Download
1 variant available
1,4800 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
(197)
May 5, 2023
SD 1.5
This new version is based in LoHa training, that give me a better results than the LoRa.
Use the loha tag at 1 of weight. (If u use a realistic model, could help increase the stregth of the trigger word at 1.1 or 1.2
<lora:roundglasses_v3:1>
As extra, was trained in the tag "cum on glasses", you could trigger it using:
cum, (cum on glasses:1.1)
Show more

1.7K0 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9K
16.4K0 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
Round Glasses Lora
This is my very first lora, was trained with 15 images and 1600 steps. I tried with multiple configs and images, trying to get a small size and a roundness glasses, but at final this one was the best.
Read the notes of each version to see the usage notes.
Note:
V1 is a LoRa
V2 is a LoHa

