Type | |
Stats | 209 61 |
Reviews | (53) |
Published | Mar 12, 2024 |
Base Model | |
Training | Epochs: 49 |
Usage Tips | Clip Skip: 2 Strength: 1 |
Trigger Words | furiouzly |
Hash | AutoV2 10B9CE3BB7 |
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.π
This model was trained using the collab/guide by holostrawberry [Guide] Make your own Loras, easy and free - colabs | Stable Diffusion Other | Civitai
Checkpoint tained on and used in examples:
model.ckpt Β· a1079602570/animefull-final-pruned at main (huggingface.co)
If you want optimal results and don't want to experiment combining styles, use this base model!
It is old but gold, and allows for model training that gets a lot closer to the original, compared to tons of other often used models like AnyLoRA. Otherwise I recommend using simple anime style checkpoints.
I am once again open for suggestions for other styles, SFW and NSFW.
You can always drop model suggestions in the comments, both for styles that are missing on civit or those that are outdated. No guarantees but if it interests me I'll give it a go.
About the artist:
Patreon: Furiouzly | creating mangas/comics with some sexy 18+ contents | Patreon
Twitter: Furiouzly (@Furiouzly1) / X (twitter.com)
Furiouzly creates not just nsfw fanart but also draws and writes an original manga "I sold my body to a god" (which has a lot of additional nsfw content/chapter pages)
I SOLD MY BODY TO A GOD | MANGA Plus Creators by SHUEISHA (medibang.com)
Their gorgeous artstyle leans more into realism and is pretty character centric, mostly drawing in black and white but also making a good amount of fully colorized artworks.
Drop them a follow or maybe subscribe to their patreon! As good as the model might be, the original is still a lot better. The art doesn't make the story after all.
Weights & Prompts
The activation prompt is:
furiouzly
There were enough images of Charona in the dataset to replicate her quite well. Check the first example image for inspiration.
The training data contains a lot of sex acts so quite a few should work without additional LoRA. It can be used at full strength with lightweight character LoRA.
Use a weight of 0.7-1.2, adjust to taste and depending on your checkpoint.
As usual I have included an XYZ plot for reference.
Please leave a review if you enjoyed this model or have problems with it. This helps me with improving future models and finetuning them in general. Give it a try and throw some images down below! π