#106 · Primary category： Image Generation
web-stable-diffusion
Bringing stable diffusion models to web browsers. Everything runs inside the browser with no server support.
Project last updated：03/12/24
GitHub Stars
3.7K
Forks
238
Contributors
10
License
Apache-2.0
Why we included this project
The usual way to ship text-to-image is to rent a GPU server, but this project compiles stable diffusion into WebGPU and WebAssembly so the prompt, the latent diffusion step, and the image decoding all happen inside a browser tab. That saves the per-request inference bill and keeps prompts off hardware you do not control, both benefits the README calls out explicitly. It is built on the MLC/TVM toolchain, the same stack behind the sibling WebLLM project, which makes it a handy reference for anyone wondering how far client-side generative AI can go. There is working code, a live demo, and a concrete answer to whether your own workload could run without a backend.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
stable-diffusion-webui
Stable Diffusion web UI
ComfyUI
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
diffusers
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.
upscayl
🆙 Upscayl - #1 Free and Open Source AI Image Upscaler for Linux, MacOS and Windows.
InvokeAI
InvokeAI is a leading open-source creative engine for Stable Diffusion, offering an industry-leading web UI for generating and editing visual media.