AI Paper Atlas

Research map / Video / Video generation

FlowDirector: Training-Free Flow Steering for Precise Text-to-Video Editing

Guangzhao Li, Yanming Yang, Chenxi Song, Xiaohong Liu, Chi Zhang

CVPR 2026 · Video › Video generation · approach: Diffusion-based video editing · 22 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add direction-aware flow correction (DA-FC) (ablation)FlowDirector · 150 video edits (41 frames)Qedit: 25.42 -> 27.19Improved
add direction-aware flow correction (DA-FC) (ablation)FlowDirector · 150 video edits (41 frames)CLIP-T: 32.25 -> 34.64Improved
add motion-appearance decoupling (MAD-FC) (ablation)FlowDirector · 150 video edits (41 frames)WarpSSIM: 69.26 -> 78.49Improved
add motion-appearance decoupling (MAD-FC) (ablation)FlowDirector · 150 video edits (41 frames)Qedit: 24.04 -> 27.19Improved
add differential averaging guidance (DAG) (ablation)FlowDirector · 150 video edits (41 frames)Qedit: 27.11 -> 27.19Improved
add differential averaging guidance (DAG) (ablation)FlowDirector · 150 video edits (41 frames)WarpSSIM: 78.32 -> 78.49Mixed
remove parallel component of the editing flow (ablation)DA-FC · 150 video edits (41 frames)Qedit: 25.42 -> 26.04Improved
amplify opposing component with alpha 0.25 versus no amplification (ablation)DA-FC · 150 video edits (41 frames)Qedit: 26.04 -> 27.19Improved
increase alpha amplification (ablation)DA-FC · 150 video edits (41 frames)WarpSSIM: 78.85 -> 78.49Hurt
use direction-aware correction versus skipping early steps (ablation)Director ODE (skip) · 150 video edits (41 frames)CLIP-T: 32.23 -> 34.64Improved
skip early steps in direct ODE (ablation)Director ODE · 150 video edits (41 frames)WarpSSIM: 62.71 -> 78.90Improved
use DAG with 4 rounds instead of 20-round conventional averagingconventional averaging · 41-frame editing timeediting time: 19 min 3s -> 2 min 54sImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy