import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("jice2/CreaPrompt_Ultimate6", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]It is an SDXL 1.0 merged model oriented towards realism, but it is also capable of creating all styles of images.
It also integrates the lora Hyper-CFG-8-Steps for accelerated rendering times.
Recommended settings:
Sampler: Euler/uniform
Steps: 8 to 14
CFG: 2 to 3.5
- Downloads last month
- 50