Type | |
Stats | 794 |
Reviews | (119) |
Published | Jul 11, 2023 |
Base Model | |
Training | Epochs: 31 |
Trigger Words | snegovski |
Hash | AutoV2 BDCC366E9A |
If you enjoyed this model, why don't you check out my other works? I put a lot of effort into correctly recreating artist styles and making the occasional character LoRA.😊
You can also buy me a Coffee ☕ at https://ko-fi.com/stickyricky
This model was trained using the collab/guide by holostrawberry [Guide] Make your own Loras, easy and free - colabs | Stable Diffusion Other | Civitai
About the artist:
Twitter: 🐍SNEGOVSKI (@Snegovski9623) / Twitter
Patreon: Snegovski | Creating Arts and web comics | Patreon
Snegovski creates nsfw images, largely with characters from different games and anime.
They are also currently working on an incredible doujinshi 🥵
Zelda's Double Date Porn comic, Cartoon porn comics, Rule 34 comic (multporn.net)
Weights & Prompts
For inspiration check the examples. I heavily recommend experimenting with the steps as well. Sometimes a 12 step image is just what you want, sometimes it takes 30 to get the necessary detail.
NAI v1:
This should be your goto model. Use a weight of 0.9-1.0, adjust to taste. Check the XYZ plot in the examples.
It is still a bit volatile sometimes massively changing the image layout with different weights and especially struggles with dark skin and hair colors at lower simulation steps and prompt weights.
AOM v2:
Version 2 is a lot more consistent than V1. Most of the examples are redos of the original examples without cherrypicking the best results.
A weight of 0.9-1.0 works best in my opinion, with lower weights around 0.6-0.8 when used with other LoRA.
I'll still need to do some more testing. Right now for nsfw prompts using V1 at lower weights could be better.
AOM v1:
While snegovski mostly makes porn comics I also quite enjoyed how this lora pans out with landscapes.
A weight of 1 works when used by itself. At 0.6-0.8 it is compatible with most character lora.
Please leave a review if you enjoyed this model or have problems with it. I'd also be interested in how the model behaves with other base checkpoints, so why don't you give it a try and throw some images down below! 👇