Leffa

Leffa is a unified framework for controllable person image generation, enabling precise manipulation of both appearance and pose. It is designed for researchers and developers who need to generate high-quality person images with specific attributes. Leffa achieves state-of-the-art performance in controlling appearance and pose, significantly reducing fine-grained detail distortion while maintaining high image quality. Leffa's code is based on Diffusers and Transformers, and it uses SCHP and DensePose to generate masks and densepose in its demo. The framework is particularly useful for applications such as virtual try-on and pose transfer, where precise control over the person's appearance or pose is crucial. By leveraging Leffa, users can generate high-quality images with reduced distortion, making it an valuable tool for various use cases.