Text-to-Image
Diffusers
TensorBoard
StableDiffusionPipeline
stable-diffusion
stable-diffusion-diffusers
dreambooth
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("camus-ng/dreambooth_cory_v20", dtype=torch.bfloat16, device_map="cuda")
prompt = "a photo of a cory_ng man"
image = pipe(prompt).images[0]DreamBooth - camus-ng/dreambooth_cory_v20
This is a dreambooth model derived from stabilityai/stable-diffusion-2. The weights were trained on a photo of a cory_ng man using DreamBooth. You can find some example images in the following.
DreamBooth for the text encoder was enabled: False.
- Downloads last month
- 6
Model tree for camus-ng/dreambooth_cory_v20
Base model
stabilityai/stable-diffusion-2