# SwiftDiffusion: Efficient Diffusion Model Serving with Add-on Modules

arXiv: https://arxiv.org/abs/2407.02031 · HTML: https://mlsanity.com/paper/2407.02031/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models.
- Builds on 19 of its 44 references that are in the map.
- First posted on arXiv 2 Jul 2024.

## Placed in

- Diffusion models / [Diffusion foundations and sampling](https://mlsanity.com/diffusion/diffusion-foundations-and-sampling/)

## Builds on (most cited first, 19 of 19)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [Scaling Autoregressive Models for Content-Rich Text-to-Image Generation](https://mlsanity.com/paper/2206.10789/) (2022)
- [DiffusionDB: A Large-scale Prompt Gallery Dataset for Text-to-Image Generative Models](https://mlsanity.com/paper/2210.14896/) (2022)
- [SpecInfer: Accelerating Generative Large Language Model Serving with Tree-based Speculative Inference and Verification](https://mlsanity.com/paper/2305.09781/) (2023)
- [DeepCache: Accelerating Diffusion Models for Free](https://mlsanity.com/paper/2312.00858/) (2023)
- [Clipper: A Low-Latency Online Prediction Serving System](https://mlsanity.com/paper/1612.03079/) (2016)
- [S-LoRA: Serving Thousands of Concurrent LoRA Adapters](https://mlsanity.com/paper/2311.03285/) (2023)
- [Serving DNNs like Clockwork: Performance Predictability from the Bottom Up](https://mlsanity.com/paper/2006.02464/) (2020)
- [DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models](https://mlsanity.com/paper/2402.19481/) (2024)
- [Punica: Multi-Tenant LoRA Serving](https://mlsanity.com/paper/2310.18547/) (2023)
- [Speed Is All You Need: On-Device Acceleration of Large Diffusion Models via GPU-Aware Optimizations](https://mlsanity.com/paper/2304.11267/) (2023)
- [CaraServe: CPU-Assisted and Rank-Aware LoRA Serving for Generative LLM Inference](https://mlsanity.com/paper/2401.11240/) (2024)

## Built on by (most cited first, 5 of 5)

- [Efficient Diffusion Models: A Survey](https://mlsanity.com/paper/2502.06805/) (2025)
- [DreamFit: Garment-Centric Human Generation via a Lightweight Anything-Dressing Encoder](https://mlsanity.com/paper/2412.17644/) (2024)
- [Parallel Simulation for Log-concave Sampling and Score-based Diffusion Models](https://mlsanity.com/paper/2412.07435/) (2024)
- [FlexCache: Flexible Approximate Cache System for Video Diffusion](https://mlsanity.com/paper/2501.04012/) (2024)
- [Co-occurrence Patterns of LoRA Adapters in Production Diffusion Model Inference Services](https://mlsanity.com/paper/2609.23321/) (2026)

## Abstract (arXiv)

Text-to-image (T2I) generation using diffusion models has become a blockbuster service in today's AI cloud. A production T2I service typically involves a serving workflow where a base diffusion model is augmented with various "add-on" modules, notably ControlNet and LoRA, to enhance image generation control. Compared to serving the base model alone, these add-on modules introduce significant loading and computational overhead, resulting in increased latency. In this paper, we present SwiftDiffusion, a system that efficiently serves a T2I workflow through a holistic approach. SwiftDiffusion decouples ControNet from the base model and deploys it as a separate, independently scaled service on dedicated GPUs, enabling ControlNet caching, parallelization, and sharing. To mitigate the high loading overhead of LoRA serving, SwiftDiffusion employs a bounded asynchronous LoRA loading (BAL) technique, allowing LoRA loading to overlap with the initial base model execution by up to k steps without compromising image quality. Furthermore, SwiftDiffusion optimizes base model execution with a novel latent parallelism technique. Collectively, these designs enable SwiftDiffusion to outperform the state-of-the-art T2I serving systems, achieving up to 7.8x latency reduction and 1.6x throughput improvement in serving SDXL models on H800 GPUs, without sacrificing image quality.