import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("Kumar-kun/kuman-generator", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]Kuman-generator Dreambooth model trained by Kumar-kun with buildspace's DreamBooth notebook
Build your own using the AI Avatar project!
To get started head over to the project dashboard.
Sample pictures of this concept:
- Downloads last month
- 5