EffectMaker: Unifying Reasoning and Generation for Customized Visual Effect Creation
This addresses the challenge of scalable and flexible VFX creation for video content producers, offering a novel approach that avoids costly pipelines and data scarcity issues.
The paper tackles the problem of generating high-quality visual effects (VFX) without expert knowledge or per-effect fine-tuning by introducing EffectMaker, a unified reasoning-generation framework that uses a multimodal large language model and diffusion transformer for reference-based customization, achieving superior visual quality and effect consistency over state-of-the-art baselines.
Visual effects (VFX) are essential for enhancing the expressiveness and creativity of video content, yet producing high-quality effects typically requires expert knowledge and costly production pipelines. Existing AIGC systems face significant challenges in VFX generation due to the scarcity of effect-specific data and the inherent difficulty of modeling supernatural or stylized effects. Moreover, these approaches often require per-effect fine-tuning, which severely limits their scalability and generalization to novel VFX. In this work, we present EffectMaker, a unified reasoning-generation framework that enables reference-based VFX customization. EffectMaker employs a multimodal large language model to interpret high-level effect semantics and reason about how they should adapt to a target subject, while a diffusion transformer leverages in-context learning to capture fine-grained visual cues from reference videos. These two components form a semantic-visual dual-path guidance mechanism that enables accurate, controllable, and effect-consistent synthesis without per-effect fine-tuning. Furthermore, we construct EffectData, the largest high-quality synthetic dataset containing 130k videos across 3k VFX categories, to improve generalization and scalability. Experiments show that EffectMaker achieves superior visual quality and effect consistency over state-of-the-art baselines, offering a scalable and flexible paradigm for customized VFX generation. Project page: https://effectmaker.github.io