{"id":3716,"date":"2024-08-08T19:17:12","date_gmt":"2024-08-08T17:17:12","guid":{"rendered":"https:\/\/www.robinglauser.ch\/blog\/?p=3716"},"modified":"2024-08-24T10:48:48","modified_gmt":"2024-08-24T08:48:48","slug":"how-to-setup-flux-model-locally-with-pinokio","status":"publish","type":"post","link":"https:\/\/www.robinglauser.ch\/blog\/2024\/08\/08\/how-to-setup-flux-model-locally-with-pinokio\/","title":{"rendered":"How to Setup Flux AI Model Locally with Pinokio"},"content":{"rendered":"

If you want to try out the new Flux model locally and don’t want to waste hours trying to set up Python, Conda, PyTorch, etc., I’ve got just the thing for you! This guide will walk you through the Flux Pinokio setup, making local AI image generation a breeze.<\/p>\n

With https:\/\/pinokio.computer\/<\/a>, you can easily install Flux and other models without risking your existing Python installation. It provides a nice, user-friendly interface to install, reset, and uninstall models.<\/p>\n

\n

What is Pinokio?<\/h4>\n

Pinokio is a self-contained platform that lets you install apps in an isolated manner.<\/p>\n

    \n
  1. Isolated Environment:<\/strong> No need to worry about messing up your global system configurations and environments<\/li>\n
  2. Batteries Included:<\/strong> No need to manually install required programs just to install something (such as ffmpeg<\/strong>, node.js<\/strong>, visual studio<\/strong>, conda<\/strong>, python<\/strong>, pip<\/strong>, etc.). Pinokio takes care of it automatically.<\/li>\n<\/ol>\n

    To achieve this, Pinokio stores everything under a single isolated folder (“pinokio home”)<\/strong>, so it never has to rely on your system-wide configs and programs but runs everything in a self-contained manner.<\/p>\n

    You can set the pinokio home<\/strong> folder when you first set up Pinokio, as well as later change it to a new location from the settings<\/strong> tab.<\/p>\n

    Taken straight from here: https:\/\/program.pinokio.computer\/#\/?id=pinokio-file-system<\/a><\/small><\/p>\n<\/div>\n

    \"Flux
    https:\/\/pinokio.computer\/item?uri=https:\/\/github.com\/pinokiofactory\/flux-webui<\/figcaption><\/figure>\n

    There is a Gradio interface, which you can see above, with which you can install to use the Flux model with no knowledge of Python just by following the instructions.<\/p>\n

    Flux Pinokio Setup: Installation Steps<\/h2>\n
      \n
    1. First, download Pinokio by following the instructions on https:\/\/program.pinokio.computer\/#\/?id=install<\/a><\/li>\n
    2. After installation, use the discover button on the menubar to get a list of installable apps:
      \n\"Discover<\/li>\n
    3. Select the flux-webui and click on it:
      \n\"Selecting<\/li>\n
    4. Press download on the next screen:
      \n\"Download<\/li>\n
    5. Confirm the directory and press download again. (No need to change the name, the default is fine.)
      \n\"Confirming<\/li>\n
    6. Press install again for a third time (I promise we’ll be done soon)
      \n\"Final<\/li>\n<\/ol>\n

      Now Pinokio will download and install all needed software to run the model.<\/p>\n

      \"Installation<\/p>\n

      After it has downloaded everything, you should see the Gradio interface, which will appear automatically:<\/p>\n

      \"Gradio<\/p>\n

      Here you can (1) input your prompt, (2) change the model, (3,4) configure the height, (5) select the number of images to generate and (6) choose how many inference steps the model should do.<\/p>\n

      Generating an Image with Flux Pinokio Setup<\/h2>\n

      Now we’ll try to generate an image. I’ve chosen “a black forest cake with the words ‘it works’ written in icing” as my prompt, but you do as you like.<\/p>\n

      \"Image<\/p>\n

      The first time it runs, it will have to download the model, which can take a long time. You can watch the process and also check if you get errors by clicking on the Terminal entry on the left menubar.<\/p>\n

      \"Terminal<\/p>\n

      This might take a while (5-10 minutes depending on the internet connection), so lie back and get yourself some coffee or other beverage.<\/p>\n