import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("John6666/wai-nsfw-illustrious-v110-sdxl", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("Shero448/erza-illu2")
prompt = "UNICODE\u0000\u0000 \u0000g\u0000e\u0000n\u0000e\u0000r\u0000a\u0000l\u0000,\u0000h\u0000i\u0000g\u0000h\u0000r\u0000e\u0000s\u0000,\u0000 \u0000u\u0000l\u0000t\u0000r\u0000a\u0000-\u0000d\u0000e\u0000t\u0000a\u0000i\u0000l\u0000e\u0000d\u0000,\u0000v\u0000e\u0000r\u0000y\u0000 \u0000a\u0000e\u0000s\u0000t\u0000h\u0000e\u0000t\u0000i\u0000c\u0000,\u0000b\u0000e\u0000s\u0000t\u0000 \u0000q\u0000u\u0000a\u0000l\u0000i\u0000t\u0000y\u0000 \u0000,\u0000b\u0000e\u0000s\u0000t\u0000 \u0000h\u0000a\u0000n\u0000d\u0000s\u0000,\u0000b\u0000e\u0000s\u0000t\u0000 \u0000e\u0000y\u0000e\u0000s\u0000,\u0000e\u0000a\u0000s\u0000y\u0000n\u0000e\u0000g\u0000a\u0000t\u0000i\u0000v\u0000e\u0000,\u0000"
image = pipe(prompt).images[0]erza-illu2
- Prompt
- UNICODE general,highres, ultra-detailed,very aesthetic,best quality ,best hands,best eyes,easynegative,
Trigger words
You should use Erza Scarlet to trigger the image generation.
You should use red hair to trigger the image generation.
You should use long_hair to trigger the image generation.
You should use brown eyes to trigger the image generation.
You should use huge_breasts to trigger the image generation.
You should use hair over one eye to trigger the image generation.
Download model
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.
- Downloads last month
- 1
Model tree for Shero448/erza-illu2
Base model
KBlueLeaf/kohaku-xl-beta5 Finetuned
John6666/wai-nsfw-illustrious-v110-sdxl