metadata
license: creativeml-openrail-m
language:
- en
library_name: diffusers
tags:
- text-to-image
- stable-diffusion
- stable-diffusion-xl
- SDXL
- LoRA
widget:
- text: >-
painting of an Ogryn from the Warhammer 40k universe, front view, large
muscular body, scarred face, tattered shirt and pants, dirt and grime,
large toothy grin, wide and bloodshot eyes, holding a large axe, hires
scan, oil on canvas, grimdark, moody, concept art, by John Wigley
<lora:Oldhammer:1>
output:
url: >-
https://huggingface.co/Schisim/Oldhammer-SDXL-LoRA/resolve/main/assets/sample_images/image%20(6).png?download=true
- text: >-
A painting of three red and metal jetbikes flying over a pipe in a fiery
industrial setting. The jetbikes are all flying at a slight angle and are
angled toward the viewer. The jetbikes have a single rider each. The
riders are wearing red and metal armor and are all wearing helmets. The
jetbikes are all firing their guns. The background of the painting is a
dark sky with a hint of a moon. By Eric Ren. tabletop RPG artbook, hires
scan, concept art, grimdark, intricately detailed. <lora:Oldhammer:1>
output:
url: >-
https://huggingface.co/Schisim/Oldhammer-SDXL-LoRA/resolve/main/assets/sample_images/image%20(3).png?download=true
- text: >-
painting from warhammer 40k, Sister of battle, white hair, holding a
bolter in her right hand, epic, grimdark, [gothic], bold colors, oil on
canvas, by John Blanche <lora:Oldhammer:1>
output:
url: >-
https://huggingface.co/Schisim/Oldhammer-SDXL-LoRA/resolve/main/assets/sample_images/image%20(4).png?download=true
Oldhammer SDXL
The inference images are just to display samples. The inference API is not connected.
Base Model | SDXL v1.0 |
VAE | SDXL-VAE-FP16-FIX |
Type | LoRA |
Note:
This LoRA was trained on a subset of a much larger dataset I am creating for a full-parameter WH40k SDXL fine-tune.
The dataset was not designed for LoRA training. As a result, you may experience some 'wonkiness'.
The prompts for the sample images are mostly taken from the dataset caption-pairs (the subset has been recaptioned since this LoRA was created). You can get much better results using your own prompts.