H2-Cache: A Novel Hierarchical Dual-Stage Cache for High-Performance Acceleration of Generative Diffusion Models

Documenti analoghi

• GLYPH-SR: Can We Achieve Both High-Quality Image Super-Resolution and High-Fidelity Text Recovery via VLM-guided Latent Diffusion Model?
  di: Sung, Mingyu, et al.
  Pubblicazione: (2025)
• No Pose Estimation? No Problem: Pose-Agnostic and Instance-Aware Test-Time Adaptation for Monocular Depth Estimation
  di: Sung, Mingyu, et al.
  Pubblicazione: (2025)
• SeaCache: Spectral-Evolution-Aware Cache for Accelerating Diffusion Models
  di: Chung, Jiwoo, et al.
  Pubblicazione: (2026)
• Trajectory-Consistent Calibration for Cache-Accelerated Diffusion Models
  di: Liang, Mingyu, et al.
  Pubblicazione: (2026)
• Cache Me if You Can: Accelerating Diffusion Models through Block Caching
  di: Wimbauer, Felix, et al.
  Pubblicazione: (2023)