import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("John6666/ilustmix-v10-sdxl", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("Shero448/tsubaki-ilu")
prompt = "masterpiece, best quality, indoors, cinematic lighting, amazing quality, very aesthetic, absurdres, best quality, 4k, upscale, Tsubaki, solo, looking at viewer, blush, smile, sky, indoors, sweatdrop, covered nipples, dutch angle, night, night sky, robe, sliding doors <lora:JN_Tsubaki_Illus:0.8>"
image = pipe(prompt).images[0]tsubaki-ilu
- Prompt
- masterpiece, best quality, indoors, cinematic lighting, amazing quality, very aesthetic, absurdres, best quality, 4k, upscale, Tsubaki, solo, looking at viewer, blush, smile, sky, indoors, sweatdrop, covered nipples, dutch angle, night, night sky, robe, sliding doors <lora:JN_Tsubaki_Illus:0.8>
- Negative Prompt
- pubic hair, 3d, cropped, loli, censored, bar censoring, mosaic censoring, (simple background:1.0), siblings, bad legs, clones, monochrome, clones, sketch, rought lines, patreon username, logo, bad proportions, artist signature, artist name,
Trigger words
You should use Tsubaki to trigger the image generation.
You should use breasts to trigger the image generation.
You should use japanese clothes to trigger the image generation.
You should use kimono 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
- 2
Model tree for Shero448/tsubaki-ilu
Base model
KBlueLeaf/kohaku-xl-beta5 Finetuned
John6666/ilustmix-v10-sdxl