A training-free closed loop, in which a multimodal LLM rewrites a text prompt after inspecting the generated image, improves overall text-to-image alignment but degrades some attribute and spatial categories.
Improving image generation with better captions
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Test-time Prompt Refinement for Text-to-Image Models
A training-free closed loop, in which a multimodal LLM rewrites a text prompt after inspecting the generated image, improves overall text-to-image alignment but degrades some attribute and spatial categories.