In July 2023, I started making and posting AI generated images with Stable Diffusion (SD) and Automatic1111 (A1111) and started posting them to Inkbunny. It started out as a curiosity, but it has since turned into an ongoing hobby that has been a fun, creative outlet for me. Over the last year, I have had a lot of practice and learned a lot about how to (somewhat) efficiently use these tools. It turns out that I had a lot of ideas to explore, and SD gave me a way to explore those ideas and bring them to life.
For a while now, I have been contemplating the idea of making a tutorial series that examines how I use SD and A1111 to make my renders. I knew that this would take a lot of work, so I avoided it for a while. However, I have gotten several questions about my process, so I know there is some demand for it. Also, after getting 1000 watchers, I decided to finally start making this series as a way to thank my followers.
Current status
This journal will be used as a hub that will be kept up to date with the tutorials in the series. I’ll use this section for status updates.
2024-08-28: I've just posted Tutorial 7. This will be my last tutorial in the series for now. I’ve now covered most of the big topics I wanted in this series, and I am happy with how they turned out.
General details about this tutorial series
• I hope that these tutorials to be useful even if someone isn’t using my exact process. Not everyone can run SD locally or is using some UI other than A1111. A lot of the details will be specific to my setup, but I expect that some of the info to still be helpful. • Each tutorial will have a render that is meant to be reproducible. I will avoid using any add-ons like textual inversions, negative embeddings, LoRAs, or plugins; unless the use of those is the point of that tutorial. • The renders in the series will all be made using the model indigoFurryMix_v120Hybrid. I’ve tried a few different models and this one is my favorite. • I intend for these to be done in any order; except the first one which will just be an introduction and a test that you can reproduce my result. • The posts in the tutorial series will all be General rated. I do make a lot of NSFW, but the tutorials will not be about that. I want them to be as accessible as possible, and having them be viewable without an account will help with that.
List of tutorials posted
• Tutorial 1: Basic Overview Basic info about Stable Diffusion (SD) and (A1111). An overview of my work process. Steps on how to reproduce a sample render.
This list tracks my topic ideas for future tutorials. Feel free to send me ideas.
• Using LoRAs A low-rank adaptation (LoRA) provides a way to introduce a character, style, or concept into a model that does not already know it. Most commonly, LoRAs are used to add specific characters to a scene. Using them can sometimes be tricky and they don’t always work as you would expect.
• Using Textual inversions This probably doesn’t warrant its own tutorial, but textual inversions and negative embeddings are commonly used in SD renders. Sometimes, it is not indicated which phrases in a prompt are these, which could cause confusion for someone who doesn’t know this.
I appreciate the support, but I decided long ago that I'm not going to do that. The tutorials will be a lot of work, but I am choosing to do them on my own terms. I want to keep all of this as a personal creative hobby, and if I start accepting money it will become something else.
I appreciate the support, but I decided long ago that I'm not going to do that. The tutorials will b
Just saw your journal saying you completed this series, thank you so much for doing it! My GPU is getting repaired but when I get it back I'm going to try the techniques you outlined here. Really appreciate you putting so much time and effort into helping others, that's very respectable of you!
Just saw your journal saying you completed this series, thank you so much for doing it! My GPU is ge
