Compute Only 16 Tokens in One Timestep: Accelerating Diffusion Transformers with Cluster-Driven Feature Caching
Open Access
- 27 October 2025
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 10181-10189
Abstract
No abstract availableAll Related Versions
This publication has 12 references indexed in Scilit:
- Timestep Embedding Tells: It’s Time to Cache for Video Diffusion Model2025
- Ditto: Accelerating Diffusion Model via Temporal Value Similarity2025
- Cache Me if You Can: Accelerating Diffusion Models through Block Caching2024
- DeepCache: Accelerating Diffusion Models for Free2024
- VBench: Comprehensive Benchmark Suite for Video Generative Models2024
- Scalable Diffusion Models with Transformers2023
- Q-Diffusion: Quantizing Diffusion Models2023
- Post-Training Quantization on Diffusion Models2023
- Token Merging for Fast Stable Diffusion2023
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015