BiFM: Bidirectional Flow Matching for Few-Step Image Editing and Generation

ArXi:2603.24942v1 Announce Type: new Recent diffusion and flow matching models have nstrated strong capabilities in image generation and editing by progressively removing noise through iterative sampling. While this enables flexible inversion for semantic-preserving edits, few-step sampling regimes suffer from poor forward process approximation, leading to degraded editing quality. Existing few-step inversion methods often rely on pretrained generators and auxiliary modules, limiting scalability and generalization across different architectures.