{"id":1040,"date":"2023-02-27T13:11:06","date_gmt":"2023-02-27T19:11:06","guid":{"rendered":"https:\/\/promptphantom.com\/?p=1040"},"modified":"2023-02-27T13:11:07","modified_gmt":"2023-02-27T19:11:07","slug":"how-do-you-install-models-in-stable-diffusion","status":"publish","type":"post","link":"https:\/\/promptphantom.com\/how-do-you-install-models-in-stable-diffusion\/","title":{"rendered":"How Do You Install Models in Stable Diffusion?"},"content":{"rendered":"\n

Have you heard about custom models for Stable Diffusion, but you don\u2019t know how to install and use them? Don\u2019t worry, I\u2019ll show you the way! In this quick guide, I\u2019ll show you the super easy way to add endless custom models to your current installation of Stable Diffusion<\/p>\n\n\n

What is a Stable Diffusion Model?<\/h1>\n\n\n

I have a full article<\/a> on this topic. But, in summary, a Stable Diffusion model is a file that tells Stable Diffusion how to create images in a certain way based on a specific dataset. Custom models can be trained on a custom set of images (on top of the base dataset, that is).<\/strong><\/p>\n\n\n\n

If you want to train a model to know and recreate your own face, you can do that. If you want to train a model on a specific art style, then you can do that too!<\/p>\n\n\n\n

Models in Stable Diffusion are like mod packs in video games: they add onto the base game experience with more content (or, in this case, more specific styles of content).<\/p>\n\n\n\n

\"\"<\/figure>\n\n\n

How To Install New Models in Stable Diffusion<\/h1>\n\n\n

So how do we install a custom model into Stable Diffusion? You don\u2019t actually have to install models, you just add them to a sub-folder. That\u2019s it! Do you have Stable Diffusion installed on your computer<\/a> already? Then you\u2019re good to go.<\/strong><\/p>\n\n\n\n

To \u201cinstall\u201d a model, just download it\u2019s checkpoint file (either a .CKPT or a .SafeTensors file) and place it in your \u201cmodels\u201d subfolder. The location of your subfolder depends on:<\/p>\n\n\n\n