Download
1 variant available
fp16 PickleTensor
startrek_uniform_lora_5000.pt
Half precision, best balance • 144.33 MB
Verified: 3 years ago
This asset is only available as a PickleTensor which is a deprecated and insecure format. We caution against using this asset until it can be converted to the modern SafeTensor format.
2,1930 1 2 3 4 5 6 7 8 9,0 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
3460 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
590 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
(179)
Feb 19, 2023
SD 1.5

4.9K0 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9K
62.1K0 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9K

LORA for Star Trek uniforms. It responds to colors (so you can get red, blue, yellow, or any other color) but since it was trained on a variety of uniforms sometimes we will get a combination previously not seen in the shows/movies.
You can put colors in the prompt as well as in the negatives.
Tested on various models, also works on anime (although I'm bad with anime generations, someone could try to play with it and show us nicer results :P)
The trigger is strtrk uniform and it works well in someone wearing a strtrk uniform but other usages seem to work fine too.
As per usual, you can decrease or increase the LORA's strength. When I was playing with it I noticed that different models may want higher values than others (it also depends if you are mixing LORAs together).
But for typical generations, I was using strength between 1.1 and 1.35
If you want to see more examples, here is an Imgur gallery: https://imgur.com/a/7whYoPE
