web-stable-diffusion VS daedalOS

Yup, here's their web stable diffusion repo: https://github.com/mlc-ai/web-stable-diffusion

The input is a model (weights + runtime lib) compiled via the mlc-llm project: https://mlc.ai/mlc-llm/docs/compilation/compile_models.html

The MLC team got that working back in March: https://github.com/mlc-ai/web-stable-diffusion

Even more impressively, they followed up with support for several Large Language Models: https://webllm.mlc.ai/

[https://github.com/mlc-ai/web-stable-diffusion

You can run it directly in the browser with WebGPU, https://mlc.ai/web-stable-diffusion/

Using the amazing work of https://mlc.ai/web-stable-diffusion/ I've got the code moved into a Web Worker and running fully local client side. It does require 2GB's of model files be downloaded (automatically), and takes a few minutes for the first load, but it works and once it's going it only takes 20s to make a 512x512 image.

The Apache TVM machine learning compiler has a WASM and WebGPU backend, and can import from most DNN frameworks. Here's a project running Stable Diffusion with webgpu and TVM [1].

Questions exist around post-and-pre-processing code in folks' Python stacks, with e.g. NumPy and opencv. There's some NumPy to JS transpilers out there, but those aren't feature complete or fully integrated.

[1] https://github.com/mlc-ai/web-stable-diffusion

I've learned so much while making this project into my personal website (dustinbrett.com). It's made me a much better web developer as I have tried to emulate a desktop environment with pixel perfect accuracy using CSS, HTML & JavaScript.

I'm very happy to announce that my personal website has once again been nominated for a Webby Award!

This has also been ported to the web via Emscripten. I host it on my website if anyone wants to play. https://dustinbrett.com/?app=SpaceCadet

Demo: https://dustinbrett.com/

As someone who built a website around this idea, I agree! The desktop metaphor is powerful. If anyone wants to check it out it's at https://dustinbrett.com

Very cool! It's always refreshing to see the "OS in the browser" projects that try and actually make something functional. I've been working on one myself for nearly 3 years now, called daedalOS (https://github.com/DustinBrett/daedalOS).

The WASM kernel idea is very cool and I hope one day to be able to add something similar to my project. I think you are onto something and I am excited to see your progress as you implement the GUI.

If you want some Browserception, my desktop environment (https://dustinbrett.com/) can indeed do this. But after a few levels in Chromium you need to add a random query string (/?a=1) to the URL otherwise it stops working.