import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("Strike1999/GeoDiffusion_512x512_GDCC", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]GDCC-Generation Model Card
GDCC is a detection data generation model fine-tuned from GeoDiffusion. This repo contains the GDCC checkpoint trained on COCO-stuff dataset under 512x512. Check detailed usage in our Github repo.
- Downloads last month
- -