FlowBind: Efficient Any-to-Any Generation with Bidirectional Flows

TL;DR

FlowBind introduces an efficient, unified framework for any-to-any cross-modal generation using shared latent spaces and invertible flows, reducing data needs and computational costs.

Contribution

It presents a simple, joint-optimized approach with a shared latent space and modality-specific flows, enabling flexible training and direct cross-modal translation.

Findings

Achieves comparable quality with up to 6x fewer parameters.

Trains 10x faster than prior flow-based methods.

Demonstrates effectiveness across text, image, and audio modalities.

Abstract

Any-to-any generation seeks to translate between arbitrary subsets of modalities, enabling flexible cross-modal synthesis. Despite recent success, existing flow-based approaches are challenged by their inefficiency, as they require large-scale datasets often with restrictive pairing constraints, incur high computational cost from modeling joint distribution, and rely on complex multi-stage training. We propose FlowBind, an efficient framework for any-to-any generation. Our approach is distinguished by its simplicity: it learns a shared latent space capturing cross-modal information, with modality-specific invertible flows bridging this latent to each modality. Both components are optimized jointly under a single flow-matching objective, and at inference the invertible flows act as encoders and decoders for direct translation across modalities. By factorizing interactions through the shared latent, FlowBind naturally leverages arbitrary subsets of modalities for training, and achieves competitive generation quality while substantially reducing data requirements and computational cost. Experiments on text, image, and audio demonstrate that FlowBind attains comparable quality while requiring up to 6x fewer parameters and training 10x faster than prior methods. The project page with code is available at https://yeonwoo378.github.io/official_flowbind.