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.

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.

Yeah I absolutely prefer the OpenPose approach because #1 you can guarantee that you will have (at least) the number of subjects that you want, it’s fairly straightforward, and I like having control over the pose.

If you are using SD1.4/SD1.5 I’d use controlnet with openpose