FluxSpace: Disentangled Semantic Editing in Rectified Flow Transformers
This addresses the limitation of precise image editing for users of rectified flow models, though it appears incremental as it builds on existing transformer-based methods.
The paper tackled the problem of disentangled editing in rectified flow models for image generation, introducing FluxSpace to enable precise, attribute-specific modifications without affecting unrelated aspects, achieving scalable and effective editing capabilities.
Rectified flow models have emerged as a dominant approach in image generation, showcasing impressive capabilities in high-quality image synthesis. However, despite their effectiveness in visual generation, rectified flow models often struggle with disentangled editing of images. This limitation prevents the ability to perform precise, attribute-specific modifications without affecting unrelated aspects of the image. In this paper, we introduce FluxSpace, a domain-agnostic image editing method leveraging a representation space with the ability to control the semantics of images generated by rectified flow transformers, such as Flux. By leveraging the representations learned by the transformer blocks within the rectified flow models, we propose a set of semantically interpretable representations that enable a wide range of image editing tasks, from fine-grained image editing to artistic creation. This work offers a scalable and effective image editing approach, along with its disentanglement capabilities.