RDBT | MOSS

RDBT | MOSS

Finetuned LoRA from a personal all-in-one dataset, mainly for digital art and drawings, focusing on lighting, textures. Covered from wallpaper level digital art, to 5-min sketch

LoRA is trained against MOSS base (not sft). Cover images are also from MOSS base. It works on SFT, but you might need to lower the strength.

Dataset contains ~2k images (latest version), handpicked by professional amateur artists. The criteria for evaluation are not visual appeal, but the drawing technique and the level of completion.

There is no trigger words or style tags. All images are captioned by LLM. I'm too lazy to classify them. (Most of the style can't be classified in just few words tbh. It's hard to describe art.). So I used high caption drop rate hoping the model can guide itself from it's high noise steps.

Versions:

v0.1:

Same dataset as Anima v3.0. This is a test run.

If you are from Anima, note that MOSS (especially the base version) does not have strong @style trigger words. Without strong style guidance, styles from my dataset seem to be messed up all together, drawing + painting + digital art.... I might need to change the way to caption, or just train dedicated LoRAs.

But it still works as usual if you have strong style trigger words, like on this finetuned model, or with style LoRAs. https://civitai.red/images/146568174

For now I recommend to use it as a "regulator/stabilizer/detailer/whatever" LoRA with strength (0.2~0.5). It might alleviate the overfitting from other style LoRAs.

Or higher strength if you want some spicy visual effects. (Usually I use it at full strength with my other style LoRAs)

Sharing merges using this model is not allowed. This "restriction" won't affect anyone. It's only aimed at those who steal others' models to sell.