import torch
from diffusers import DiffusionPipeline
from diffusers.utils import load_image
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("GreeneryScenery/SheepsControlV2", dtype=torch.bfloat16, device_map="cuda")
prompt = "Turn this cat into a dog"
input_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png")
image = pipe(image=input_image, prompt=prompt).images[0]V2
3 epochs 🤗.
Much room for improvement.
Examples:
Conditional image:
Images:
A bull:
A chicken:
A cow with background removed, 8k:
A donkey:
A goat:
A realistic horse on a field with background removed, 8k:
A realistic horse on ice with background removed, 8k:
A realistic horse with background removed, 8k:
A realistic sheep on ice with background removed, 8k:
A sheep facing left:
A tiger:
- Downloads last month
- 19