Zero-Shot Image Style Transfer Using Conditional Inversion-Free Flow

Zero-shot image style transfer has recently attracted increasing attention, as it enables style manipulation without additional model optimization or parameter tuning. However, most existing approaches still rely on latent inversion, where introduced reconstruction errors may accumulate and gradually degrade content structures. Moreover, currentstyle transfer methods still struggle to balance style strength and content preservation due to inadequate guidance. To address these issues, this paper proposes a novel zero-shot image style transfer method based on conditional inversionfree flow. Built upon pre-trained Flow Matching models, our method eliminates the inversion by constructing a styletransfertrajectory ODE from a gradient-injected discrepancy between content-conditioned and style-conditioned velocity fields. To further enhance style representation, we introduce a conditional guidance mechanism driven by a pre-trained CLIP model. Specifically, a style loss is introduced to align the Gram matrix statistics of multi-layer CLIP features with those of the reference style; a semantic consistency constraint based on CLIP embedding cosine distance preserves high-level semantics. The dual guidance terms are incorporated into each Euler sampling step through lossgradients, guiding the generation trajectory without model fine-tuning or access to internal model features. Extensive quantitative and qualitative experiments demonstrate that our method outperforms state-of-the-art approaches on ArtFID, FID, LPIPS, and CFSD, providing a better balance between style consistency and content preservation.