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 ☕ .
Husbando LoCon is a LyCORIS for creating bara/yaoi hentai and sexually suggestive males.
🚀 Please also check out Selai Mix, my recent checkpoint merge model release, if you love the aesthetics of Husbando LoCon!
Features
Easy to create good-looking masculine characters using tag-based prompts.
Good male genitalia.
Good solo / solo focus homoerotic content.
Bara/yaoi hentai depicting 2 or more people are highly erroneous. You'll need luck and careful prompting to get things right.
Recommended Settings (v4)
CLIP skip: 2
You can start by trying a weight of 0.5 with CFG scale 7.
For hentai art, I recommend LoRA weight of 1.0 with CFG scale 9.
Since Selai Mix already contains Husbando LoCon v4.0, a lighter weight such as 0.3 should already give you the desired effect. You should not set the weight to over 0.7 when using on Selai Mix.
How to use
Select any checkpoint that works with tag-based prompts. Recommended models: Selai Mix and AnyLoRA.
Select a VAE if the checkpoint model you're using doesn't have a baked-in VAE, or else you'll find your generated images have dull colors. Recommended VAEs: blessed2, vae-ft-mse-840000-ema-pruned or kl-f8-anime2.
Make sure to follow the steps in How to use a LoRA.
Generate at 512 base resolution (512x768, 512x512 or 768x512) and use hires fix to improve the details. Recommended upscaler: R-ESRGAN 4x+ Anime6B; denoising strength: 0.4.
Description
Trained on 2182 mostly NSFW bara/yaoi images. Images are tagged with wd-v1-4-swinv2-tagger-v2.
FAQ
Comments (3)
Really looking forward to playing with this. I already loved the Husbando LoRA quite a lot, and rely on it for accurate cocks, instead of others made specifically for that purpose. Your examples are outstanding.
My only concern is that this is 594mb. 😱 Aren't LoCons/LoHas/Lycorises generally smaller than LoRAs? That was my understanding anyway.
Nah, LoCons are about 2 times the size of LoRAs with the same dimension. I chose the LoCon’s dimension to be 256 (same as v3) and the file size doubled. 😅 I will experiment on a lower dimension to address the overfitting issue. I'm glad you enjoy my work!
@Koolchh Ahh, okay. I guess the ones that I had looked at before, the creator had reduced the dimension when moving from LoRA to LoCon.
And I do enjoy your work quite a lot. I'll put this on a fast track to try to review sooner rather than later.
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.






