The authors built TemplateCraft around four stages: template planning, material generation, effect-workflow generation and protocol compilation.
Multi-agent revisions improve reusable visual templates across different user inputs
TemplateCraft turns natural-language instructions into executable image and video templates, using feedback, targeted rollback and memory to improve reliability.
Top University
Hongjie Yu · Zhiyuan Fan · Yuzhe Zhang · Jiangcun Du · Zhicheng Gao · Yuhong Zhang · +2 more
Peking University · Kuaishou Technology
Research Digest··2 min read
Yu et al.
Why this paper
From Peking University and Kuaishou Technology
In one line
TemplateCraft uses a multi-agent loop to turn natural-language instructions into reusable visual templates, raising generation success rates.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ·No stated limitations found
- ✓Reports numbers on named benchmarks
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§