Run Stable Diffusion on your own PC
A GPU and plenty of time to spend downloading
WHILE MOST OF THE TEXT- AND IMAGE- GENERATING AI MODELS we’ve discussed here run in massive throbbing data centers on racks of GPUs—indeed, Elon Musk purchased 10,000 Nvidia cards in March for an unannounced AI project within Twitter—there is one that can be run on your home PC.
Stable Diffusion is a deep learning text-to-image service that was released in 2022. It uses a diffusion model rather than a large language model, but the concept is broadly similar in that it’s probability based and is trained from images harvested from the wider internet, plus words associated with them, as well as versions of the same images that have been blurred. With this knowledge, Stable Diffusion is able to begin with a frame full of random image noise, and works to de-blur it to ‘reveal’ the image. The final result is based on the model’s training and the prompt it’s provided with.
If you go to stablediffusionweb.com, you’ll be able to use Stable Diffusion to create images, but it’s also possible to run it on your own PC as long as your graphics card has 6GB or more VRAM. It doesn’t matter if the card is from AMD or Nvidia, as it doesn’t use any technology that’s specific to a manufacturer. It’s the RAM allocation that counts, though it also helps if your card is a newer one. You’ll need to download a lot of data to make this work, but once you’ve got it, you’ll have your own image generation service at your fingertips. There’s no copyright on AIgenerated images, and those created by Stable Diffusion are fully public domain, so you’ll be able to use them in social media posts, college assignments, hilarious pranks, and even more.
1
DOWNLOAD AND DOWNLOAD SOME MORE
We’re going to show you how to install Stable Diffusion with a GUI on Windows, as we suspect that no one really likes messing around with command prompts. You’ll need to have Python (the programming language) and Git (the version control system) installed first, which are easily acquired from python. org/downloads and git-scm.com/download/win respectively.
» Once these are installed, you’ll need the Stable Diffusion GUI GitHub repo, which is at https://github.com/AUTOMATIC1111/ stable-diffusion-webui. Click the green Code button and choose Download Zip [ Image A]. Unzip the file and save it wherever you want, but make sure you keep a note of the folder location, as it will become the working folder for the installation.
» If you don’t want to (or can’t) download Python and Git, there’s a version with everything included available at https:// github.com/AUTOMATIC1111/stable-diffusion-webui/releases/ tag/v1.0.0-pre, but it works with Nvidia GPUs only.
» Next, you’re going to need some checkpoints. These are a
dump of an AI model’s internal state at a specific point, and are a great alternative to setting up and training your own. You can get them from the machine learning community Huggingface, and specifically you want sd-v1-4.ckpt from https://huggingface.co/CompVis/ stable-diffusion-v-1-4-original. It’s over 4GB, but once it’s down, put it in the “stable-diffusion-webuimaster\models\Stable-diffusion” folder and rename it to model.ckpt.
2
KEEP ON DOWNLOADING
There’s more. You’ll also need as many ESRGAN (Enhanced Super-Resolution Generative