LoRA DreamBooth - merve/lego-lora-trained-xl

These are LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0. The weights were trained on a picture of <s1><s2> minifigure using DreamBooth. You can find some example images in the following.

You can use this code 👇

from huggingface_hub.repocard import RepoCard
from diffusers import DiffusionPipeline
import torch

lora_model_id = "merve/lego-lora-trained-xl"
card = RepoCard.load(lora_model_id)
base_model_id = card.data.to_dict()["base_model"]

pipe = DiffusionPipeline.from_pretrained(base_model_id, torch_dtype=torch.float16)
pipe = pipe.to("cuda")
pipe.load_lora_weights(lora_model_id)

pipe("a picture of <s1><s2> minifigure as lana del rey, high quality", num_inference_steps=35).images[0]

LoRA for the text encoder was enabled: False.

Special VAE used for training: madebyollin/sdxl-vae-fp16-fix.