LayerFlow: A Unified Model for Layer-aware Video Generation

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Ji, Sihui, Luo, Hao, Chen, Xi, Tu, Yuanpeng, Wang, Yiyang, Zhao, Hengshuang
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866909637221023744
author Ji, Sihui
Luo, Hao
Chen, Xi
Tu, Yuanpeng
Wang, Yiyang
Zhao, Hengshuang
author_facet Ji, Sihui
Luo, Hao
Chen, Xi
Tu, Yuanpeng
Wang, Yiyang
Zhao, Hengshuang
contents We present LayerFlow, a unified solution for layer-aware video generation. Given per-layer prompts, LayerFlow generates videos for the transparent foreground, clean background, and blended scene. It also supports versatile variants like decomposing a blended video or generating the background for the given foreground and vice versa. Starting from a text-to-video diffusion transformer, we organize the videos for different layers as sub-clips, and leverage layer embeddings to distinguish each clip and the corresponding layer-wise prompts. In this way, we seamlessly support the aforementioned variants in one unified framework. For the lack of high-quality layer-wise training videos, we design a multi-stage training strategy to accommodate static images with high-quality layer annotations. Specifically, we first train the model with low-quality video data. Then, we tune a motion LoRA to make the model compatible with static frames. Afterward, we train the content LoRA on the mixture of image data with high-quality layered images along with copy-pasted video data. During inference, we remove the motion LoRA thus generating smooth videos with desired layers.
format Preprint
id arxiv_https___arxiv_org_abs_2506_04228
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LayerFlow: A Unified Model for Layer-aware Video Generation
Ji, Sihui
Luo, Hao
Chen, Xi
Tu, Yuanpeng
Wang, Yiyang
Zhao, Hengshuang
Computer Vision and Pattern Recognition
We present LayerFlow, a unified solution for layer-aware video generation. Given per-layer prompts, LayerFlow generates videos for the transparent foreground, clean background, and blended scene. It also supports versatile variants like decomposing a blended video or generating the background for the given foreground and vice versa. Starting from a text-to-video diffusion transformer, we organize the videos for different layers as sub-clips, and leverage layer embeddings to distinguish each clip and the corresponding layer-wise prompts. In this way, we seamlessly support the aforementioned variants in one unified framework. For the lack of high-quality layer-wise training videos, we design a multi-stage training strategy to accommodate static images with high-quality layer annotations. Specifically, we first train the model with low-quality video data. Then, we tune a motion LoRA to make the model compatible with static frames. Afterward, we train the content LoRA on the mixture of image data with high-quality layered images along with copy-pasted video data. During inference, we remove the motion LoRA thus generating smooth videos with desired layers.
title LayerFlow: A Unified Model for Layer-aware Video Generation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2506.04228