import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("0xahzam/biodiffusion", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]BioDiffusion Model 👾
Exploring the intersection of art and biology by fine-tuning diffusion models on datasets like david goodsell's work to generate sci-art that is unique but also really fascinating.
note: don't forget to add in the style of DavidGoodsell in the prompt
Some eye-blessing generated examples :)
- Downloads last month
- 41