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.
Upload FiTv1_xl/model_ema.bin with huggingface_hub
