Diffusion Models
Last updated
Was this helpful?
Last updated
Was this helpful?
PatchedServe: A Patch Management Framework for SLO-Optimized Hybrid Resolution Diffusion Serving (arXiv:2501.09253) []
UWaterloo & CMU & Rice
Serve requests with hybrid resolutions.
FlexCache: Flexible Approximate Cache System for Video Diffusion (arXiv:2501.04012) []
UWaterloo
Cache for text-to-video diffusion models.
xDiT: an Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism (arXiv:2411.01738) [] []
Tencent
Several parallel approaches for DiTs.
SwiftDiffusion: Efficient Diffusion Model Serving with Add-on Modules (arXiv:2407.02031) []
HKUST & Alibaba
PipeFusion: Displaced Patch Pipeline Parallelism for Inference of Diffusion Transformer Models (arXiv:2405.14430) [] []
Tencent & HKU
Cache Me if You Can: Accelerating Diffusion Models through Block Caching () [] []
Meta & TUM & MCML & Oxford
CAT-DM: Controllable Accelerated Virtual Try-on with Diffusion Model () [] []
TJU & Tencent
CAT-DM: Controllable Accelerated virtual Try-on with Diffusion Model
DeepCache: Accelerating Diffusion Models for Free () [] []
NUS
DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models () [] []
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 () [] []
Adobe Research & UIUC
Skip a certain number of denoising steps.
HKU & AWS & OSU
Fill the computation of non-trainable model parts into idle periods of the pipeline training of the backbones.
NUS & Tencent & FDU
ICT, CAS
DiT: Diffusion Transformer
DiffusionPipe: Training Large Diffusion Models with Efficient Pipelines () [] []
X-Adapter: Adding Universal Compatibility of Plugins for Upgraded Diffusion Model () [] [] []
Cambricon-D: Full-Network Differential Acceleration for Diffusion Models () []