Download
1 variant available
Stats
360 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
5480 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
2200 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
Reviews
(3)
Published
Jan 9, 2025
Base Model
Training
Steps: 2,400
Epochs: 20
Usage Tips
Clip Skip: 1
Strength: 1
Hash
AutoV2
056A8FE07D

5400 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
1.9K0 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9K

Created on Civitai
This model was trained on 48 of my old (over 20 years) digital photographs. Unlike usual training methods, I only tagged minor details or general characteristics of each image, not the primary subjects, and then trained it heavily to hopefully get lots of associative bleed over. Generated images should be generally realistic with occasional unrecognizable or surreal elements, but it's relatively subtle.

