web-stable-diffusion VS stable-diffusion-paperspace

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

The other path I am going now: https://github.com/Engineer-of-Stuff/stable-diffusion-paperspace This is automatic1111. It is a very good written notebook. One thing I noticed that i could not install extensions. But when I turned on the password (that you can do in the early settup stages of this notebook, just enter a login name and password there) then extensions will be unlocked... otherwise rando`s can come into your notebook and install extensions...

The "easiest" (due to the provider being okay with it) may be to use Paperspace in conjunction with this notebook

yes there is https://github.com/Engineer-of-Stuff/stable-diffusion-paperspace

im running mine on paperspace. 8 dollars per month and most of the time you can use free RTX4000 GPUs. im using the ipynb from here: https://github.com/Engineer-of-Stuff/stable-diffusion-paperspace

You can't use DreamStudio to train your models, and I don't think there are any other apps available for training. DreamStudio is one of the cheapest options for image generation, at 10 USD for about 5000 generations. But it has limited models, and no sampling method selection. I haven't tried any other paid apps for SD. What I use is a PaperSpace notebook, with a Pro subscription. This guide will help you set up SD image generation/training using AUTOMATIC1111 on PaperSpace. Here is the ui-config.json that I use. And a list of models, for image generation.

I have a notebook I downloaded from here https://github.com/Engineer-of-Stuff/stable-diffusion-paperspace that works pretty well and can run automatic1111. Except the only problem is that it crashes like maybe once every 10 minutes.

Go here, and click on the code button and download the ZIP file. Unzip it and you'll find it in there.