Updated: Nov 30, 2023
base modelVerified: 2 years ago
SafeTensor
This Stability AI Model is licensed under the Stability AI Non-Commercial Research Community License, Copyright (c) Stability AI Ltd. All Rights Reserved.
This is my Realistic focused SDXL Model merged with the new SDXL Turbo for super fast generations at a slightly lower quality.
It can generate a 768x768 image at 5 steps in 1.7 Seconds on my RTX 3090.
IMPORTANT.
I have found these settings best in my testing in Automatic1111:
Sampling Method: Euler a
Initial image resolution: 768x768
Number of steps: 5
CFG: 1
Img2Img Upscaling settings:
Sampling Method: DPM++ 3M SDE
image resolution: Resize by 2.4x (1843x1843)
Steps: 7
Denoising strength: 0.15
Note: That Img2Img the num_of_steps * Denoising Strength has to be equal or larger to 1. ie 0.15 x 7 = 1.05 or else you will get errors. "UnboundLocalError: local variable 'h' referenced before assignment"