OmniPSD：基于扩散变换器的分层PSD生成
OmniPSD: Layered PSD Generation with Diffusion Transformer
AI总结：
OmniPSD通过扩散变换器实现文本到PSD生成和图像到PSD分解，提升分层设计的生成与编辑能力。
摘要：
近期扩散模型的进步显著提升了图像生成与编辑能力，但生成或重建具有透明alpha通道的分层PSD文件仍极具挑战性。我们提出OmniPSD，一种基于Flux生态系统的统一扩散框架，通过上下文学习实现文本到PSD生成和图像到PSD分解。在文本到PSD生成中，OmniPSD将多个目标图层在单一画布上按空间排列，并通过空间注意力学习其组成关系，生成语义连贯且层次分明的图层。在图像到PSD分解中，它执行迭代上下文编辑，逐步提取并擦除文本和前景组件，从单张扁平图像中重建可编辑的PSD图层。采用RGBA-VAE作为辅助表示模块，以保留透明度而不影响结构学习。在我们新的RGBA分层数据集上进行的大量实验表明，OmniPSD实现了高保真生成、结构一致性及透明度意识，为基于扩散变换器的分层设计生成与分解提供了新范式。
英文摘要：
Recent advances in diffusion models have greatly improved image generation and editing, yet generating or reconstructing layered PSD files with transparent alpha channels remains highly challenging. We propose OmniPSD, a unified diffusion framework built upon the Flux ecosystem that enables both text-to-PSD generation and image-to-PSD decomposition through in-context learning. For text-to-PSD generation, OmniPSD arranges multiple target layers spatially into a single canvas and learns their compositional relationships through spatial attention, producing semantically coherent and hierarchically structured layers. For image-to-PSD decomposition, it performs iterative in-context editing, progressively extracting and erasing textual and foreground components to reconstruct editable PSD layers from a single flattened image. An RGBA-VAE is employed as an auxiliary representation module to preserve transparency without affecting structure learning. Extensive experiments on our new RGBA-layered dataset demonstrate that OmniPSD achieves high-fidelity generation, structural consistency, and transparency awareness, offering a new paradigm for layered design generation and decomposition with diffusion transformers.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
