import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("pimentooliver/fungi-sd-diffusion", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]This is a fine-tune of CompVis/stable-diffusion-v1-4. It has been fine tuned on a dataset of fungi imagery which has been clustered to represent 'species'. Each 'species' has been assigned a generated name in an attempt to fine-tune the model on nonexistent fungal species. Unfortunately, this model has been impacted by catastrophic forgetting. It will be retrained soon, upload only for academic use.
- Downloads last month
- 2