import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("Norod78/SD15-IllusionDiffusionPattern-LoRA")
prompt = "Wonderwoman IllusionDiffusionPattern"
image = pipe(prompt).images[0]Trigger word
Use "IllusionDiffusionPattern" in your prompts
Dataset
Trained upon the "high contrast" suffixed images in Norod78/microsoft-fluentui-emoji-512-whitebg
Intended use
- Generate input pattern images to be used with qrcode_monster
- Use LoRA scale weights in the range of around 0.5 to 0.8
Examples
Prompt: Kitten IllusionDiffusionPattern
LoRA weight scale: 0.5
Together with IP-Adapter + QR-Code Monster
Prompt:A spiral wormhole IllusionDiffusionPattern
LoRA weight scale: 0.8
Together with IP-Adapter + QR-Code Monster
- Downloads last month
- 31
Model tree for Norod78/SD15-IllusionDiffusionPattern-LoRA
Base model
runwayml/stable-diffusion-v1-5