Sync-LoRA Overview for Video Editing Propagation
Figure 2 : Overview of Sync-LoRA. Given a source video S S , an edited first frame I I , and an edit prompt P P , Sync-LoRA denoises the target video T T conditioned on these inputs. During training, only the edited branch is noised, while the source branch stays clean and provides motion and identity cues through shared attention, so the model copies motion from S S and propagates the local edit across all frames.
Paper context
Paper title: In-Context Sync-LoRA for Portrait Video Editing Abstract: Editing portrait videos is a challenging task that requires flexible yet precise control over a wide range of modifications, such as appearance changes, expression edits, or the addition of objects. The key difficulty lies in preserving the subject's original temporal behavior, demanding that every edited frame remains precisely synchronized with the corresponding source frame. We present Sync-LoRA, a method for editing portrait videos that achieves high-quality visual modifications while maintaining frame-accurate synchronization and identity consistency. Our approach uses an image-to-video diffusion model, where the edit is defined by modifying the first frame and then propagated to the entire sequence. To enable accurate synchronization, we train an in-context LoRA using paired videos that depict identical motion trajectories but differ in appearance. These pairs are automatically generated and curated through a synchronization-based filtering process that selects only the most temporally aligned examples for training. This training setup teaches the model to combine motion cues from the source video with the visual changes introduced in the edited first frame. Trained on a compact, highly curated set of synchronized human portraits, Sync-LoRA generalizes to unseen identities and diverse edits (e.g., modifying appearance, adding objects, or changing backgrounds), robustly handling variations in pose and expression. Our results demonstrate high visual fidelity and strong te Passages referencing this figure: Figure 1 : Given a source video and an edited first frame, our method propagates the visual edit. By training on our curated set of synchronized examples, the model learns to propagate motion cues from the source to the edited view, applying only localized changes defined by the first frame while maintaining frame-level alignment with the source video (see Figure 1 ).
