Stabilizer IL/NAI

Trained on a normal and natural dataset. For natural lighting, textures, details...

The dataset only has high resolution images. Zero AI image. So you can get texture and details beyond pixel level. Instead of a weird smooth feeling. FYI, all cover images directly come from a1111, no upscale, no inpainting. If you think they are, then this LoRA did its job well.

Recent updates:

(5/19/2025): Recommend to use illus version of this LoRA even if your base model is NoobAI.

Ironically, last time I update. I recommended to use NoobAI version, because I found, 95% base models are NoobAI.

Long story short, I grabbed a 5K dataset and did some big trainings last week, on illus and nbep. I noticed that nbep "refuse" to learn things, even if the training settings are identical. illus versions LoRA always had better effects on both illus and nbep model.

My assumption is that it is still the "overfitting" problem, the more a model trained from original SDXL, the more it forgets. Because I also tried to train on the new Illustrious 2.0, the result is: It is nearly un-trainable, much worse than NoobAi.

(5/19/2025): illus v1.152

The more the better. 5K more photographs. Still, contains everything, except human. More data, so more training steps, as a result, much stronger effect. But still quite stable on brightness and colors. .........