import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("siliconflow/stable-diffusion-v1-5-onediff-deepcache-int8", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]license: apache-2.0
Stable Diffusion v1.5 + OneDiff Quant + DeepCache
This is the SD-v1-5-onediff-deepcache-int8 model required for OneDiff Enterprise, for more details and running instructions, please refer to onediff.
- Downloads last month
- 1