import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("LandonAbundre/SCGAnatomy")
prompt = "-"
image = pipe(prompt).images[0]SCGAnatomy
- Prompt
- -
Model description
I'm finding that you get best results using this lora in the 0.65 to 1.2 model strength range (leaving clip strength at 1.0). keep your guidance at 3.0 and CFG at 1.0, any more than that and it will fry and get bad looking really fast. I use DEIS and ddim_uniform at 25 steps
Trigger words
You should use scg-anatomy-female to trigger the image generation.
Download model
Download them in the Files & versions tab.
- Downloads last month
- 27
Model tree for LandonAbundre/SCGAnatomy
Base model
black-forest-labs/FLUX.1-dev