this post was submitted on 06 Jul 2023
16 points (100.0% liked)

Stable Diffusion

4304 readers
4 users here now

Discuss matters related to our favourite AI Art generation technology

Also see

Other communities

founded 1 year ago
MODERATORS
 

Hi there, I'm trying to get (more or less) historically accurate images from the early and high middle ages, but none of the models seems to have a grasp of what "maille armor" or "bucket helmets" are and I either get complete garbage or fantasy armor that mostly resembles the early modern period (the stereotypical shining knight armor).

I assume a Lora, trained on images of the armor and weapons I'd like to include, could fix this problem. I found some neat tutorials for making Lora's and think I'll give it a shot.

Do any of you have experience in making these kinds of style Lora's? What should I take care of? I will be manually downloading images that fit my aestethic and manually tag them - how many images should I use? Any input here is highly appreciated.

you are viewing a single comment's thread
view the rest of the comments
[โ€“] [email protected] 1 points 1 year ago (1 children)

I think I'll try autotagging with 1-2 pictures just to see how the format looks and how its supposed to work for starters. Then do all the real tagging manually. Just to make sure, I got the syntax right.

[โ€“] [email protected] 1 points 1 year ago

Yeah, that's a decent idea. Autotagging will at least spit out one txt file per file, which will save you from having to make them, and they can fill in the "man standing in a field" parts of the prompt.