
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.?
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:
This artist creates very nsfw content. Fuya has a penchant for very large breasts and a generally thicc body type. The model was almost exclusively trained on newer images with minimal SFW content included and therefore excells at prompts along those lines in particular.
Twitter: FUYA?PATREON (@fuyafuyu) /Twitter
Gumroad: Fuya (gumroad.com)
Pixiv: FUYA - pixiv
Weights & Prompts
The only necessary prompt is
Fuya
Note that any other checkpoint affects the effectiveness of this model. The same goes for most character LoRA that weren't trained well enough.
NAI:
This should be your goto version with most checkpoints.
Use a weight of 1.0, adjust to taste.
AOM3:
Use a weight of 1.0, adjust to taste. As usual I have included an XYZ plot for reference.
Lightweight character models can be used at the same or higher weight (I tried up to 1.3) but, in my experience, are a bit more likely to have deformed hands.
For inspiration check the examples. I recommend heavily 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.
(Backgrounds and objects in general are barely affected in this model.)
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! ?
描述:
115 images, 3 repetitions, unet_lr: 3e-4, 3 images per batch
训练词语: Fuya
名称: Fuya-18.safetensors
大小 (KB): 16570
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success