Add model card

This PR adds a model card for FiTv2, linking it to the paper [FiTv2: Scalable and Improved Flexible Vision Transformer for Diffusion Model](https://huggingface.co/papers/2410.13925) and the official code repository. It also adds the appropriate `pipeline_tag` for unconditional image generation so the model is discoverable on the Hub.

README.md

@@ -0,0 +1,9 @@
+---
+pipeline_tag: unconditional-image-generation
+---
+
+# FiTv2: Scalable and Improved Flexible Vision Transformer for Diffusion Model
+
+This repository contains the FiTv2 model described in [FiTv2: Scalable and Improved Flexible Vision Transformer for Diffusion Model](https://huggingface.co/papers/2410.13925). FiTv2 is a flexible vision transformer for diffusion models that generates images at unrestricted resolutions and aspect ratios. It builds on FiT with innovations such as Query-Key vector normalization, AdaLN-LoRA, a rectified flow scheduler, and a Logit-Normal sampler.
+
+The official code and sampling scripts are available at [https://github.com/whlzy/FiT](https://github.com/whlzy/FiT).