It takes substantial time and efforts to bake models. If you appreciate my models, I would be grateful if you could support me on Ko-fi ☕ .
This is an archived page. Please check out Husbando LoCon and Selai Mix -- The succeeding versions of this asset.
Description
More diverse training set; doubled network dimension; trained at 768 resolution. Better anatomy and composition than v2.
Trained on 2267 mostly NSFW bara/yaoi images. Images are tagged with wd-v1-4-swinv2-tagger-v2.