web-stable-diffusion
mach
web-stable-diffusion | mach | |
---|---|---|
21 | 36 | |
3,455 | 2,809 | |
1.6% | 3.2% | |
4.4 | 9.7 | |
about 2 months ago | 10 days ago | |
Jupyter Notebook | Zig | |
Apache License 2.0 | GNU General Public License v3.0 or later |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
web-stable-diffusion
-
GPU-Accelerated LLM on a $100 Orange Pi
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
-
StableDiffusion can now run directly in the browser on WebGPU
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/
- Web StableDiffusion
-
[Stable Diffusion] Diffusion stable Web: exécution de diffusion stable directement dans le navigateur sans serveur GPU
[https://github.com/mlc-ai/web-stable-diffusion
-
Now that they started banning stable diffusion on google colab, what's the cheapest and the best way to deploy stable diffusion?
You can run it directly in the browser with WebGPU, https://mlc.ai/web-stable-diffusion/
-
I've got Stable Diffusion integrated into my site now, fully client side with no setup or servers.
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.
-
Chrome Ships WebGPU
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
- Bringing stable diffusion models to web browsers
- mlc-ai/web-stable-diffusion: Bringing stable diffusion models to web browsers. Everything runs inside the browser with no server support.
- Web Stable Diffusion: Running Diffusion Models with WebGPU
mach
-
Zig Software Foundation 2024 Financial Report and Fundraiser
Myself and many others are betting on Zig in major ways, I truly think it has a bright future ahead.
In spare time, myself and a few others are working on a game engine in Zig[0], and the Zig core team has been very receptive to addressing issues our project faces and supporting us.
Others are working on pixel art editors[1], open source 2D RPG games[2], there's a group of independent folks working on a 3D massive immersive sim game[3], a group working on making Zig an amazing language for micro-controllers[4], etc.
Please consider donating $5-10 a month to the ZSF! They are a great group of people, and it has so many knock-on effects for others in the FOSS community. :)
[0] https://machengine.org/
[1] https://github.com/foxnne/pixi
[2] https://github.com/foxnne/aftersun
[3] https://github.com/Srekel/tides-of-revival
[4] https://github.com/ZigEmbeddedGroup
-
DevDocs
I don't know if there's anything better than a zip. For our website[0] which includes a bunch of docs for our game engine, Zig packages, etc. we just offer a link "offline version of this site" in the footer which is an ~80MB zip file.
I think the challenge with zip files is.. do you want all the images? do you want all versions of the docs, or just a specific version of the docs? It's hard to tailor the zip to the user's desire. But zip still seems to be the best.
[0] https://machengine.org/
- Not only Unity...
- Mach - Zig game engine & graphics toolkit
-
New Béziers from Math
Cool to see others working on this problem. I hope more people do.
Funnily I've seen a lot of programmers and math folks who express how truly, genuinely beautiful Beziers and the math behind them are. But I've never met an artist or graphic designer who didn't express some deep frustration at Bezier controls and how hard they are to work with.
There are even games[0] which make a mockery out of how hard Bezier controls are to use, where the game is purely using the controls.
Controls are just one side of the problem, in my view; the other side is that cubics are terrible for GPUs, they don't understand them - and I believe many of the best 2D graphics libraries today are not even fully GPU accelerated, e.g. Skia. There are folks working on compute shader-based approaches, where we try to shoe-horn this CPU-focused algorithm into GPUs and pray - but it still isn't really suitable.
The controls suck for artists, and the math sucks for GPUs. This is only true of cubics, if you restrict yourself to quadratics (although that brings other challenges), both the control issue goes away (you can just click+drag the curve!) and the performance issue goes away (quadratics are triangles, GPUs love them)
That's the summary of the talk[1] I gave at SYCL'22. In that talk, I didn't have time to present the downsides of quadratics (which are real) - so if you watch it please keep that in mind - but my overall point I think is a solid one: the controls suck, and GPUs can't handle them.
The only reason we stick with cubics in its current form is because of SVG, compatibility with existing tooling, etc. But isn't it crazy? We have new bitmap image formats all the time, and so few vector graphics formats.
In Mach engine[2] we're continuing to explore this space, end-to-end, from author tooling -> format -> rendering. I'm not claiming we have a perfect solution, we don't, but we're at least thinking about this problem. Kudos to the authors of this article for thinking about this space as well.
[0] https://bezier.method.ac/
[1] https://www.youtube.com/watch?v=QTybQ-5MlrE
[2] https://machengine.org
-
0.11.0 Release Notes
A game engine https://machengine.org is being written in zig, there's also https://microzig.tech as zig is well suited to embedded development.
-
Significant examples of Zig software (June 2023)?
https://github.com/hexops/mach (shameless plug)
-
Learn WebGPU
Zig fits pretty naturally here too. We've got ~19 WebGPU examples[1] which use Dawn natively (no browser support yet), and we build it using Zig's build system so it 'just works' out of the box with zero fuss as long as you grab a recent Zig version[2]. No messing with cmake/ninja/depot_tools/etc.
WASM support in Zig, Rust, and C++ is also not equal. C++ prefers Emscripten which reimplements parts of popular libraries like SDL, for me personally that feels a bit weird as I don't want my compiler implementing my libraries / changing how they behave. Rust I believe generally avoids emscripten(?), but Zig for sure lets me target WASM natively and compile C/C++ code to it using the LLVM backend and soon the custom Zig compiler backend.
[1] https://github.com/hexops/mach-examples
[2] https://github.com/hexops/mach#supported-zig-version
-
Zig for gamedev?
We're building Mach which aims to be competitive with Unity/Unreal/Godot in spriti, but super modular / let you pick and choose which parts to use or build yourself.
-
Mach (Zig) Adventures - Part 1
git clone --recursive https://github.com/hexops/mach-examples cd mach-examples/ zig build run-sprite2d
What are some alternatives?
stable-diffusion-webui-directml - Stable Diffusion web UI
SDL.zig - A shallow wrapper around SDL that provides object API and error handling
rust-bert - Rust native ready-to-use NLP pipelines and transformer-based models (BERT, DistilBERT, GPT2,...)
zig - General-purpose programming language and toolchain for maintaining robust, optimal, and reusable software.
SHA256-WebGPU - Implementation of sha256 in WGSL
quickjs-emscripten - Safely execute untrusted Javascript in your Javascript, and execute synchronous code that uses async functions
wgpu-py - Next generation GPU API for Python
zigstr - Zigstr is a UTF-8 string type for Zig programs.
onnxruntime - ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
arocc - A C compiler written in Zig.
js-promise-integration - JavaScript Promise Integration
mach-glfw-vulkan-example - mach-glfw Vulkan example