Garrote-LoRA-V1 for SDXL

A LoRA model as an extension for Stable Diffusion XL (SDXL)

The LoRA creates images of people strapped to a garrote in various stages of execution. It allows both genders and many different image styles and also full body shots and specific angles.

The mechanics of a garrote are very difficult for the AI to reproduce accurately. In most images, there will be some element of the image that is not accurate. It depends a lot on the style used. Experimenting around with the weighting and the different LoRAs included can change a lot. The image composition, poses, etc. are often very good, details of the mechanics may need post processing with inpainting or in other image processing software. Do not expect perfect images.

The promo images are all unedited images directly from the AI

It was trained with about 400 images and 29 tags and can be used with many styles.

The package contains 4 LoRA

Version 1.0 is the version I consider most suitable and flexible.

The other versions are less (0.8 & 0.9) and higher (1.1) trained and behave in many cases accordingly different. In certain situations these might be the better choice, which is why they are included in the package.

Of course you need Stable Diffusion XL and one of the many user interfaces to use it. A small description is included.

All product images are unedited and were created using the SDXL base model and the Fooocus user interface.

In addition, the readme file contains 8 example prompts, which were also used to create the promo images, these are intended as a starting point.

the password for the zip files is always "Frotz"