Female SAK amputee with forearm crutches.

As with all my models, it's all experimental. I have found a strength of 0.8-1.0 is best with a cfg of 1.0-1.2

It does not have a trigger word but has been trained with a few similar descriptions for each image, depending on what I want.

"left above knee single leg amputee"

"right above knee single leg amputee"

"her residual limb is visible"

"her residual limb is not visible"

"her residual limb is covered by her skirt"

"her residual limb is covered by her pants"

"walking with Forearm crutches"

"stood with forearm crutches"

it works okay but isn't perfect. I also find with Moss Image that even using random seeds the images do not change much unless the prompt is much different. It sometimes works better without a prompt enhancer, it's a lot of trial and error.

My images here also uses 8-step-dmd2-lora and moss_image_sft loras

As usual I would love to see how you use it.