---
license: mit

language:
- en
pipeline_tag: "image-segmentation, text-to-image, image-to-image, image-to-video, unconditional-image-generation, depth-estimation, zero-shot-object-detection"
library_name: oneformer, depth-anything-v2, erika, ControlNetHED, diffusion
tags:
- depth
- relative depth

---

# ControlNet preprocessor sets

## Introduction
This collection includes the most practical Stable Diffusion preprocessor (annotator) models, along with other valuable types of models.
I'll categorize them concisely and organize them into subfolders or a similar structure.
You can integrate these models into your auxiliary tools, and the directory structure will be approximately as follows:

![image/png](https://cdn-uploads.huggingface.co/production/uploads/6651b9ff61422fc89770c998/205NNxmoKUdsvxyh2IRj-.png)


## Installation

```bash
git clone https://huggingface.co/Cyber-BCat/ControlNet-Preprocessors_Annotators
```