A LORA model trained on 8 high-quality images of forsen

Optimal CFG Scale 3-6

Optimal Lora ranges: 0.85 - 1.22

Works best on vanilla SD1.5, but can also give decent results on other custom models.

To use this model In a1111 webui, download it, rename it to forsen.safetensors place it in models/lora and include <lora:forsen:1> anywhere in the prompt, where 1 can be any value in lora ranges mentioned above.

Click on the images to see the prompts used, if it doesn't work, turn off ublock or refresh the page. The trigger phrases are: a man with a beard, a man in a jacket. The sample images were cherry picked.