Text-to-Image
Diffusers
PyTorch
StableDiffusionPipeline
stable-diffusion
diffusion-models-class
dreambooth-hackathon
animal
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("marshmellow77/rio-cat-sd-1-5", dtype=torch.bfloat16, device_map="cuda")
prompt = "rio cat - superman, hyperrealism, no blur, 4 k resolution, ultra detailed, style of ivan shishkin, thomas kinkad, zdzisław beksinski"
image = pipe(prompt).images[0]DreamBooth model for the rio concept trained by marshmellow77 on the marshmellow77/pics_rio dataset.
This is a Stable Diffusion model v1-5 fine-tuned on the rio concept with DreamBooth. It can be used by modifying the instance_prompt: a photo of rio cat
This model was created as part of the DreamBooth Hackathon 🔥. Visit the organisation page for instructions on how to take part!
Description
This is a Stable Diffusion model v1-5 fine-tuned on cat images for the animal theme.
Usage
from diffusers import StableDiffusionPipeline
pipeline = StableDiffusionPipeline.from_pretrained('marshmellow77/rio-cat-sd-1-5')
image = pipeline().images[0]
image
- Downloads last month
- 2