import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("Gurusha/dreambooth_peace_sign")
prompt = "a human sks hand making peace sign, with index and middle finger pointing out and rest of the fingers folded"
image = pipe(prompt).images[0]LoRA DreamBooth - Gurusha/dreambooth_peace_sign
These are LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0. The weights were trained on a human sks hand making peace sign, with index and middle finger pointing out and rest of the fingers folded using DreamBooth. You can find some example images in the following.
LoRA for the text encoder was enabled: False.
Special VAE used for training: madebyollin/sdxl-vae-fp16-fix.
- Downloads last month
- 2
Model tree for Gurusha/dreambooth_peace_sign
Base model
stabilityai/stable-diffusion-xl-base-1.0