Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/nus-hpc-ai-lab/awesome-efficient-video-generation
A curated list of recent efficient video generation methods.
https://github.com/nus-hpc-ai-lab/awesome-efficient-video-generation
List: awesome-efficient-video-generation
awesome diffusion-models efficiency high-performance-computing video-generation
Last synced: 22 days ago
JSON representation
A curated list of recent efficient video generation methods.
- Host: GitHub
- URL: https://github.com/nus-hpc-ai-lab/awesome-efficient-video-generation
- Owner: NUS-HPC-AI-Lab
- Created: 2024-11-16T04:49:58.000Z (about 1 month ago)
- Default Branch: main
- Last Pushed: 2024-11-23T08:08:11.000Z (28 days ago)
- Last Synced: 2024-11-23T08:19:40.007Z (28 days ago)
- Topics: awesome, diffusion-models, efficiency, high-performance-computing, video-generation
- Homepage:
- Size: 3.91 KB
- Stars: 5
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
- ultimate-awesome - awesome-efficient-video-generation - A curated list of recent efficient video generation methods. (Other Lists / Monkey C Lists)
README
# Awesome Efficient Video Generation
[](https://github.com/sindresorhus/awesome)
[](https://github.com/Naereen/StrapDown.js/graphs/commit-activity)
[](https://github.com/xuyang-liu16/Awesome-Diffusion-Acceleration)
[](https://github.com/NUS-HPC-AI-Lab/Awesome-Efficient-Video-Generation.git)
A curated list of recent efficient video generation methods.
## 🗂️ Table of Contents
- [Scheduler](#scheduler)
- [Distillation](#distillation)
- [Quantization](#quantization)
- [Caching](#caching)
- [Pruning](#pruning)
- [Parallelism](#parallelism)
- [Others](#others)
## 📄 Papers
### Scheduler
* [Pyramidal Flow Matching for Efficient Video Generative Modeling](https://arxiv.org/abs/2410.05954) \
arXiv 2024 | [Paper](https://arxiv.org/abs/2410.05954) | [Code](https://github.com/jy0205/Pyramid-Flow) | 
* [AdaDiff: Adaptive Step Selection for Fast Diffusion Models](https://arxiv.org/pdf/2311.14768) \
arXiv 2023 | [Paper](https://arxiv.org/pdf/2311.14768)
* [Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference](https://arxiv.org/abs/2310.04378) \
ICLR 2024 | [Paper](https://arxiv.org/abs/2310.04378) | [Code](https://github.com/luosiallen/latent-consistency-model) | 
* [DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models](https://arxiv.org/abs/2211.01095) \
arXiv 2022 | [Paper](https://arxiv.org/abs/2211.01095) | [Code](https://github.com/LuChengTHU/dpm-solver) | 
* [Flow Matching for Generative Modeling](https://arxiv.org/abs/2210.02747) \
ICLR 2023 (Spotlight) | [Paper](https://arxiv.org/abs/2210.02747)
* [Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow](https://arxiv.org/abs/2209.03003) \
ICLR 2023 (Spotlight) | [Paper](https://arxiv.org/abs/2209.03003) | [Code](https://github.com/gnobitab/RectifiedFlow) | 
* [DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps](https://arxiv.org/abs/2206.00927) \
NeurIPS 2022 | [Paper](https://arxiv.org/abs/2206.00927) | [Code](https://github.com/LuChengTHU/dpm-solver) | 
* [Denoising Diffusion Implicit Models](https://arxiv.org/pdf/2010.02502) \
ICLR 2021 | [Paper](https://arxiv.org/pdf/2010.02502) | [Code](https://github.com/ermongroup/ddim) | 
### Distillation
* [Distilling Diffusion Models into Conditional GANs](https://arxiv.org/abs/2405.05967) \
ECCV 2024 | [Paper](https://arxiv.org/abs/2405.05967)
* [Improved Distribution Matching Distillation for Fast Image Synthesis](https://arxiv.org/abs/2405.14867) \
NeurIPS 2024 (Oral) | [Paper](https://arxiv.org/abs/2405.14867) | [Code](https://github.com/tianweiy/DMD2) | 
* [Fast High-Resolution Image Synthesis with Latent Adversarial Diffusion Distillation](https://arxiv.org/abs/2403.12015) \
arXiv 2024 | [Paper](https://arxiv.org/abs/2403.12015)
* [LCM-LoRA: A Universal Stable-Diffusion Acceleration Module](https://arxiv.org/abs/2311.05556) \
arXiv 2023 | [Paper](https://arxiv.org/abs/2311.05556) | [Code](https://github.com/luosiallen/latent-consistency-model) | 
* [One-step Diffusion with Distribution Matching Distillation
](https://arxiv.org/abs/2311.18828) \
CVPR 2024 | [Paper](https://arxiv.org/abs/2311.18828)
* [Adversarial Diffusion Distillation](https://arxiv.org/abs/2311.17042) \
ECCV 2024 | [Paper](https://arxiv.org/abs/2311.17042)
### Quantization
### Caching
* [Adaptive Caching for Faster Video Generation with Diffusion Transformers](https://arxiv.org/abs/2411.02397) \
arXiv 2024 | [Paper](https://arxiv.org/abs/2411.02397) | [Code](https://github.com/Shenyi-Z/ToCa) | 
* [FasterCache: Training-Free Video Diffusion Model Acceleration with High Quality](https://arxiv.org/abs/2410.19355) \
arXiv 2024 | [Paper](https://arxiv.org/abs/2410.19355) | [Code](https://github.com/Vchitect/FasterCache) | 
* [Accelerating Diffusion Transformers with Token-wise Feature Caching](https://arxiv.org/abs/2410.05317) \
arXiv 2024 | [Paper](https://arxiv.org/abs/2410.05317) | [Code](https://github.com/AdaCache-DiT/AdaCache) | 
* [Real-Time Video Generation with Pyramid Attention Broadcast](https://arxiv.org/abs/2408.12588) \
arXiv 2024 | [Paper](https://arxiv.org/abs/2408.12588) | [Code](https://github.com/NUS-HPC-AI-Lab/VideoSys) | 
* [∆-DiT: A Training-Free Acceleration Method Tailored for Diffusion Transformers](https://arxiv.org/abs/2406.01125) \
arXiv 2024 | [Paper](https://arxiv.org/abs/2406.01125)
* [DiTFastAttn: Attention Compression for Diffusion Transformer Models](https://arxiv.org/abs/2406.08552) \
arXiv 2024 | [Paper](https://arxiv.org/abs/2406.08552) | [Code](https://github.com/thu-nics/DiTFastAttn) | 
* [Faster Diffusion via Temporal Attention Decomposition](https://arxiv.org/abs/2404.02747v2) \
arXiv 2024 | [Paper](https://arxiv.org/abs/2404.02747v2) | [Code](https://github.com/HaozheLiu-ST/T-GATE) | 
* [Cross-Attention Makes Inference Cumbersome in Text-to-Image Diffusion Models](https://arxiv.org/abs/2404.02747v1) \
arXiv 2024 | [Paper](https://arxiv.org/abs/2404.02747v1) | [Code](https://github.com/HaozheLiu-ST/T-GATE) | 
### Pruning
### Parallelism
* [xDiT: an Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism](https://arxiv.org/abs/2405.14430) \
arXiv 2024 | [Paper](https://arxiv.org/abs/2405.14430) | [Code](https://github.com/xdit-project/xDiT) | 
* [PipeFusion: Patch-level Pipeline Parallelism for Diffusion Transformers Inference](https://arxiv.org/abs/2405.14430) \
arXiv 2024 | [Paper](https://arxiv.org/abs/2405.14430) | [Code](https://github.com/xdit-project/xDiT) | 
* [DSP: Dynamic Sequence Parallelism for Multi-Dimensional Transformers](https://arxiv.org/abs/2403.10266) \
arXiv 2024 | [Paper](https://arxiv.org/abs/2403.10266) | [Code](https://github.com/NUS-HPC-AI-Lab/VideoSys) | 
* [DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models](https://arxiv.org/abs/2402.19481) \
CVPR 2024 (Highlight) | [Paper](https://arxiv.org/abs/2402.19481) | [Code](https://github.com/mit-han-lab/distrifuser) | 
### Others