Negative values will add sharpness/clarity while positive values will soften and stylize the image. While the examples bellow show values between -1 to 1, it is recommended to stick with -0.6 to 1.0
a
b
c
Downloads last month
-
Downloads are not tracked for this model. How to track
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("melmass/sdxl_loras", device_map="auto")