AViTS: Adaptive Spatiotemporal Token Selection for Efficient Dynamic-Resolution Generation

2026-08-18

AI Summary

为解决扩散变换模型中因均匀上采样导致的冗余计算和细节一致性问题，提出AViTS框架，通过自适应时空令牌选择减少高分辨率计算并提高效率。

Abstract

Diffusion Transformers (DiTs) achieve high-quality generation but are costly due to iterative sampling. Dynamic-resolution sampling reduces early-stage cost by denoising at low resolution; however, uniformly upsampling all latent tokens at resolution transitions incurs redundant computation and may degrade fine-detail consistency. Existing partial upsampling strategies typically rely on local latent structure cues or single-step statistics, making it difficult to jointly capture token-text semantic relevance and token-wise representation dynamics across diffusion steps. We propose AViTS, an adaptive spatiotemporal token selection framework for dynamic-resolution DiTs. AViTS models spatial importance via latent-text attention and temporal importance via token-level feature variation across diffusion timesteps, and fuses them to enable spatiotemporal importance-aware selective upsampling: it prioritizes resolution refinement for critical tokens while deferring less important ones, thereby reducing redundant high-resolution computation and improving the quality-efficiency trade-off. AViTS achieves up to 6.34x on FLUX and nearly 9x FLOPs reduction on Qwen-Image-Edit and FLUX.1-Kontext-dev, orthogonal to distillation, quantization, and feature caching, and reaching 14.76x with distilled models. Code: https://github.com/QHR69/AViTS

Problem

• Diffusion Transformers
• Dynamic-resolution Sampling
• Spatiotemporal Token Selection
• Redundant Computation
• Fine-detail Consistency

Innovation

• Adaptive Spatiotemporal Token Selection
• Dynamic-Resolution Generation
• Diffusion Transformers
• Latent-Text Attention
• Token-Level Feature Variation