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

• URL: http://arxiv.org/abs/2506.05046v1
• Date: Thu, 05 Jun 2025 13:54:40 GMT
• Title: FlowDirector: Training-Free Flow Steering for Precise Text-to-Video Editing
• Abstract summary: FlowDirector is a novel inversion-free video editing framework.<n>Our framework models the editing process as a direct evolution in data space.<n>To achieve localized and controllable edits, we introduce an attention-guided masking mechanism.
• Score: 2.7248421583285265
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• EditStream: A Unified Autoregressive Framework for Interactive Video Generation and Editing [67.99022753510475]
  EditStream is a unified framework for interactive video generation and editing.<n>It unifies multiple video creation and manipulation tasks within a single DiT-based model.<n>It supports Text-to-Video, Image-to-Video, Video-to-Video, Editing propagation, Reference-guided Video Editing, and Camera Pose Change.
  arXiv  Detail & Related papers  (2026-08-16T07:27:18Z)
• LiveEdit: Towards Real-Time Diffusion-Based Streaming Video Editing [19.90420626930003]
  We present a novel streaming video editing framework that performs causal, frame-by-frame editing with strong content preservation and real-time responsiveness.<n>Our method achieves state-of-the-art visual quality among streaming baselines while drastically boosting inference speed to 12.66 FPS, making it suitable for interactive and augmented reality applications.
  arXiv  Detail & Related papers  (2026-06-25T08:24:03Z)
• Beyond Consistency: Preserving Temporal Structure in Zero-Shot Video Editing [48.768011768488584]
  Existing zero-shot video editing methods fail to preserve the video's original temporal structure.<n>We introduce a novel zero-shot editing approach that explicitly focuses on preserving the source video's temporal structure.<n>Our method achieves state-of-the-art results, successfully balancing the preservation of original temporal structure with computational efficiency.
  arXiv  Detail & Related papers  (2026-06-07T18:53:57Z)
• Reasoning to Align: Implicit Reasoning in Diffusion Transformers for Video Editing [55.211537893248675]
  We propose RVEDiT, an implicit Reasoning Video Editing DiT framework built around two complementary components.<n> RVEDiT consistently outperforms state-of-the-art baselines, with particularly strong gains on localized and compositional edits.
  arXiv  Detail & Related papers  (2026-05-23T17:22:14Z)
• FlowAnchor: Stabilizing the Editing Signal for Inversion-Free Video Editing [7.08737643046839]
  FlowAnchor is a training-free framework for stable and efficient inversion-free, flow-based video editing.<n>It anchors both where to edit and how strongly to edit in high-dimensional video latent spaces.<n>It achieves more faithful, temporally coherent, and computationally efficient video editing across challenging multi-object and fast-motion scenarios.
  arXiv  Detail & Related papers  (2026-04-24T14:17:11Z)
• SAMA: Factorized Semantic Anchoring and Motion Alignment for Instruction-Guided Video Editing [76.349958946335]
  We present SAMA (factorized Semantic Anchoring and Motion Alignment), a framework that factorizes video editing into semantic anchoring and motion modeling.<n>First, we introduce Semantic Anchoring, which establishes a reliable visual anchor by jointly predicting semantic tokens and video latents at sparse anchor frames.<n>Second, Motion Alignment pre-trains the same backbone on motion-centric video restoration pretext tasks.
  arXiv  Detail & Related papers  (2026-03-19T17:59:51Z)
• PropFly: Learning to Propagate via On-the-Fly Supervision from Pre-trained Video Diffusion Models [35.59605874012795]
  PropFly is a training pipeline for propagation-based video editing.<n>PropFly relies on pre-trained video diffusion models (VDMs) instead of requiring off-the-shelf or precomputed paired video editing datasets.<n>Our pipeline enables an adapter attached to the pre-trained VDM to learn to propagate edits via Guidance-Modulated Flow Matching (GMFM) loss.
  arXiv  Detail & Related papers  (2026-02-24T06:11:08Z)
• Shifting the Breaking Point of Flow Matching for Multi-Instance Editing [47.32746672482526]
  We introduce Instance-Disentangled Attention, a mechanism that partitions joint attention operations and enforces binding between instance-specific textual instructions and spatial regions.<n>Our approach promotes edit disentanglement and locality while preserving global output coherence, enabling single-pass, instance-level editing.
  arXiv  Detail & Related papers  (2026-02-09T14:52:45Z)
• VALA: Learning Latent Anchors for Training-Free and Temporally Consistent [29.516179213427694]
  We propose VALA, a variational alignment module that adaptively selects key frames and compresses their latent features into semantic anchors for consistent video editing.<n>Our method can be fully integrated into training-free text-to-image based video editing models.
  arXiv  Detail & Related papers  (2025-10-27T03:44:11Z)
• Follow-Your-Shape: Shape-Aware Image Editing via Trajectory-Guided Region Control [52.87568958372421]
  Follow-Your-Shape is a training-free and mask-free framework that supports precise and controllable editing of object shapes.<n>We compute a Trajectory Divergence Map (TDM) by comparing token-wise velocity differences between the inversion and denoising paths.<n>Our method achieves superior editability and visual fidelity, particularly in tasks requiring large-scale shape replacement.
  arXiv  Detail & Related papers  (2025-08-11T16:10:00Z)
• InstantEdit: Text-Guided Few-Step Image Editing with Piecewise Rectified Flow [19.972879378697215]
  We propose a fast text-guided image editing method called InstantEdit based on the RectifiedFlow framework.<n>Our approach leverages the straight sampling trajectories of RectifiedFlow by introducing a specialized inversion strategy called PerRFI.<n>We also propose a novel regeneration method, Inversion Latent Injection, which effectively reuses latent information obtained during inversion to facilitate more coherent and detailed regeneration.
  arXiv  Detail & Related papers  (2025-08-08T05:38:17Z)
• Edit as You See: Image-guided Video Editing via Masked Motion Modeling [18.89936405508778]
  We propose a novel Image-guided Video Editing Diffusion model, termed IVEDiff.<n>IVEDiff is built on top of image editing models, and is equipped with learnable motion modules to maintain the temporal consistency of edited video.<n>Our method is able to generate temporally smooth edited videos while robustly dealing with various editing objects with high quality.
  arXiv  Detail & Related papers  (2025-01-08T07:52:12Z)
• Re-Attentional Controllable Video Diffusion Editing [48.052781838711994]
  We propose a Re-Attentional Controllable Video Diffusion Editing (ReAtCo) method.<n>To align the spatial placement of the target objects with the edited text prompt in a training-free manner, we propose a Re-Attentional Diffusion (RAD)<n>RAD refocuses the cross-attention activation responses between the edited text prompt and the target video during the denoising stage, resulting in a spatially location-aligned and semantically high-fidelity manipulated video.
  arXiv  Detail & Related papers  (2024-12-16T12:32:21Z)
• VIA: Unified Spatiotemporal Video Adaptation Framework for Global and Local Video Editing [91.60658973688996]
  We introduce VIA, a unified Video Adaptation framework for global local video editing, pushing the limits of consistently editing minute-long videos.<n>To ensure local consistency within individual frames, we designed test-time editing adaptation to adapt a pre-trained image editing model.<n>We show that VIA can achieve consistent long video editing in minutes, unlocking the potential for advanced video editing tasks over long video sequences.
  arXiv  Detail & Related papers  (2024-06-18T17:51:37Z)
• COVE: Unleashing the Diffusion Feature Correspondence for Consistent Video Editing [57.76170824395532]
  Video editing is an emerging task, in which most current methods adopt the pre-trained text-to-image (T2I) diffusion model to edit the source video.<n>We propose COrrespondence-guided Video Editing (COVE) to achieve high-quality and consistent video editing.<n>COVE can be seamlessly integrated into the pre-trained T2I diffusion model without the need for extra training or optimization.
  arXiv  Detail & Related papers  (2024-06-13T06:27:13Z)
• FLATTEN: optical FLow-guided ATTENtion for consistent text-to-video editing [65.60744699017202]
  We introduce optical flow into the attention module in the diffusion model's U-Net to address the inconsistency issue for text-to-video editing. Our method, FLATTEN, enforces the patches on the same flow path across different frames to attend to each other in the attention module. Results on existing text-to-video editing benchmarks show that our proposed method achieves the new state-of-the-art performance.
  arXiv  Detail & Related papers  (2023-10-09T17:59:53Z)
• Ground-A-Video: Zero-shot Grounded Video Editing using Text-to-image Diffusion Models [65.268245109828]
  Ground-A-Video is a video-to-video translation framework for multi-attribute video editing. It attains temporally consistent editing of input videos in a training-free manner. Experiments and applications demonstrate that Ground-A-Video's zero-shot capacity outperforms other baseline methods in terms of edit-accuracy and frame consistency.
  arXiv  Detail & Related papers  (2023-10-02T11:28:37Z)
• InstructVid2Vid: Controllable Video Editing with Natural Language Instructions [97.17047888215284]
  InstructVid2Vid is an end-to-end diffusion-based methodology for video editing guided by human language instructions. Our approach empowers video manipulation guided by natural language directives, eliminating the need for per-example fine-tuning or inversion.
  arXiv  Detail & Related papers  (2023-05-21T03:28:13Z)
• Structure and Content-Guided Video Synthesis with Diffusion Models [13.464501385061032]
  We present a structure and content-guided video diffusion model that edits videos based on visual or textual descriptions of the desired output. Our model is trained jointly on images and videos which also exposes explicit control of temporal consistency through a novel guidance method.
  arXiv  Detail & Related papers  (2023-02-06T18:50:23Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.