← all repositories

mlc-ai/web-stable-diffusion

A browser-based inference runtime that executes Stable Diffusion image generation models entirely client-side using WebAssembly and WebGPU.

3.7k stars Jupyter Notebook Inference · ServingImage · Video · Audio
web-stable-diffusion
Not currently ranked — collecting fresh signals.
star history

This project ports Stable Diffusion models to web browsers by compiling them to WebAssembly and running inference via WebGPU. All computation happens on the client device with no server communication required. The implementation uses TVM (Tensor Virtual Machine) for model compilation and optimization, targeting the WebGPU compute API to achieve reasonable performance for generative image tasks in a web environment.

Frequently asked

What is mlc-ai/web-stable-diffusion?
A browser-based inference runtime that executes Stable Diffusion image generation models entirely client-side using WebAssembly and WebGPU.
Is web-stable-diffusion open source?
Yes — mlc-ai/web-stable-diffusion is open source, released under the Apache-2.0 license.
What language is web-stable-diffusion written in?
mlc-ai/web-stable-diffusion is primarily written in Jupyter Notebook.
How popular is web-stable-diffusion?
mlc-ai/web-stable-diffusion has 3.7k stars on GitHub.
Where can I find web-stable-diffusion?
mlc-ai/web-stable-diffusion is on GitHub at https://github.com/mlc-ai/web-stable-diffusion.

heatdrop uses Google Analytics to see which pages get read — nothing else. Your call. How we handle data.