MangaFlow introduces an agentic framework for controllable story-to-manga generation by decomposing the process into explicit intermediate steps and using story section memory to improve layout adherence and cross-panel consistency over direct baselines.
Variant CSD↑CIDS↑PA↑ CM↑Inc↑Aes↑CP↓ Cross Self Cross Self Scene Shot CI IA Avg
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
MangaFlow: An End-to-End Agentic Framework for Controllable Story to Manga Generation
MangaFlow introduces an agentic framework for controllable story-to-manga generation by decomposing the process into explicit intermediate steps and using story section memory to improve layout adherence and cross-panel consistency over direct baselines.