VideoX-Qwen, an integrated data-construction and model-training framework for general instruction-based video editing, and a unified Qwen-Wan editor that combines multimodal semantic conditioning with dense source-video latent guidance provide a practical foundation for more capable instruction-driven video editing.
Abstract
Progress in general-purpose video editing depends on constructing large-scale paired supervision and effectively adapting video-generation backbones to instruction-driven editing. Unlike video generation, video editing must execute a requested transformation while preserving unrelated subjects, scene structure, motion, and temporal continuity. We present VideoX-Qwen, an integrated data-construction and model-training framework for general instruction-based video editing. Our scalable production pipeline organizes specialized generation and understanding models into complementary routes for addition, removal, replacement, and attribute editing, followed by quality screening and instruction enrichment. It produces more than 1.2 million directional video-editing records, including over 400,000 records in each major task group, with an automatic acceptance rate of 89%. The resulting corpus provides broad and structured coverage of common editing operations through a unified source-instruction-target interface. We further develop a unified Qwen-Wan editor that combines multimodal semantic conditioning with dense source-video latent guidance. A progressive image-video training strategy aligns the multimodal instruction interface, adapts the video generator to source-conditioned editing, and refines output quality with selected high-resolution data. In a 100-example comparison with UniVideo and Kling O1, VideoX-Qwen achieves the best mean result on nine of eleven reported metrics, including instruction following, editing quality, content preservation, structural and perceptual similarity, and video-distribution quality. Together, the large-scale data-production system and unified training framework provide a practical foundation for more capable instruction-driven video editing.
Instruction-based video editing is commonly built on video-pretrained generative backbones: a video diffusion transformer is adapted, at considerable cost, to condition on a source video and an editing instruction. In this report we explore a different route and show that a strong instruction-based image editing model...
Yun-Peng Bai, Yossi Gandelsman, Michael Gharbi et al.· 3 citations
The quality and diversity of instruction-based video editing datasets are steadily improving, yet existing datasets mainly focus on single editing operations and fall short in supporting compositional instruction-guided video editing. In particular, multiple editing intents must be jointly understood and faithfully exe...
Fuchen Long, Cong Wang, Zitao Gao et al.· 1 citation
RefVideo-6M, a large-scale reference-guided editing dataset containing 5 million video editing samples and 1 million image editing samples, is introduced and enables the training of powerful editing models with improved visual quality, controllability, and reference consistency.
Bo-Jia Zi, Xiaoyan Yang, Yu Zhou et al.· 1 citation
Conventional video editing primarily focuses on scene-level content, whereas live streaming places greater emphasis on the human subject. However, directly applying existing video-editing methods to human-centric live streaming remains challenging, as they may introduce facial-expression inconsistencies and typically d...
Zhiyuan Li, Chi-Man Pun, Peng-Tao Jiang et al.· 0 citations
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...
Yu-Qian Zhou, Zhenghong Zhou, Zongze Wu et al.· 1 citation
Video editing spans diverse editing paradigms, yet achieving high-quality instruction-guided and subject-guided editing within a single unified framework remains challenging. We introduce EditVid, a training-free framework combining sparse causal memory for local coherence, correspondence-based post-attention token inj...
A. Juvekar, O. Susladkar, K. A. Nguyen et al.· 0 citations