Stable Diffusion - Experimenting with different checkpoints
Stable Diffusion - Experimenting with different checkpoints
I am in the process of learning the basics, and I was exploring what different checkpoints would look like for the same set of configuration. I thought the results were interesting and that it was worth sharing.
You're viewing a single thread.
-
Is there an easy to follow step by step guide to setting up Stable Diffusion?
I have a powerful PC but the few times I’ve looked into it it seemed complex.
And is it all prompts or can I feed it example photos to have it use?
-
I got started by following the sticky post in this community. Warning: there is a bit of a learning curve to get good, but everyone should at least try because its not hard to at least get going.
-
https://github.com/AUTOMATIC1111/stable-diffusion-webui is the go-to web ui and it's fairly easy to set up, not much harder than running a regular installer for any other software, just make sure you have the required python version installed.
You mainly use text prompts, but there are ways to use example photos to get similar images. You'll want to look into the controlnet extension, and specifically the "reference" modes.
-
FWIW, I am not using controlnet here or anything fancy. Just standard settings and a single prompt for every photo
-
Yeah, I wasn't implying that. Mentioning controlnet was mostly to answer @Anomalous_Llama@lemmy.world's question about being able to use example photos to generate new images.
-
-
-