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("kycocotree/lora-trained-xl_with_text_encoder")
prompt = "realistic, photorealism, highest quality, a photo of a man wearing an sks t-shirt, natural textures"
image = pipe(prompt).images[0]LoRA DreamBooth - kycocotree/lora-trained-xl_with_text_encoder
These are LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0. The weights were trained on realistic, photorealism, highest quality, a photo of a man wearing an sks t-shirt, natural textures using DreamBooth. You can find some example images in the following.
LoRA for the text encoder was enabled: True.
Special VAE used for training: madebyollin/sdxl-vae-fp16-fix.
- Downloads last month
- 6
Model tree for kycocotree/lora-trained-xl_with_text_encoder
Base model
stabilityai/stable-diffusion-xl-base-1.0