Modeling Artistic Workflows for Image Generation and Editing

TL;DR

This paper introduces a generative model that mimics artistic workflows, allowing multi-stage image creation and editing with optimized regularization to maintain image fidelity, demonstrated across multiple datasets.

Contribution

It presents a novel generative framework that models artistic workflows for both image synthesis and editing, incorporating an optimization process for high-fidelity modifications.

Findings

Effective multi-stage image generation and editing demonstrated

Model outperforms baselines on artistic datasets

Regularization improves editing accuracy

Abstract

People often create art by following an artistic workflow involving multiple stages that inform the overall design. If an artist wishes to modify an earlier decision, significant work may be required to propagate this new decision forward to the final artwork. Motivated by the above observations, we propose a generative model that follows a given artistic workflow, enabling both multi-stage image generation as well as multi-stage image editing of an existing piece of art. Furthermore, for the editing scenario, we introduce an optimization process along with learning-based regularization to ensure the edited image produced by the model closely aligns with the originally provided image. Qualitative and quantitative results on three different artistic datasets demonstrate the effectiveness of the proposed framework on both image generation and editing tasks.