AI RESEARCH
AI-T2I: Aggregating-and-Isolating Cross-Attention to Diffusion Models for Text-to-Image Synthesis
arXiv CS.CV
•
ArXi:2605.25763v2 Announce Type: replace Text-to-image synthesis has made significant progress, benefiting from the strong generative capabilities of diffusion models. However, these models struggle to achieve precise text-to-image alignment within cross-attention maps during the denoising process. Existing works primarily focus on inter-subject-token activations (i.e., cross-attention scores) overlap for different subjects, overlooking the intra-subject-token activations scattering issue for identical subjects.