Feeding large multimodal models a prompt in multiple languages, not just English, improves text-to-image alignment and human-preference scores across three benchmarks.
Design guidelines for prompt engineering text- to-image generative models,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
Boosting Text-To-Image Generation via Multilingual Prompting in Large Multimodal Models
Feeding large multimodal models a prompt in multiple languages, not just English, improves text-to-image alignment and human-preference scores across three benchmarks.