Saved in:
Bibliographic Details
Main Authors: Chen, Junwen, Jiang, Heyang, Wang, Yanbin, Wu, Keming, Li, Ji, Zhang, Chao, Yanai, Keiji, Chen, Dong, Yuan, Yuhui
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.22523
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915310450245632
author Chen, Junwen
Jiang, Heyang
Wang, Yanbin
Wu, Keming
Li, Ji
Zhang, Chao
Yanai, Keiji
Chen, Dong
Yuan, Yuhui
author_facet Chen, Junwen
Jiang, Heyang
Wang, Yanbin
Wu, Keming
Li, Ji
Zhang, Chao
Yanai, Keiji
Chen, Dong
Yuan, Yuhui
contents Generating high-quality, multi-layer transparent images from text prompts can unlock a new level of creative control, allowing users to edit each layer as effortlessly as editing text outputs from LLMs. However, the development of multi-layer generative models lags behind that of conventional text-to-image models due to the absence of a large, high-quality corpus of multi-layer transparent data. In this paper, we address this fundamental challenge by: (i) releasing the first open, ultra-high-fidelity PrismLayers (PrismLayersPro) dataset of 200K (20K) multilayer transparent images with accurate alpha mattes, (ii) introducing a trainingfree synthesis pipeline that generates such data on demand using off-the-shelf diffusion models, and (iii) delivering a strong, open-source multi-layer generation model, ART+, which matches the aesthetics of modern text-to-image generation models. The key technical contributions include: LayerFLUX, which excels at generating high-quality single transparent layers with accurate alpha mattes, and MultiLayerFLUX, which composes multiple LayerFLUX outputs into complete images, guided by human-annotated semantic layout. To ensure higher quality, we apply a rigorous filtering stage to remove artifacts and semantic mismatches, followed by human selection. Fine-tuning the state-of-the-art ART model on our synthetic PrismLayersPro yields ART+, which outperforms the original ART in 60% of head-to-head user study comparisons and even matches the visual quality of images generated by the FLUX.1-[dev] model. We anticipate that our work will establish a solid dataset foundation for the multi-layer transparent image generation task, enabling research and applications that require precise, editable, and visually compelling layered imagery.
format Preprint
id arxiv_https___arxiv_org_abs_2505_22523
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle PrismLayers: Open Data for High-Quality Multi-Layer Transparent Image Generative Models
Chen, Junwen
Jiang, Heyang
Wang, Yanbin
Wu, Keming
Li, Ji
Zhang, Chao
Yanai, Keiji
Chen, Dong
Yuan, Yuhui
Computer Vision and Pattern Recognition
Generating high-quality, multi-layer transparent images from text prompts can unlock a new level of creative control, allowing users to edit each layer as effortlessly as editing text outputs from LLMs. However, the development of multi-layer generative models lags behind that of conventional text-to-image models due to the absence of a large, high-quality corpus of multi-layer transparent data. In this paper, we address this fundamental challenge by: (i) releasing the first open, ultra-high-fidelity PrismLayers (PrismLayersPro) dataset of 200K (20K) multilayer transparent images with accurate alpha mattes, (ii) introducing a trainingfree synthesis pipeline that generates such data on demand using off-the-shelf diffusion models, and (iii) delivering a strong, open-source multi-layer generation model, ART+, which matches the aesthetics of modern text-to-image generation models. The key technical contributions include: LayerFLUX, which excels at generating high-quality single transparent layers with accurate alpha mattes, and MultiLayerFLUX, which composes multiple LayerFLUX outputs into complete images, guided by human-annotated semantic layout. To ensure higher quality, we apply a rigorous filtering stage to remove artifacts and semantic mismatches, followed by human selection. Fine-tuning the state-of-the-art ART model on our synthetic PrismLayersPro yields ART+, which outperforms the original ART in 60% of head-to-head user study comparisons and even matches the visual quality of images generated by the FLUX.1-[dev] model. We anticipate that our work will establish a solid dataset foundation for the multi-layer transparent image generation task, enabling research and applications that require precise, editable, and visually compelling layered imagery.
title PrismLayers: Open Data for High-Quality Multi-Layer Transparent Image Generative Models
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2505.22523