Generating images with A.I for free using Automatic1111
Are you reading about A.I generated images online and been facinated by it but haven’t tried yet, this blog is for you. We’ll go through setting up a Google Colab (for free GPU access), host Automatic1111 (more on this a moment later), train Dreambooth, Launch Gradio, enter prompt and be blown away with thing it generate.
Don’t you worry if you have no idea about any of this term, I didn’t had it when I first started diving into it. But it’s easy to understand and I’ll be guiding you along.
How to run AUTOMATIC1111 on Google Colab
This is a step-by-step guide for using the Google Colab notebook in the Quick Start Guide to run AUTOMATIC1111. This is one of the easiest way to use AUTOMATIC1111 because you don’t need to deal with install.
What is AUTOMATIC1111?
You should know what AUTOMATIC1111 is if you want to be a serious user of Stable Diffusion. You can choose not to use it. But you need to know what it can do because it is the gold standard in terms of features, though not necessarily software stability…
Stable Diffusion is a machine learning model. By itself is not very user-friendly. You will need to write codes to use it. It’s kind of a hassle. Most users use a GUI (Graphical User Interface) to use Stable Diffusion. Instead of writing codes, we write prompt in a text box and click some buttons to generate images.
AUTOMATIC1111 was one of the first GUI developed for Stable Diffusion. Although it associates with AUTOMATIC1111’s GitHub account, it has been a community effort to develop this software.
AUTOMATIC1111 is feature-rich: You can use text-to-image, image-to-image, upscaling, depth-to-image, run and train custom models all within this GUI. Many of the tutorials in this site are demonstrated with this GUI.
What is Google Colab?
Google Colab is an interactive computing service offered by Google. You can use it if you have a free Google account. You can use Colab for free but you may get disconnected during busy hours or have been using too much lately.
They have three paid plans – Pay As You Go, Colab Pro and Colab Pro+. If you decided to pay, I recommend using the Colab Pro plan. It gives you 100 compute unit per month which is about 50 hours on a standard GPU. (It’s a steal) You can also request high RAM machines which may come handy if you need to generate large or many images.
With a paid plan, you can choose to use Premium GPU, which is a A100 processor. That comes in handy when you need to train Dreambooth models fast.
If you use Colab for AUTOMATIC1111, be sure to disconnect and shut down the notebook when you are done. It will consume compute units when notebook is kept open.
Step-by-step instructions to run Colab notebook
Step 1. Open the Colab notebook in Quick Start Guide. You should see the notebook with the second cell like below.
Step 2. Review username and password. You will need the credential after you start AUTOMATIC11111.
Step 3. Check SAVE_IN_GOOGLE_DRIVE if you want to save all images generated in your Google Drive automatically. It will be saved under the directory specified in output_path. You will need to grant permission to access Google Drive if you check this option.
Step 4. Check the models you want to load. Currently we offer v1.4, v1.5, v1.5 inpainting, F222, anything v3, inkpunk diffusion, Mo Di diffusion, v2.1-512, v2.1-768 and v2 depth model.
If you are a first time user, you can just select v1.5 model.
Step 5. You can optionally include models in your Google Drive, such as the ones created from the Dreambooth notebook. You can include multiple models. Separate them with commas.
Step 6. Click the Play button on left of the cell to start.
Step 7. Start up should complete within a few minutes. How long it takes depends on how many models you include. When it is done, you should see the message like below.
Step 8. Follow the
gradio.livelink to start AUTOMATIC1111.Step 9. Enter username and password you specified in the notebook.
Step 10. You should see the AUTOMATIC1111 GUI after you login.
Put in “a cat” in the prompt text box and press Generate to test using Stable Diffusion. You should see it generates an image of a cat.