import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("anshudaur/cat_model_small_lr", dtype=torch.bfloat16, device_map="cuda")
prompt = "photo of a <new1> cat"
image = pipe(prompt).images[0]Custom Diffusion - anshudaur/cat_model_small_lr
These are Custom Diffusion adaption weights for CompVis/stable-diffusion-v1-4. The weights were trained on photo of a cat using Custom Diffusion. You can find some example images in the following.
For more details on the training, please follow this link.
- Downloads last month
- 2
Model tree for anshudaur/cat_model_small_lr
Base model
CompVis/stable-diffusion-v1-4