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"
Description
First Merge with SDXL Turbo.
FAQ
Comments (1)
I made some grids of all currently uploaded turbo models. all but the base model and jib's need atleast 3 steps for a decent image, and anything over config 2 tends to be either very cartoony or blurry/other artifacts. also almost no difference between 1 step and 2 steps.
(step check 1-4, cfg1)https://civitai.com/posts/929205
(cfg check, 4steps)https://civitai.com/posts/929178
(same model order as pervious grids, cfg 1 steps 3) https://civitai.com/posts/929237
Looks like we don't have an active mirror for this file right now.
CivArchive is a community-maintained index — we catalog mirrors that volunteers upload to HuggingFace, torrents, and other public hosts. Looks like no one has uploaded a copy of this file yet.
Some files do get recovered over time through contributions. If you're looking for this one, feel free to ask in Discord, or help preserve it if you have a copy.