Training on "black sclera".
I have been working to integrate various unique features into LoRa's (and now LoCon). I have found making individual trainings on each feature, then merging the ones needed together gets remarkable results.
Eyes are hard to get right, this helps but isn't a perfect solution yet though.
This has been trained on about 80 AI generated images from various models (picked out from hundreds), after using a couple not so great lora's I had experimented with before.
This can be used stand-alone to add black sclera with much higher efficiency, or mixed with other LoRA / LoCon to mix the feature in. I recommend to avoid using this with multiple other LoRA / LoCon without mixing first, it is more prone to cause issues.
If you like this, get me a coffee :D
Description
Seems to get better results than v1, however, still has some bias issues I will need to work out in the next version.
This has been trained on 80 images of black sclera, rather than the previous 40 in v1, also with many tweaks to the training process.
Has an easier time getting results in other models, though, but prefers face close-ups, and fails quite often if there is too much distance.
I will continue tweaking and any feedback is appreciated. Black Sclera is a tough feature to work with.