Jun 2026
Intermediate Text Representation Guided Text-to-Image Generation for Enhancing One-and-Only Alignment
Intermediate Text Representation (IR)-guided diffusion is proposed, which injects intermediate hidden states of the text encoder into the conditioning signal during early denoising steps, recovering suppressed concepts without any additional training, optimization, or external models.
Soyoun Won, Aryan Yazdan Parast, Basim Azam et al.
· arXiv.org · 0 citations