EPISODE · Dec 12, 2025 · 26 MIN
OmniPSD: Layered PSD Generation with Diffusion Transformer
from Daily Paper Cast · host Jingwen Liang, Gengyu Wang
🤗 Upvotes: 27 | cs.CV Authors: Cheng Liu, Yiren Song, Haofan Wang, Mike Zheng Shou Title: OmniPSD: Layered PSD Generation with Diffusion Transformer Arxiv: http://arxiv.org/abs/2512.09247v1 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.
What this episode covers
🤗 Upvotes: 27 | cs.CV Authors: Cheng Liu, Yiren Song, Haofan Wang, Mike Zheng Shou Title: OmniPSD: Layered PSD Generation with Diffusion Transformer Arxiv: http://arxiv.org/abs/2512.09247v1 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.
NOW PLAYING
OmniPSD: Layered PSD Generation with Diffusion Transformer
No transcript for this episode yet
Similar Episodes
No similar episodes found.