Niji soft style XL (furry focused)

This Lora is made for a semi-realistic Niji style with high detail and textured fur
The dataset is mostly furry art, but it handles humans just fine too

It’s my first LoRA, so it might be unstable, though the dataset I used is pretty solid overall

V2.5 key changes:

• The dataset has been expanded 2.5× compared to v2.

• Improved generation stability and higher flexibility (thanks to the new dataset, v2 was a bit overfitted).

• Around 50% of the dataset consists of humans and backgrounds, the rest is furry content.

V2 Key Changes:

• The dataset has become more diverse.

• The dataset now consists of approximately 40% humans, 60% furry.

• The style has become more stable, but I recommend using this LoRA with other niji LoRAs for better results (see Suggested Resources).

Works well with Euler a + Exponential/Karras.

For stable results, strength 0.8 is recommended

Tensor.art_link

for V1: If you want softer shades and "fluffy fur", based on my experience, it's best to use NoobAI V-pred models (example - the 3rd image in the post)