import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("li-yan/cat-by-breed-stable-diffusion", dtype=torch.bfloat16, device_map="cuda")
prompt = "a photo of maine coon cat on the Golden Gate Bridge"
image = pipe(prompt).images[0]Trained by li-yan on the li-yan/cat-by-breed-part1-v1 dataset.
This is a Stable Diffusion model fine-tuned on the cat image by different breeds. It can be used by modifying the instance_prompt: a photo of maine coon cat on the Golden Gate Bridge
Description
This is a Stable Diffusion model fine-tuned on dataset "li-yan/cat-by-breed" images for the different breeds of cats.
Usage
from diffusers import StableDiffusionPipeline
pipeline = StableDiffusionPipeline.from_pretrained('li-yan/cat-by-breed-stable-diffusion')
image = pipeline().images[0]
image
- Downloads last month
- 4