This PR adds a model card for FiTv2, linking to the paper [FiTv2: Scalable and Improved Flexible Vision Transformer for Diffusion Model](https://huggingface.co/papers/2410.13925) and the official GitHub repository. It also adds the `pipeline_tag` (`unconditional-image-generation`) so the model can be discovered on the Hub.
Merge branch 'main' of https://huggingface.co/InfImagine/FiTv2 into main