---
pipeline_tag: text-to-image
library_name: diffusers
license: mit
---

# Model

This repo contains the full fine-tuned model of the paper [TextDiffuser-2: Unleashing the Power of Language Models for Text Rendering](https://huggingface.co/papers/2311.16465).

# Usage

The script [here](https://github.com/microsoft/unilm/tree/master/textdiffuser-2#firecracker-inference) can be used to perform inference with the model.