Fluxster/Glasses LoRA
[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 model Recommended model: DarkSushiMix Recommended weight: 0.4 - 0.8 Useful trigger words: aviators, sunglasses, reflection, tinted Recommendations: 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.
| Author / organization | Fluxster |
|---|---|
| Downloads | 4K (as reported by Civitai) |
| Likes | 518 |
| Task | text-to-image |
| Created | 24 May 2023 |
| Last updated at source | — |
Silytics shows public metadata from Civitai and links to the original. Information may be incomplete or out of date. Last refreshed 15 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.