SlerpFlow: Spherical Trajectory Correction for Rectified Flow Inversion
Rectified-flow-based diffusion transformers, particularly FLUX, have demonstrated outstanding performance in high-quality image generation. However, achieving fast and accurate inversion--transforming images back to latent noise for faithful reconstruction and editing--remains a challenging bottleneck due to the discretization errors of linear solvers. This paper introduces SlerpFlow, a straightforward yet highly effective zero-shot approach that unlocks the full potential of FLUX for high-fidelity inversion and editing. Unlike existing approaches (e.g., RF-Solver) that rely on complex numeric
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 48%[Paper] Multi-Resolution Flow Matching: Training-Free Diffusion Acceleration via Staged Sampling →
- LinkedLinked via arxiv author · 85%Wenbin Duan →
“SlerpFlow: Spherical Trajectory Correction for Rectified Flow Inversion”
- LinkedLinked via arxiv author · 85%Yan Shu →
“SlerpFlow: Spherical Trajectory Correction for Rectified Flow Inversion”
- LinkedLinked via arxiv author · 85%Zhuoyuan Fu →
“SlerpFlow: Spherical Trajectory Correction for Rectified Flow Inversion”
- LinkedLinked via arxiv author · 85%Fangmin Zhao →
“SlerpFlow: Spherical Trajectory Correction for Rectified Flow Inversion”
- LinkedLinked via arxiv author · 85%Yan Li →
“SlerpFlow: Spherical Trajectory Correction for Rectified Flow Inversion”
- LinkedLinked via arxiv author · 85%Yaru Zhao →
“SlerpFlow: Spherical Trajectory Correction for Rectified Flow Inversion”
- LinkedLinked via arxiv author · 85%Binyang Li →
“SlerpFlow: Spherical Trajectory Correction for Rectified Flow Inversion”