FlowDirector, an inversion-free video editing framework, uses ODEs for spatiotemporal coherent editing and attention-guided masking for localized control, achieving state-of-the-art performance.
Text-driven video editing aims to modify video content according to natural
language instructions. While recent training-free approaches have made progress
by leveraging pre-trained diffusion models, they typically rely on
inversion-based techniques that map input videos into the latent space, which
often leads to temporal inconsistencies and degraded structural fidelity. To
address this, we propose FlowDirector, a novel inversion-free video editing
framework. Our framework models the editing process as a direct evolution in
data space, guiding the video via an Ordinary Differential Equation (ODE) to
smoothly transition along its inherent spatiotemporal manifold, thereby
preserving temporal coherence and structural details. To achieve localized and
controllable edits, we introduce an attention-guided masking mechanism that
modulates the ODE velocity field, preserving non-target regions both spatially
and temporally. Furthermore, to address incomplete edits and enhance semantic
alignment with editing instructions, we present a guidance-enhanced editing
strategy inspired by Classifier-Free Guidance, which leverages differential
signals between multiple candidate flows to steer the editing trajectory toward
stronger semantic alignment without compromising structural consistency.
Extensive experiments across benchmarks demonstrate that FlowDirector achieves
state-of-the-art performance in instruction adherence, temporal consistency,
and background preservation, establishing a new paradigm for efficient and
coherent video editing without inversion.
