STEDiff: Strengthening Text Embedding for Text-to-Image Alignment in Diffusion Model
Researchers have introduced STEDiff, a novel training-free method to improve the semantic alignment of text-to-image diffusion models. This approach enhances text embeddings by leveraging the [EOT] token to strengthen sub-sentence semantics and incorporates a semantic enhancement loss for precise spatial mapping of entities. Evaluations on the T2I-CompBench show STEDiff significantly boosts semantic consistency and generation quality for complex prompts. AI
IMPACT Improves semantic accuracy in text-to-image generation, enabling more faithful rendering of complex prompts.