README.md

---
license: apache-2.0
---

Pre-trained models and output samples of ControlNet-LLLite form bdsqlsz

Inference with ComfyUI: https://github.com/kohya-ss/ControlNet-LLLite-ComfyUI

For 1111's Web UI, [sd-webui-controlnet](https://github.com/Mikubill/sd-webui-controlnet) extension supports ControlNet-LLLite.

Training: https://github.com/kohya-ss/sd-scripts/blob/sdxl/docs/train_lllite_README.md

The recommended preprocessing for the animeface model is [Anime-Face-Segmentation](https://github.com/siyeong0/Anime-Face-Segmentation)

# Models

## Trained on anime model

AnimeFaceSegment、Normal、T2i-Color/Shuffle

Base Model use[Kohaku-XL](https://civitai.com/models/136389?modelVersionId=150441)

MLSD 

Base Model use[ProtoVision XL - High Fidelity 3D](https://civitai.com/models/125703?modelVersionId=144229)

# Samples

## AnimeFaceSegmentV1

![source 1](./sample/00000-1254802172.png) ![sample 1-1](./sample/00153-1415397694.png)

![sample 1-2](./sample/00155-541628598.png) ![sample 1-3](./sample/00156-3563138011.png)

![source 2](./sample/00013-1254802185.png) ![sample 2-1](./sample/00157-172216875.png)

![sample 2-2](./sample/00161-125697048.png) ![sample 2-3](./sample/00163-3802019239.png)

## AnimeFaceSegmentV2

![source 1](./sample/00015-882327104.png)

![sample 1](./sample/grid-0000-656896882.png)

![source 2](./sample/00081-882327170.png)

![sample 2](./sample/grid-0000-2857388239.png)

## MLSDV2

![source 1](./sample/0 (73).png)

![preprocess 1](./sample/00015-882327104.png)

![sample 1](./sample/grid-0000-656896882.png)

![source 2](./sample/00081-882327170.png)

![preprocess 2](./sample/00015-882327104.png)

![sample 2](./sample/grid-0000-2857388239.png)

## Normal

## T2i-Color/Shuffle