import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("TheBirdLegacy/OSD-Model", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]This model was finetuned on the OSD dataset. It uses Stable Diffusion V2.1-Base as a foundation model. This is also entered into the Dreambooth Hackathon. The prompt prompt is as followed Words + |Timestamp| Eg. A dog |10-21T10:10|
- Downloads last month
- 4