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This is an archived page.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.
FAQ
Comments (8)
thanks！
can you make one for older chubby daddies? :D
Just want to let you guys know if you haven't check it out yet: there's an updated LoCon version of Husbando LoRA -- Husbando LoCon
What if I want to use it with realistic model
Which one better?
how do i use the ai generator?
Are you new to stable diffusion? If so, you should learn how to use Automatic1111 web UI first. If you don't know how to use LoRAs/LoCons, see https://github.com/civitai/civitai/wiki/How-to-use-models#lora. Note that LoRAs/LoCons are supposed to use on other stable diffusion checkpoints, and for my Husbando LoRA/LoCon, it's recommended to try it on Anything v4.5: anything-v4.5-pruned.safetensors · andite/anything-v4.0 at main (huggingface.co)
@Koolchh Sir, link to anything 4.5 error
Don't take offense, because it's a common place terminology, but how is any of this 'Safe For Work'? :D What kind of work do you people do?