import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("Blib-la/sd-turbo-fp16", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]SD-Turbo (fp16)
This is a fork from stabilityai/sd-turbo. We just removed a few files to have a fp16-only version, the license from Stability AI still applies.
We use this model in Captain.
- Downloads last month
- 28