Instructions to use Shero448/illya-ilu-1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Shero448/illya-ilu-1 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("John6666/ilustrealmix-v20-sdxl", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("Shero448/illya-ilu-1") prompt = "masterpiece, best quality, amazing quality, very aesthetic, absurdres, newest, scenery, 1girl, solo, medium breasts, <lora:illyasviel von einzbern illustxl:1> illyasviel von einzbern, white hair, long hair, red eyes, hair between eyes, purple headwear, papakha, white scarf, purple capelet, purple coat, long sleeves, coat dress, long dress, standing, upper body, dark, night, street, castle, outside, looking at viewer, shiny skin, masterpiece, best quality, amazing quality, very aesthetic, absurdres, newest, scenery" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
illya-ilu-1

- Prompt
- masterpiece, best quality, amazing quality, very aesthetic, absurdres, newest, scenery, 1girl, solo, medium breasts, <lora:illyasviel von einzbern illustxl:1> illyasviel von einzbern, white hair, long hair, red eyes, hair between eyes, purple headwear, papakha, white scarf, purple capelet, purple coat, long sleeves, coat dress, long dress, standing, upper body, dark, night, street, castle, outside, looking at viewer, shiny skin, masterpiece, best quality, amazing quality, very aesthetic, absurdres, newest, scenery
- Negative Prompt
- lowres, (worst quality:1.2), (bad quality:1.2), bad anatomy, sketch, jpeg artifacts, signature, watermark, old, oldest, censored, bar censor, (pregnant), chibi, loli, simple background, conjoined, ai-generated, 3d, realistic, (shaded face:1.1)
Trigger words
You should use illyasviel von einzbern to trigger the image generation.
You should use white hair to trigger the image generation.
You should use long hair to trigger the image generation.
You should use red eyes to trigger the image generation.
You should use hair between eyes 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
- -
Model tree for Shero448/illya-ilu-1
Base model
KBlueLeaf/kohaku-xl-beta5 Finetuned
John6666/ilustrealmix-v20-sdxl