import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("andite/anything-v4.0", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("lora-library/saz")
prompt = "saz"
image = pipe(prompt).images[0]LoRA DreamBooth - saz
These are LoRA adaption weights for andite/anything-v4.0. The weights were trained on the instance prompt "saz" using DreamBooth. You can find some example images in the following.
- Downloads last month
- 2