S2ED is a prompt-layer framework that decomposes stories into editable executable descriptions via three agents to improve sequence consistency and character fidelity in story illustrations.
Characterfactory: Sampling consistent characters with gans for diffusion models,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
S2ED: From Story to Executable Descriptions for Consistency-Aware Story Illustration
S2ED is a prompt-layer framework that decomposes stories into editable executable descriptions via three agents to improve sequence consistency and character fidelity in story illustrations.