If you like my work and would like to leave a review, go for it. Motivation is motivation. I do this for fun mainly.

This LoRA is part of a Collection!

Model Information

A Clothing LoRA from Conan Exiles Enhanced. It's called Pictish Brave.

Dataset consists of 15 images. I basically locked the time and weather to noon, went into the Nordheimer region, stood in a place with grass and trees, went into Tot Custom and took some screenshots from multiple angles (with some poses). They may or may not be stiff.

Helpful Information

Sample Images may involve wildcards for poses, angles and backgrounds. They were ran through x/y/z plot across multiple checkpoints. ADetailer and 4x-UltraSharpV2 are typically used as well.

Metadata is not scrubbed so feel free to reference the sample images for generation tips.

Training Notes

For these outfits, my target steps were on the lower end (480 steps). I intentionally aimed to undertrain them as the intent was to take video game outfits and prompt them with anime styles in some decency.

If you want to know my training settings, load my LoRA through something like LoRA Metadata Viewer and take a look. AI Toolkit is nasty, and so is scrubbing metadata!

Prompt Usage

Here is how to prompt the outfit. Poses, expressions, angles and anything else of the sort is up to the user.

Pictish Brave (in-game preview)

pictish_brave_cl, 1girl, solo, wolf pelt headdress, black fur trim, midriff, bone-studded pauldron, black fur mantle, leg wraps, metal breastplate, leather 
bracers, bone-studded loincloth

Others: outdoor, grass, wildflowers, forest background, daytime, 3d, game screenshot, realistic

Final Notes

Slapping this at the very end of my description(s) in an attempt not to annoy people as much.

1) I create content entirety for fun. I refuse to do this for money or to ask for money. I don't do commissions or anything of the sort. You can request things, but if I don't like it or care for it, you won't get a response.

2) If you are curious how I made something, just ask me. I don't mind sharing a dataset, training settings and the sort. I am a curious person. I'm not overly protective of my work and I am not worried about who does or does not jack off to it.