[Concept version]I noticed that some checkpoints have trouble with glasses, like rims fading into nothingness and etc. So this is my first LoRA that I botched up in 1 hour and trained for 20 minutes on like 15 images. Nothing groundbreaking, but this first concept version works (For Aviators).Trained on: SXZ-Luma modelRecommended model: DarkSushiMixRecommended weight: 0.4 - 0.8Useful trigger words: aviators, sunglasses, reflection, tintedRecommendations: Use low GFG scale (5.5), use more Steps (40-50), trained only on 512x512 images, so higher resolution is a bit wonky at higher weights.Enjoy prompting!

Files with SHA256: 08e8be88383f6c0f9c40e911fa1beff21f56606fa43e7a7446e07260a4f77232