---
license: mit
language:
- en
base_model:
- Laxhar/sdxl_noob
pipeline_tag: text-to-image
tags:
- art
datasets:
- v2ray/mike-no-hito
library_name: peft
---
# NoobAI XL LoRA Mike No Hito
This is a LoRA for the [v0.5 version of the NoobAI XL model](https://civitai.com/models/833294?modelVersionId=968495), the v1.0 and v0.75 is actually worse than the v0.5 version thus this LoRA isn't trained for those 2 newer versions. Please use the older v0.5 version for the optimal experience.

The dataset [v2ray/mike-no-hito](https://huggingface.co/datasets/v2ray/mike-no-hito) used to train this LoRA is scraped using [LagPixelLOL/mitgw](https://github.com/LagPixelLOL/mitgw), containing a total of 172 images.

Big thanks to the artist for the very cute catgirls :3, you can find the artist on X (Twitter) with ID [@doremifaso64](https://x.com/doremifaso64).

To use this LoRA, you can use the trigger word `mike no hito`, it's best to add `black eyes` and `white pupils` too for better eye performance. The artist is a furry artist so this will have a chance to make a character into a furry unprompted, if you encounter this, simply add `furry` to the negative prompt.

This LoRA is trained using [kohya-ss/sd-scripts](https://github.com/kohya-ss/sd-scripts), with rank 8, alpha 16, learning rate 1e-4, for 128 epochs with a total of 2432 steps, using a H100, took approximately 2 hours.

## Changelog
- **v2.1**: This version is trained with 3x3 Conv2d layers targeted, for 128 epochs (64 more epochs compared to v2.0).
- **v2.0**: This version added a lot more training data, which are hand picked, cleaned, and deduped by me, mostly by hand. It has improved non-furry ability thanks to generalization, and overall better quality.

## Examples
![](https://huggingface.co/v2ray/nai-lora-mike-no-hito/resolve/main/examples/0.avif)
![](https://huggingface.co/v2ray/nai-lora-mike-no-hito/resolve/main/examples/1.avif)
![](https://huggingface.co/v2ray/nai-lora-mike-no-hito/resolve/main/examples/2.avif)