Skip to main content

Running models locally

All the big models run on external servers and are usually only available through a (paid) account. There are some alternatives available that you can run locally on your own machine. Installing these usually involves complex installation procedures, but there's a trend for 'one-click-installers' that get you set up relatively painlessly. Below you can find some simple installers for various generative AI's. At the moment there's also Pinokio, which strives to be something of an AI-app-store that can also automate processes between different AI types. You can find it here: https://pinokio.computer/

Note 1 All of these models take up significant amount of space on your computer. The environment can take up to 3Gb, and the models are even larger. Make sure you have around 30Gb free once you get these models running!

Note 2 Most of these models need (recent and beefy) Nvidia graphics cards to run, or Apple M1/M2.

Image generation on your own computer

These models are based on Stable Diffusion. You will not get the latest version, but you can re-train the model, or download variants from the internet. Automatic11111 also allows you to combine models.

Stable Diffusion WebUI by Automatic11111: https://github.com/AUTOMATIC1111/stable-diffusion-webui (Win, Linux, Mac)

Easy Diffusion https://github.com/easydiffusion/easydiffusion (Win, Linux, Mac)

Both programs above can be downloaded from the Github page directly, resulting in a folder containing a .bat file. Run this and it will start downloading and installing all necessary files. Once it's done, run the .bat again and the program will start in your browser.

DiffusionBee https://diffusionbee.com/ (Mac)

Text generation ('ChatGPT') on your own computer

Llama2: https://github.com/oobabooga/text-generation-webui (Win, Linux, Mac)

The program above can be downloaded from the Github page directly, resulting in a folder containing a .bat file. Run this and it will start downloading and installing all necessary files. Once it's done, run the .bat again and the system will be running in a terminal. At that point you can start the interface by opening your favourite browser and going to the web address that the terminal shows (usually http:\\127.0.0.1:7860).

The first time you run it you will still need to download a language model. You can find those on Huggingface, for instance TheBloke/Llama-2-7B-Chat-GPTQ. Not all models are available without registering on Huggingface. You can paste this address into the File Name section of the Model tab, then hit Download. After the model has been downloaded, you can load it from the Model loader bar on the top left.