Skip to main content
Search

Qinghai Institute of Technology

1 related articles

Subscribe to updates
  1. arXiv

    Diffusion Transformers at 4K stop losing semantics: text attention stays global while image attention returns to training scale

    Diffusion Transformer (DiT) text-to-image models degrade semantically beyond their training resolution, and generated content loses recognizable meaning. A training-free framework keeps attention for text tokens global while confining the receptive field of image tokens to the training-resolution scale, then corrects high-frequency detail along the denoising trajectory with cross-scale and cross-temporal guidance. On Flux.1.0-dev, the method beats the listed training-free approaches on FID, KID and their patch-level versions FIDp and KIDp at 2048×2048, 2048×4096 and 4096×4096, and runs 4096×4096 inference in 14.7 time units, whereas ScaleDiff runs out of memory at that resolution.

You’re all caught up