확산 모델은 최첨단 이미지 생성 성능을 제공하지만, 높은 메모리 연산 요구로 인해 운용 비용이 매우 크다. 본 연구는 SDXL을 위한 웨이블릿 기반 저비트 양자화 파이프라인을 제안하며, 가중치 중심 채널별 평활화와 U-Net 중간 특징맵에 적용하는 DWT를 결합한다. DWT는 에너지를 LL 서브밴드에 집중시켜 구조적 정보를 보존하고, 서브밴드 특성에 따라 비트폭을 달리하는 차등 양자화를 가능하게 한다. 또한 제안한 평활화는 가중치 중심의 스케일 재배치를 통해 활성값 이상치의 영향을 완화한다. RTX 6000 GPU에서 실험한 결과, 제안한 Wavelet-INT4 모델은 최대 VRAM을 약 70% 절감하고, 1024×1024 해상도에서 FP32 대비 1.24배 빠른 추론을 달성했으며, 동일 프롬프트에서 CLIP-FID 차이 5 이하로 품질도 유지했다. 이는 특징맵에 대한 웨이블릿 분석과 가중치 중심 평활화의 결합이 품질, 속도, 메모리 효율 사이의 균형을 개선하여, 소비자용 GPU 환경에서도 실용적인 저비트 확산 모델 운용 가능성을 보여줌을 의미한다.
Keyword
확산 모델, 경량화, 양자화, 저비트, 웨이블릿 변환
This work is distributed under the term of Creative Commons License (CCL)
(CC BY NC)
Copyright Policy
ETRI KSP Copyright Policy
The materials provided on this website are subject to copyrights owned by ETRI and protected by the Copyright Act. Any reproduction, modification, or distribution, in whole or in part, requires the prior explicit approval of ETRI. However, under Article 24.2 of the Copyright Act, the materials may be freely used provided the user complies with the following terms:
The materials to be used must have attached a Korea Open Government License (KOGL) Type 4 symbol, which is similar to CC-BY-NC-ND (Creative Commons Attribution Non-Commercial No Derivatives License). Users are free to use the materials only for non-commercial purposes, provided that original works are properly cited and that no alterations, modifications, or changes to such works is made. This website may contain materials for which ETRI does not hold full copyright or for which ETRI shares copyright in conjunction with other third parties. Without explicit permission, any use of such materials without KOGL indication is strictly prohibited and will constitute an infringement of the copyright of ETRI or of the relevant copyright holders.
J. Kim et. al, "Trends in Lightweight Kernel for Many core Based High-Performance Computing", Electronics and Telecommunications Trends. Vol. 32, No. 4, 2017, KOGL Type 4: Source Indication + Commercial Use Prohibition + Change Prohibition
J. Sim et.al, “the Fourth Industrial Revolution and ICT – IDX Strategy for leading the Fourth Industrial Revolution”, ETRI Insight, 2017, KOGL Type 4: Source Indication + Commercial Use Prohibition + Change Prohibition
If you have any questions or concerns about these terms of use, or if you would like to request permission to use any material on this website, please feel free to contact us
KOGL Type 4:(Source Indication + Commercial Use Prohibition+Change Prohibition)
Contact ETRI, Research Information Service Section
Privacy Policy
ETRI KSP Privacy Policy
ETRI does not collect personal information from external users who access our Knowledge Sharing Platform (KSP). Unathorized automated collection of researcher information from our platform without ETRI's consent is strictly prohibited.
[Researcher Information Disclosure] ETRI publicly shares specific researcher information related to research outcomes, including the researcher's name, department, work email, and work phone number.
※ ETRI does not share employee photographs with external users without the explicit consent of the researcher. If a researcher provides consent, their photograph may be displayed on the KSP.