import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("animagine-xl-4.0", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("Rudra973592/jjk-style-lora")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]JJK Style LoRA
A custom LoRA trained for Jujutsu Kaisen anime style.
Trigger words
jjkstyle
Recommended settings
- Weight: 0.8–1.0
- Sampler: Euler a
- Steps: 30
- CFG: 6
Example prompt
lora:jjk_style_lora-20:1 jjkstyle, solo, smile, short hair, long sleeves, 1boy, jacket, closed eyes, upper body, white hair, male focus, outdoors, hand up, grin, tree, black jacket, facing viewer, high collar, blindfold, black blindfold, gojou satoru
- Downloads last month
- 25