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/dreembooth_two_hands_touching")
prompt = "closeup of two human sks hands holding each other"
image = pipe(prompt).images[0]LoRA DreamBooth - Gurusha/dreembooth_two_hands_touching
These are LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0. The weights were trained on closeup of two human sks hands holding each other 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
- 1
Model tree for Gurusha/dreembooth_two_hands_touching
Base model
stabilityai/stable-diffusion-xl-base-1.0