import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("Drawin/DDPM-Street-Scene-Repaint", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]Pretrain model for https://github.com/Draw1n/DDPM-Street-Scene-Repaint
iamge_size = (128x128), batch = 16, epoch = 250, 8 hours training
Put the model.bin and json into the ./output/
- Downloads last month
- 1
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support