ART: Anonymous Region Transformer for Variable Multi-Layer Transparent Image Generation

TL;DR

ART introduces a novel transformer-based method for generating variable multi-layer transparent images from text prompts, enabling efficient, high-quality, and editable layered image creation with reduced computational costs.

Contribution

The paper proposes the Anonymous Region Transformer (ART), a new approach that uses anonymous region layouts and layer-wise cropping to improve multi-layer image generation efficiency and quality.

Findings

Over 12 times faster than full attention methods

Supports over 50 distinct image layers

Enables precise control and scalable layer generation

Abstract

Multi-layer image generation is a fundamental task that enables users to isolate, select, and edit specific image layers, thereby revolutionizing interactions with generative models. In this paper, we introduce the Anonymous Region Transformer (ART), which facilitates the direct generation of variable multi-layer transparent images based on a global text prompt and an anonymous region layout. Inspired by Schema theory suggests that knowledge is organized in frameworks (schemas) that enable people to interpret and learn from new information by linking it to prior knowledge.}, this anonymous region layout allows the generative model to autonomously determine which set of visual tokens should align with which text tokens, which is in contrast to the previously dominant semantic layout for the image generation task. In addition, the layer-wise region crop mechanism, which only selects the visual tokens belonging to each anonymous region, significantly reduces attention computation costs and enables the efficient generation of images with numerous distinct layers (e.g., 50+). When compared to the full attention approach, our method is over 12 times faster and exhibits fewer layer conflicts. Furthermore, we propose a high-quality multi-layer transparent image autoencoder that supports the direct encoding and decoding of the transparency of variable multi-layer images in a joint manner. By enabling precise control and scalable layer generation, ART establishes a new paradigm for interactive content creation.