pip install -U diffusers transformers accelerate
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("MidnightRunner/manuka_fudge", dtype=torch.bfloat16, device_map="cuda")
prompt = "male, 1male, aesthetic, realistic, realism, strength, assertiveness, competitiveness, masterpiece, best quality, ultra-detailed, ((solo)), nature, (stars, crescent moon), (full body photo:1.3), (colorful background:1.2), spotlight backlit, psychedelic backdrop, realist detail, standing"
image = pipe(prompt).images[0]Mānuka Fudge - Base Model
Model description
This checkpoint went through three versions itself with a few merges. This is the fourth version.
Sampling method:
- DPM++ 2M Karras
- DPM++ 2M SDE Karras
Sampling Steps: 25-45 CFG Scale: 7 Clip Skip: 2
Recommended Upscaler Settings:
- Hires. fix Upscaler
- 4x-UltraSharp
Hires steps: 10-20 Hires upscale: 1.5-2 Denoising strength: ~ 0.3-0.5
For better results use Hires.fix for better Results! Use ADetailer for a better face with lora:Pear_v1:0.8!
- Downloads last month
- -
Model tree for MidnightRunner/manuka_fudge
Base model
runwayml/stable-diffusion-v1-5
# Gated model: Login with a HF token with gated access permission hf auth login