Type | |
Stats | 1,301 |
Reviews | (193) |
Published | Jul 14, 2023 |
Base Model | |
Training | Epochs: 44 |
Trigger Words | strongbana |
Hash | AutoV2 473ADE301E |
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.๐
You can also buy me a Coffee โ 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
Checkpoint used in examples:
model.ckpt ยท a1079602570/animefull-final-pruned at main (huggingface.co)
About the artist:
Twitter: Strongbana๐๐ (@strongbana) / Twitter
Patreon: StrongBana | Creating comics and NSFW art | Patreon
Strongbana creates nsfw art and comics, largely using characters from different video games, with league of legends making up a large part. The style is cartoony with exaggerated proportions and a general shine and flatness of colors.
Weights & Prompts
Lycoris:
This should be your goto model for most checkpoints, allowing for more flexibility.
Use a weight of 0.7-1.0, adjust to taste. For reference check the XYZ plot in the examples.
Different checkpoints tend to work best with a weight around 0.7. Higher weights can result in incredibly noisy images.
LoRA:
I recommend a weight of 1.0 or slightly lower. For character lora with their own artstyle try 0.7.
This model was trained almost exclusively with nsfw images. When not prompted otherwise the LoRA in particular has a strong bias towards big-breasted and nude women.
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! ๐