import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("RunDiffusion/Juggernaut-XL-v9", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("ApathyGhost/SynthModelGal_DMD2")
prompt = "-"
image = pipe(prompt).images[0]SynthGals
- Prompt
- -
Model description
Synthwave and Cyberpunk neon girlies. Bit janky, intend to have a V2 out that is much more user friendly. Start with standard-ish LCM/DMD2 settings and go from there.
With a DMD2 LORA, faces can be a bti janky without Face Restore
CFG - 1-2
Steps - 8
Sampler - LCM
Clip Skip - 2
Trigger words
You should use SynthModel to trigger the image generation.
Download model
Download them in the Files & versions tab.
- Downloads last month
- 24
Model tree for ApathyGhost/SynthModelGal_DMD2
Base model
stabilityai/stable-diffusion-xl-base-1.0 Finetuned
RunDiffusion/Juggernaut-XL-v9