CVJun 4, 2025

LayerFlow: A Unified Model for Layer-aware Video Generation

arXiv:2506.04228v19 citationsh-index: 6SIGGRAPH
Originality Incremental advance
AI Analysis

This work addresses the need for layer-aware video generation in creative and editing applications, though it is incremental as it builds upon existing text-to-video diffusion models.

The authors tackled the problem of generating videos with separate transparent foreground and background layers from text prompts, achieving a unified model that supports multiple generation and decomposition tasks without requiring high-quality layered video training data.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes