Wheelchair Users for SDXL

This is a LoRA for SDXL focusing on wheelchairs and people using them. Actually, it is an output from one of my abandoned projects. Please don't expect too much :) and handle with care.

Please feel free to improve it if you are interested in it. (Or just ignore this and grab another.)

Features of the training dataset

It consisted of:

• about 200 photos of one person who is on their wheelchair, containing less than 30 mature shots (nudes or underwears, no porns),

• about 50 photos of groups of people with one, some, or all of them in wheelcharis, and

• about 20 photos of an unattended wheelchair.

It contained usual traditional wheelcharis only. That is:

• specialized wheelchairs, such as for basketball or racing, were not included.

• about 90% were manual wheelchairs and 10% were manual-electric hybrids with two large wheels.

• Motorized wheelchairs with small driving wheels were not included.

All samples were photos. No illustrations, 3D graphics, or anime were included.

Known issues

• Wheelchairs often look strange. I believe it's better than the vanilla SDXL 1.0, but I consider it is still far from acceptable. You have been warned.

• I have a feeling (though not sure on this point) that varieties of human this model can infer are too limited. If you generate 10 pictures by a same prompt, for example, you will often find two images showing a very similar person. Perhaps an overfitting.

• ... and many more.

Acknowledgment

@asantiagowow655: Thank you for pushing me to post this model.