note that both the lora name and the lora trigger word are romero not romano. If I make a v2 i will fix this.
2000 steps, 48 training images, 15 repeats
bf16
Base model: runwayml/stable-diffusion-v1-5
Optimizer: Adafactor
Learning Rate: .0001
TE LR: .00005
Unet LR: .0001
Network dim & alpha: 91