AIGC-Driven Virtual Anime Scene and Character Generation Based on Work Orders

Abstract

Traditional virtual scene and character design suffers from low efficiency and cultural misalignment in AI - generated content. In the context of computer vision and virtual reality, this misalignment also raises concerns about digital media information security and authenticity. This paper proposes a work order - driven AIGC framework for virtual anime scene and character generation. A prompt parser is introduced to convert unstructured enterprise work orders into structured workflows, which then guide generative tools for end - to - end generation. To address cultural misalignment, a Lingnan Cultural Gene Library is constructed and parameterized constraints are applied to traditional elements during generation. A human - in - the - loop mechanism is integrated at the 2D - to - 3D transition node to combine AIGC efficiency with manual topological precision. Experiments on a dataset of 150 enterprise work orders for Lingnan virtual scenes and characters show that the proposed framework reduces design iteration time by 42% (from 68.5 h to 39.6 h) and improves cultural element accuracy from 78% to 92% (p < 0.01) compared with traditional 3D modeling pipelines, providing an efficient and culturally aware solution for AIGC applications in virtual reality and multimedia content generation, while also enhancing the security and authenticity of digital cultural media.