NoobAI XL LoRA Iewa

This is a LoRA for the v1.1 version of the NoobAI XL model.

The dataset used to train this LoRA is scraped using LagPixelLOL/aisp, containing a total of 46 images.

Big thanks to the artist for the very cute style :3, you can find the artist on X (Twitter) with ID @iewaaaaaa.

To use this LoRA, you can use the trigger word iewa.

This LoRA is trained using kohya-ss/sd-scripts, with rank 32, alpha 16, learning rate 1e-4, for 512 epochs with a total of 5120 steps, using a H100, took approximately 3 hours.

If you have any questions, suggestions, or just want to talk to me, you can add me on Discord with ID @v2ray.