Ctrlk
For the complete documentation index, see llms.txt. This page is also available as Markdown.

Diffusion Models

Diffusion Model Serving

Image Generation

  • DiFlow: A System for Micro-Serving Text-to-Image Diffusion Workflows (SOSP 2026) [arXiv]

    • HKUST & Alibaba

    • Our work!

    • Decomposes text-to-image diffusion workflows into independently managed model-execution nodes.

    • Enables per-model scaling, cross-workflow model sharing, and adaptive model parallelism for bursty serving workloads.

  • MixFusion: A Patch-Level Parallel Serving System for Mixed-Resolution Diffusion Models (PPoPP 2026) [Paper] [arXiv] [Code]

    • UWaterloo & CMU & Rice

    • Uses patch-level parallelism to batch mixed-resolution text-to-image diffusion requests.

    • Combines patch-tailored cache management with SLO-aware scheduling and online latency prediction.

  • xDiT: an Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism (arXiv:2411.01738) [arXiv] [Code]

    • Tencent

    • Several parallel approaches for DiTs.

  • Katz: Efficient Workflow Serving for Diffusion Models with Many Adapters (ATC 2025) [Paper] [arXiv] [Code] [Trace]

    • HKUST & Alibaba

    • Our work!

    • ControlNet-as-a-Service decouples ControlNets from the base model for caching, parallelization, and sharing.

    • Bounded Asynchronous Loading overlaps LoRA loading with initial denoising steps; latent parallelism accelerates the base model across GPUs.

  • PipeFusion: Displaced Patch Pipeline Parallelism for Inference of Diffusion Transformer Models (arXiv:2405.14430) [arXiv] [Code]

    • Tencent & HKU

  • Cache Me if You Can: Accelerating Diffusion Models through Block Caching (CVPR 2024) [Paper] [Homepage]

    • Meta & TUM & MCML & Oxford

  • DeepCache: Accelerating Diffusion Models for Free (CVPR 2024) [Paper] [Code]

    • NUS

  • DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models (CVPR 2024) [Paper] [Code]

    • MIT & Princeton & Lepton AI & NVIDIA

    • Split the model input into multiple patches and assign each patch to a GPU.

  • Approximate Caching for Efficiently Serving Text-to-Image Diffusion Models (NSDI 2024) [Paper] [Slides]

    • Adobe Research & UIUC

    • Skip a certain number of denoising steps.

Video Generation

  • Quant VideoGen: Auto-Regressive Long Video Generation via 2-Bit KV-Cache Quantization (ICML 2026) [arXiv] [Code]

    • UC Berkeley & MIT & NVIDIA & Amazon & UT Austin

    • Introduces QVG, a training-free 2-bit KV-cache quantization framework for auto-regressive video diffusion models.

    • Combines Semantic-Aware Smoothing with Progressive Residual Quantization to reduce KV-cache memory by up to 7.0x with less than 4% end-to-end latency overhead.

  • StreamDiffusionV2: A Streaming System for Dynamic and Interactive Video Generation (MLSys 2026) [Paper] [arXiv] [Code] [Homepage]

    • UT Austin & UC Berkeley & Nunchaku AI & Stanford & First Intelligence & MIT & Shizuku AI

    • Introduces a training-free streaming pipeline that brings video diffusion models to interactive live generation under time-to-first-frame and per-frame latency SLOs.

    • Combines SLO-aware batching and block scheduling, a rolling KV cache, motion-aware noise control, and multi-GPU pipeline orchestration.

  • Sparse VideoGen2: Accelerate Video Generation with Sparse Attention via Semantic-Aware Permutation (NeurIPS 2025) [arXiv] [Code]

    • UC Berkeley & MIT & NVIDIA & Stanford

    • Introduces SVG2, a training-free sparse-attention framework that clusters and reorders video tokens by semantic similarity.

    • Uses semantic-aware permutation, dynamic top-p budget control, and customized kernels to improve the quality-efficiency trade-off without padding scattered critical tokens.

  • Fast Video Generation with Sliding Tile Attention (ICML 2025) [Paper] [OpenReview] [arXiv] [Code]

    • UCSD & UMich & THU & UC Berkeley & MBZUAI

    • Introduces STA, a tile-wise local spatiotemporal attention mechanism for video DiTs that exploits localized attention score structure.

    • Uses a hardware-aware sliding-window design and kernel optimizations to speed up video diffusion attention and end-to-end HunyuanVideo generation.

  • Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity (ICML 2025) [Paper] [arXiv] [Code]

    • UC Berkeley & MIT & NVIDIA & THU

    • Introduces SVG, a training-free framework that dynamically classifies video DiT attention heads by spatial or temporal sparse patterns.

    • Combines online attention profiling with hardware-aware tensor layouts and customized kernels to accelerate video generation while preserving quality.

  • Looking Backward: Streaming Video-to-Video Translation with Feature Banks (ICLR 2025) [arXiv] [Code] [Homepage]

    • UT Austin & UC Berkeley

    • Introduces StreamV2V, a real-time streaming video-to-video translation system that supports unbounded input streams without diffusion-model fine-tuning.

    • Maintains a compact feature bank of past frames and extends self-attention and feature fusion to preserve temporal consistency at 20 FPS on one A100 GPU.

  • FlexCache: Flexible Approximate Cache System for Video Diffusion (arXiv:2501.04012) [arXiv]

    • UWaterloo

    • Cache for text-to-video diffusion models.

Image Editing

  • FlashPS: Efficient Generative Image Editing with Mask-aware Caching and Scheduling (EuroSys 2026) [Paper] [arXiv] [Code]

    • HKUST & Alibaba

    • Our work!

    • Uses mask-aware caching and scheduling to accelerate generative image editing workloads.

  • CAT-DM: Controllable Accelerated Virtual Try-on with Diffusion Model (CVPR 2024) [Paper] [Code]

    • TJU & Tencent

    • CAT-DM: Controllable Accelerated virtual Try-on with Diffusion Model

Diffusion Model Training

  • DiffusionPipe: Training Large Diffusion Models with Efficient Pipelines (MLSys 2024) [Paper] [Slides]

    • HKU & AWS & OSU

    • Fill the computation of non-trainable model parts into idle periods of the pipeline training of the backbones.

Supporting Add-on Modules

  • X-Adapter: Adding Universal Compatibility of Plugins for Upgraded Diffusion Model (CVPR 2024) [Paper] [Homepage] [Code]

    • NUS & Tencent & FDU

Domain-Specific Accelerator (DSA)

  • Cambricon-D: Full-Network Differential Acceleration for Diffusion Models (ISCA 2024) [Paper]

    • ICT, CAS

Acronyms

  • DiT: Diffusion Transformer

Last updated