import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("WhiteAiZ/Illustrious_2.0", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("HakuriTada/Tousen")
prompt = "lazypos,"
image = pipe(prompt).images[0]Tousen | Illustrious XL
- Prompt
- lazypos,
- Negative Prompt
- lazyneg, lazyhand, (light particles:0.4), film grain, (((joints, doll joints))), lazynsfw
Model description
Weight can be use: 0.7 ~ 0.9 Trigger word: tousen Best samplar: Euler / Euler A Steps: 20 ~ 30 CFG Scale: 3 ~ 5 Clip skip: 2
Trigger words
You should use Tousen to trigger the image generation.
Download model
Download them in the Files & versions tab.
- Downloads last month
- 3
Model tree for HakuriTada/Tousen
Base model
WhiteAiZ/Illustrious_2.0