import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("verkaDerkaDerk/tiki-64", 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 an unconditioned diffusion model trained on around 500 miscellaneous tiki images from around the web.
The resolution is 64x64.
It was trained for around 4k epochs with a loss around 1.5%.
- Downloads last month
- 3
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support