OmniPSD: Layered PSD Generation with Diffusion Transformer

TL;DR

OmniPSD introduces a diffusion transformer-based framework capable of generating and decomposing layered PSD files with transparency, advancing image editing and design automation.

Contribution

It presents a unified diffusion model for layered PSD generation and decomposition, incorporating spatial attention and an RGBA-VAE for transparency preservation.

Findings

High-fidelity layered PSD generation

Structural consistency in output layers

Effective transparency preservation

Abstract

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.