Warhammer 40K LoRAs' SDXL
Collection
Warhammer 40K SDXL LoRA(s) by nDimensional. All networks trained from SDXL v1.0
• 16 items • Updated • 3
How to use nDimensional/Oldhammer-SDXL-LoRA-Warhammer-40k with Diffusers:
pip install -U diffusers transformers accelerate
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("nDimensional/Oldhammer-SDXL-LoRA-Warhammer-40k", dtype=torch.bfloat16, device_map="cuda")
prompt = "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>"
image = pipe(prompt).images[0].png?download=true)
.png?download=true)
.png?download=true)
| 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.