STEDiff improves semantic alignment in text-to-image diffusion models via training-free embedding strengthening with the [EOT] token and a spatial semantic loss, showing gains on T2I-CompBench.
Llm blueprint: Enabling text-to-image generation with complex and detailed prompts,
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
-
STEDiff: Strengthening Text Embedding for Text-to-Image Alignment in Diffusion Model
STEDiff improves semantic alignment in text-to-image diffusion models via training-free embedding strengthening with the [EOT] token and a spatial semantic loss, showing gains on T2I-CompBench.