LCG introduces Sparse Relational Attention and Routing Consistency Constraint to produce consistent multi-image text-to-image sequences and reports better prompt alignment and character consistency than baselines on a new 600K-sequence synthetic dataset.
arXiv preprint(2023)
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
-
LCG: Long-Context Consistent Image Generation with Sparse Relational Attention
LCG introduces Sparse Relational Attention and Routing Consistency Constraint to produce consistent multi-image text-to-image sequences and reports better prompt alignment and character consistency than baselines on a new 600K-sequence synthetic dataset.