iteration 200K 500K 9.0 7.0-0.1 7.4 10.7 +0.6 7.5 11.3 FID

Diffusion Transformers (DiTs) deliver state-of-the-art image quality, yet their training remains notoriously slow. A recent remedy--representation alignment (REPA) that matches DiT hidden features to those of a non-generative teacher (e.g., DINO)--dramatically accelerates the early epochs but plateaus or even degrades performance later. We trace this failure to the capacity mismatch: once the generative student begins modeling the joint data distribution, the teacher's lower-dimensional embeddings and attention patterns become a straitjacket rather than a guide. We then introduce HASTE (Holistic Alignment with Stage-wise Termination for Efficient training), a two-phase schedule that keeps the help and drops the hindrance. Phase I applies a holistic alignment loss that simultaneously distills attention maps (relational priors) and feature projections (semantic anchors) from the teacher into mid-level layers of the DiT, yielding rapid convergence. Phase II then performs one-shot termination that deactivates the alignment loss, once a simple trigger such as a fixed iteration is hit, freeing the DiT to focus on denoising and exploit its generative capacity.