Problem
Research questions and friction points this paper is trying to address.
Interactive Video Generation
Video Editing
Autoregressive Model
EditStream: A Unified Autoregressive Framework for Interactive Video Generation and Editing
🤖 AI Summary
EditStream通过统一的DiT模型和两阶段蒸馏方法解决交互式视频生成与编辑问题，支持多种任务并提高效率和稳定性。
📝 Abstract
Interactive video generation and editing are becoming increasingly important for creative design. In this report, we introduce EditStream: a unified framework for interactive video generation and editing. EditStream unifies multiple video creation and manipulation tasks within a single DiT-based model through flexible task-specific conditioning, and further transforms it into a fast, few-step autoregressive model for efficient streaming. It supports Text-to-Video, Image-to-Video, Video-to-Video, Editing Propagation, Reference-guided Video Editing, and Camera Pose Change, enabling flexible control over video generation, transformation, and editing within one system. To make the unified model practical for interactive use, we develop a two-stage distillation approach that combines Velocity Moment Matching (VMM) with autoregressive unrolling. VMM matches conditional velocity moments at student-reached intermediate states to preserve generation quality and motion, while unrolling exposes the student to its own autoregressive predictions to improve temporal stability. Together, they alleviate common challenges in few-step autoregressive video generation, including over-saturation, degraded motion, temporal instability, and complex training. EditStream provides a practical and scalable solution that bridges high-quality diffusion-based video models with interactive creative workflows.
Innovation
Methods, ideas, or system contributions that make the work stand out.
unified framework
autoregressive model
Velocity Moment Matching (VMM)
interactive video generation
distillation approach
🔎 Similar Papers
No similar papers found.
