import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("lucostiguy11/dreambooth_if_1", dtype=torch.bfloat16, device_map="cuda")
prompt = "A photo of sks dog in a bucket"
image = pipe(prompt).images[0]DreamBooth - lucostiguy11/dreambooth_if_1
This is a dreambooth model derived from DeepFloyd/IF-I-XL-v1.0. The weights were trained on A photo of sks dog in a bucket using DreamBooth. You can find some example images in the following.
DreamBooth for the text encoder was enabled: False.
- Downloads last month
- 4
Model tree for lucostiguy11/dreambooth_if_1
Base model
DeepFloyd/IF-I-XL-v1.0