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("Charnx2/lora-trained-xl")
prompt = "Victorian-style illustration of sks Alice from Wonderland, falling down the rabbit hole bordered by floating furniture, books, and tea pots."
image = pipe(prompt).images[0]LoRA DreamBooth - Charnx2/lora-trained-xl
These are LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0. The weights were trained on Victorian-style illustration of sks Alice from Wonderland, falling down the rabbit hole bordered by floating furniture, books, and tea pots. 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
- 4
Model tree for Charnx2/lora-trained-xl
Base model
stabilityai/stable-diffusion-xl-base-1.0