---
license: apache-2.0
pipeline_tag: unconditional-image-generation
---

# FiTv2: Scalable and Improved Flexible Vision Transformer for Diffusion Model

This repository contains the FiTv2 model introduced in [FiTv2: Scalable and Improved Flexible Vision Transformer for Diffusion Model](https://huggingface.co/papers/2410.13925).

It is a diffusion transformer designed for generating images at unrestricted resolutions and aspect ratios.

For code, checkpoints, and sampling instructions, please refer to the [GitHub repository](https://github.com/whlzy/FiT).