Crying-LoRA for SDXL

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

The LoRA allows people to cry in SDXL. From simple tears to crying fits, it allows control over facial expressions from a bit sad to filled with pain. Tears and facial expression can be influenced largely independently of each other. As an addition there is the possibility of tears smeared makeup and bloody tears. And this can also be combined.

The LoRA is very flexible and can be applied to both men and women. And also some fable characters ;)

It was trained with 17 prompts and over 1200 images and can be used with many styles.

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.

Since the refiner sometimes affects the image content, it is deactivated in some of the example images. Any form of facial enhancement could also cause problems and should be switched off in this case.

The model does not always produce perfect images. But it does produce a fair share of great images. And since the image generation in SDXL does not take long, you can live with the waste or use inpainting and other techniques to repair the imperfections. It also seems to depend heavily on the theme and style whether the model can handle it or not. Therefore, 4 differently trained versions are included. It always depends on the scene, models used, trigger words, etc. which LoRA is most suitable. So you can try and choose for yourself.

In addition, the readme file contains 18 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"