import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("speach1sdef178/Project0_PJ0_Krea_v3_FP8_FP16", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]Project0_PJ0_Krea_v3_FP8_FP16
Updated version with improved realism and details.
Recommended samplers: Euler/Simple and 20-30 steps
Examples
License
Base model: FLUX.1-dev by Black Forest Labs
- Downloads last month
- 3