import torch
from diffusers import DiffusionPipeline
from diffusers.utils import load_image
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("GreeneryScenery/SheepsControlV1", 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]V1
First try at training a custom ControlNet. (Only 1 epoch 🤗) Using dataset from here.
Follow this to use (u sure ya wanna use?).
Things to improve:
- More variety of data in general? (Not only sheeps)
- More data (More sheeps)
- More epochs
- Better text prompts
Example:
Prompt: Lamb
Conditioning image:
Image:
- Downloads last month
- 11