Add model card

This PR improves the model card, by:

- adding a link to the paper
- adding a relevant `pipeline_tag`, ensuring people can find the model at https://huggingface.co/models?pipeline_tag=image-text-to-text&sort=trending
- adding a relevant `library_name`, ensuring the "how to use" button appears

README.md

@@ -0,0 +1,15 @@
+---
+library_name: diffusers
+pipeline_tag: image-text-to-text
+---
+
+This repository contains the model described in the paper [Show-o Turbo: Towards Accelerated Unified Multimodal Understanding and Generation](https://arxiv.org/abs/2502.05415).
+
+To get started with the 512-resolution model:
+```bash
+sh inference_t2i_512.sh
+```
+To get started with the 256-resolution model:
+```bash
+sh inference_t2i_256.sh
+```