Version 2.0 update: after I connected the grid pattern sometimes visible in bright or dark parts of the images with the fp4 training with OneTrainer, I switched to fp8 training, which got rid of the pattern. But I have to redo all my LoRAs to fix them all and I did some minor corrections on the dataset. Nothing changed in usage, except the tag is now &lt;lora:WireframeGlasses-SmallOval-step0960:1&gt;<hr />Flux seems pretty limited if you want glasses - mostly the more round sort with a thicker frame. I intended to make a all-in-one LoRA first, but that didn't work - if you want to specify between normal and small glasses, round, rectangular and oval shapes you had to train each one separately.This creates small oval wire-frame glasses - to acquire my dataset, I had to make some kind of internet archaeology, going back in the late 2000's when those were in vogue for a small period of time.Albeit not strictly neccessary, a &lt;lora:WireframeGlasses-ovalSmall-80:1&gt; tag increases the influence. It has also the potential of creating several colors, like the pink one in the example set.

Wire-frame glasses - small oval

Version 2.0 is trained with fp8, getting rid of the grid pattern sometimes visible in the images. The dataset was cleaned up to just the real small ones.

Files with SHA256: 41afc10d1639b89e0564359bf48adf19c7ab26baba055566e423299d996685ea