TQ-DiT: Efficient Time-Aware Quantization for Diffusion Transformers
Diffusion transformers (DiTs) combine transformer architectures with diffusion models. However, their computational complexity imposes significant limitations on real-time applications and sustainability of AI systems. In this study, we aim to enhance the computational efficiency through model quantization, which represents the weights and activation values with lower precision. Multi-region quantization (MRQ) is introduced to address the asymmetric distribution of network values in DiT blocks by allocating two scaling parameters to sub-regions. Additionally, time-grouping quantization (TGQ) is proposed to reduce quantization error caused by temporal variation in activations. The experimental results show that the proposed algorithm achieves performance comparable to the original full-precision model with only a 0.29 increase in FID at W8A8. Furthermore, it outperforms other baselines at W6A6, thereby confirming its suitability for low-bit quantization. These results highlight the potential of our method to enable efficient real-time generative models.
Code (0)
등록된 구현이 없습니다.
Tasks
Computational EfficiencyQuantizationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
TaQ-DiT: Time-aware Quantization for Diffusion Transformers
Transformer-based diffusion models, dubbed Diffusion Transformers (DiTs), have achieved state-of-the-art performance in image and video generation tasks. However, their large model size and slow inference speed limit the…
DenoisingModel CompressionQuantizationVideo GenerationEffective Quantization for Diffusion Models on CPUs
Diffusion models have gained popularity for generating images from textual descriptions. Nonetheless, the substantial need for computational resources continues to present a noteworthy challenge, contributing to time-con…
QuantizationSemanticDialect: Semantic-Aware Mixed-Format Quantization for Video Diffusion Transformers
Diffusion Transformers (DiTs) achieve state-of-the-art video generation quality, but their substantial memory and computational footprints hinder edge deployment. Quantization can reduce these costs, yet existing methods…
Video GenerationViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation
Diffusion transformers (DiTs) have exhibited remarkable performance in visual generation tasks, such as generating realistic images or videos based on textual instructions. However, larger model sizes and multi-frame pro…
QuantizationVideo GenerationConvRot: Rotation-Based Plug-and-Play 4-bit Quantization for Diffusion Transformers
Diffusion transformers have demonstrated strong capabilities in generating high-quality images. However, as model size increases, the growing memory footprint and inference latency pose significant challenges for practic…