Abstract
The growing popularity of short videos has driven demand for one-click content creation. Visual templates turn uploaded images into personalized content with preset effects, but reusable template generation still requires substantial manual effort in asset preparation and tool orchestration. We propose TemplateCraft, a multi-agent system that converts natural-language instructions into client-executable templates through planning, material generation, effect-workflow generation, and protocol compilation. Its Planner-Evaluator loop uses execution feedback for targeted rollback, while stage-level and long-term memory support revision without parameter updates. We evaluate TemplateCraft on TemplateBench, derived from 60 real-world templates. With the same Qwen3-VL backbone, TemplateCraft raises image/video generation success rates from 56.7%/30.0% to 66.7%/50.0% over Planner-only (best-of-three) and improves template adherence and style consistency. With additional evaluation and revision, it matches or exceeds a GPT-4o Planner-only baseline on selected metrics. Persistent assets further improve cross-input style consistency.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Yu, H., Fan, Z., Zhang, Y., Du, J., Gao, Z., Zhang, Y., Zhan, X., & Xie, Z. (2026). TemplateCraft: Agentic Visual Template Generation. https://omanscience.com/en/articles/templatecraft-agentic-visual-template-generation
MLA 9
Yu, Hongjie, et al. "TemplateCraft: Agentic Visual Template Generation." https://omanscience.com/en/articles/templatecraft-agentic-visual-template-generation.
Chicago (author–date)
Yu, Hongjie, Zhiyuan Fan, Yuzhe Zhang, Jiangcun Du, Zhicheng Gao, Yuhong Zhang, Xiaokai Zhan, and Zongshi Xie. 2026. "TemplateCraft: Agentic Visual Template Generation." https://omanscience.com/en/articles/templatecraft-agentic-visual-template-generation.
Harvard
Yu, H., Fan, Z., Zhang, Y., Du, J., Gao, Z., Zhang, Y., Zhan, X. and Xie, Z. (2026) 'TemplateCraft: Agentic Visual Template Generation', Available at: https://omanscience.com/en/articles/templatecraft-agentic-visual-template-generation.
Vancouver
Yu H, Fan Z, Zhang Y, Du J, Gao Z, Zhang Y, et al. TemplateCraft: Agentic Visual Template Generation. https://omanscience.com/en/articles/templatecraft-agentic-visual-template-generation
IEEE
H. Yu, Z. Fan, Y. Zhang, J. Du, Z. Gao, Y. Zhang, X. Zhan, and Z. Xie, "TemplateCraft: Agentic Visual Template Generation," https://omanscience.com/en/articles/templatecraft-agentic-visual-template-generation.