Verified: 2 years ago
SafeTensor
Type | |
Stats | 974 127 |
Reviews | (105) |
Published | Jul 25, 2023 |
Base Model | |
Training | Steps: 7,000 Epochs: 1 |
Usage Tips | Clip Skip: 1 |
Trigger Words | r4nd0m |
Hash | AutoV2 0DB2E76253 |
If you like what I do please consider supporting me on Patreon and contributing your ideas to my future projects!
This is a peculiar model. It was trained on 1,000 images of diverse types of art yet 99% of the time it generates landscapes. 1% of the time it will throw out something totally random. Spin the roulette wheel and see what you get!
I've tried clip skip 1-9 without much difference and a weight of 1 - 2.5 even up to 3 - 5 for abstract minimalist looking stuff.