# LegoDiffusion: Micro-Serving Text-to-Image Diffusion Workflows

arXiv: https://arxiv.org/abs/2604.08123 · HTML: https://mlsanity.com/paper/2604.08123/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models.
- Builds on 26 of its 75 references that are in the map.
- First posted on arXiv 9 Apr 2026.

## Placed in

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

## Builds on (most cited first, 26 of 26)

- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [SGLang: Efficient Execution of Structured Language Model Programs](https://mlsanity.com/paper/2312.07104/) (2023)
- [Ray: A Distributed Framework for Emerging AI Applications](https://mlsanity.com/paper/1712.05889/) (2017)
- [Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve](https://mlsanity.com/paper/2403.02310/) (2024)
- [CacheBlend: Fast Large Language Model Serving for RAG with Cached Knowledge Fusion](https://mlsanity.com/paper/2405.16444/) (2024)
- [BrushNet: A Plug-and-Play Image Inpainting Model with Decomposed Dual-Branch Diffusion](https://mlsanity.com/paper/2403.06976/) (2024)
- [Clipper: A Low-Latency Online Prediction Serving System](https://mlsanity.com/paper/1612.03079/) (2016)
- [OOTDiffusion: Outfitting Fusion based Latent Diffusion for Controllable Virtual Try-on](https://mlsanity.com/paper/2403.01779/) (2024)
- [Serving DNNs like Clockwork: Performance Predictability from the Bottom Up](https://mlsanity.com/paper/2006.02464/) (2020)
- [LoongServe: Efficiently Serving Long-Context Large Language Models with Elastic Sequence Parallelism](https://mlsanity.com/paper/2404.09526/) (2024)
- [Parrot: Efficient Serving of LLM-based Applications with Semantic Variable](https://mlsanity.com/paper/2405.19888/) (2024)
- [xDiT: an Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism](https://mlsanity.com/paper/2411.01738/) (2024)
- [Helix: Serving Large Language Models over Heterogeneous GPUs and Network via Max-Flow](https://mlsanity.com/paper/2406.01566/) (2024)
- [MuxServe: Flexible Spatial-Temporal Multiplexing for Multiple LLM Serving](https://mlsanity.com/paper/2404.02015/) (2024)
- [Teola: Towards End-to-End Optimization of LLM-based Applications](https://mlsanity.com/paper/2407.00326/) (2024)
- [Characterizing Mobile SoC for Accelerating Heterogeneous LLM Inference](https://mlsanity.com/paper/2501.14794/) (2025)
- [DeltaZip: Efficient Serving of Multiple Full-Model-Tuned LLMs](https://mlsanity.com/paper/2312.05215/) (2023)
- [JITServe: SLO-aware LLM Serving with Imprecise Request Information](https://mlsanity.com/paper/2504.20068/) (2025)
- [IC-Cache: Efficient Large Language Model Serving via In-context Caching](https://mlsanity.com/paper/2501.12689/) (2025)
- [Autothrottle: A Practical Bi-Level Approach to Resource Management for SLO-Targeted Microservices](https://mlsanity.com/paper/2212.12180/) (2022)
- [Following the Data, Not the Function: Rethinking Function Orchestration in Serverless Computing](https://mlsanity.com/paper/2109.13492/) (2021)
- [Towards Pareto Optimal Throughput in Small Language Model Serving](https://mlsanity.com/paper/2404.03353/) (2024)
- [TetriServe: Efficiently Serving Mixed DiT Workloads](https://mlsanity.com/paper/2510.01565/) (2025)
- [TridentServe: A Stage-level Serving System for Diffusion Pipelines](https://mlsanity.com/paper/2510.02838/) (2025)

## Abstract (arXiv)

Text-to-image generation executes a diffusion workflow comprising multiple models centered on a base diffusion model. Existing serving systems treat each workflow as an opaque monolith, provisioning, placing, and scaling all constituent models together, which obscures internal dataflow, prevents model sharing, and enforces coarse-grained resource management. In this paper, we make a case for micro-serving diffusion workflows with LegoDiffusion, a system that decomposes a workflow into loosely coupled model-execution nodes that can be independently managed and scheduled. By explicitly managing individual model inference, LegoDiffusion unlocks cluster-scale optimizations, including per-model scaling, model sharing, and adaptive model parallelism. Collectively, LegoDiffusion outperforms existing diffusion workflow serving systems, sustaining up to 3x higher request rates and tolerating up to 8x higher burst traffic.