each port.

npm install @kaminos/webgpu-inference-kit

Getting started Runtime and architecture API reference