---
license: apache-2.0
language: en
tags:
- computer-vision
- image-reconstruction
- vector-quantization
- tokenizer
- multimodal
library_name: transformers
pipeline_tag: image-to-image
---

# UniTok Transformers

**Key Features:**
- 📦 **Transformers Compatible**: Standard `from_pretrained()` and `save_pretrained()` support

For more details, visit: https://github.com/XuejiFang/UniTok_transformers

## Disclaimer

This is an unofficial implementation with Hugging Face integration. Original work: [FoundationVision/UniTok](https://github.com/FoundationVision/UniTok)