EffectMaker: Unifying Reasoning and Generation for Customized Visual Effect Creation
Shiyuan Yang, Ruihuang Li, Jiale Tao, Shuai Shao, Qinglin Lu, Jing Liao

TL;DR
EffectMaker introduces a unified framework combining reasoning and generation to enable scalable, reference-based visual effect customization without per-effect fine-tuning, leveraging large datasets and multimodal models.
Contribution
The paper presents EffectMaker, a novel unified reasoning-generation approach for VFX creation that eliminates the need for per-effect fine-tuning and introduces a large synthetic dataset.
Findings
Outperforms state-of-the-art baselines in visual quality and effect consistency.
Achieves accurate, controllable, and effect-consistent synthesis.
Demonstrates scalability and generalization to diverse VFX categories.
Abstract
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsMultimodal Machine Learning Applications · Generative Adversarial Networks and Image Synthesis · Visual Attention and Saliency Detection
