An attempt to enable Pony, and now also IL, to generate more accurate helmets.
Trained on photos of various figures in dirt bike helmets with tinted goggles, male and female. This means the model isn't good for visible faces.
! V1 occasionally wants to create eyes within the reflection of the goggles when using prompts like "looking at viewer" and/or "facing forward". Adding "eyes covered, face covered" to the positive prompt and "eyes, anime eyes" to the negative can help. !