Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Diffusion model papers, survey, and taxonomy
| Date | Stars |
|---|---|
| 2026-07-24 | 3362 |
| 2026-07-25 | 3362 |
| 2026-07-28 | 3362 |
| 2026-07-30 | 3362 |
| 2026-07-31 | 3365 |
| 2026-08-06 | 3365 |
Today
— stars today
This week
+3 stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.09%/day
# Diffusion Models: A Comprehensive Survey of Methods and Applications
This repo is constructed for collecting and categorizing papers about diffusion models according to our survey paper——[_**Diffusion Models: A Comprehensive Survey of Methods and Applications**_](https://arxiv.org/abs/2209.00796), which has been accepted by the journal **ACM Computing Surveys**. Considering the fast development of this field, we will continue to update **both [arxiv paper](https://arxiv.org/abs/2209.00796) and this repo**.
# Overview
<div aligncenter><img width="900" alt="image" src="https://user-images.githubusercontent.com/62683396/227244860-3608bf02-b2af-4c00-8e87-6221a59a4c42.png">
# Catalogue
## [Algorithm Taxonomy](#1)
### [Sampling-Acceleration Enhancement](#1.1)
- [Learning-Free Sampling](#1.1.1)
- [SDE Solver](#1.1.1.1)
- [ODE Solver](#1.1.1.2)
- [Learning-Based Sampling](#1.1.2)
- [Optimized Discretization](#1.1.2.1)
- [Knowledge Distillation](#1.1.2.2)
- [Truncated Diffusion](#1.1.2.3)
### [Likelihood-Maximization Enhancement](#1.2)
- [Noise Schedule Optimization](#1.2.1)
- [Reverse Variance Learning](#1.2.2)
- [Exact Likelihood Computation](#1.2.3)
### [Data with Special Structures](#1.3)
- [Data with Manifold Structures](#1.3.1)
- [Known Manifolds](#1.3.1.1)
- [Learned Manifolds](#1.3.1.2)
- [Data with Invariant Structures](#1.3.2)
- [Discrete Data](#1.3.3)
### [Diffusion with (Multimodal) LLM](#1.4)
- [Simple Combination](#1.4.1)
- [Deep Collaboration](#1.4.2)
### [Diffusion with DPO/RLHF](#1.5)
## [Application Taxonomy](#2)
* [Computer Vision](#2.1)
- [Image Super Resolution, Inpainting and Translation](#2.1.1)
- [Semantic Segementation](#2.1.2)
- [Video Generation](#2.1.3)
- [3D Generation](#2.1.4)
- [Anomaly Detection](#2.1.5)
- [Object Detection](#2.1.6)
* [Natural Language Processing](#2.2)
* [Temporal Data Modeling](#2.3)
- [Time-Series Imputation](#2.3.1)
- [Time-Seires Forecasting](#2.3.2)
- [Waveform Signal Processing](#2.3.3)
* [Multi-Modal Learning](#2.4)
- [Text-to-Image Generation](#2.4.1)
- [Text-to-3D Generation](#2.4.2)
- [Scene Graph/Layout to Image Generation](#2.4.3)
- [Text-to-Audio Generation](#2.4.4)
- [Text-to-Motion Generation](#2.4.5)
- [Text-to-Video Generation/Editting](#2.4.6)
* [Robust Learning](#2.5)
- [Data Purification](#2.5.1)
- [Generating Synthetic Data for Robust Learning](#2.5.2)
* [Molecular Graph Modeling](#2.6)
* [Material Design](#2.7)
* [Medical Image Reconstruction](#2.8)
## [Connections with Other Generative Models](#3)
* [Variational Autoencoder](#3.1)
* [Generative Adversarial Network](#3.2)
* [Normalizing Flow](#3.3)
* [Autoregressive Models](#3.4)
* [Energy-Based Models](#3.5)
<p id="1"></p >
## Algorithm Taxonomy
<p id="1.1"></p >
### 1. Efficient Sampling
<p id="1.1.1"></p >
#### 1.1 Learning-Free Sampling
<p id="1.1.1.1"></p >
##### 1.1.1 SDE Solver
[Score-Based Generative Modeling
through Stochastic Differential Equations](https://openreview.net/forum?id=PxTIG12RRHS)
[Adversarial score matching and improved sampling for image generation](https://openreview.net/forum?id=eLfqMl3z3lq)
[Come-closer-diffuse-faster: Accelerating conditional diffusion models for inverse
problems through stochastic contraction](https://openaccess.thecvf.com/content/CVPR2022/html/Chung_Come-Closer-Diffuse-Faster_Accelerating_Conditional_Diffusion_Models_for_Inverse_Problems_Through_Stochastic_CVPR_2022_paper.html)
[Score-Based Generative Modeling with Critically-Damped Langevin Diffusion](https://openreview.net/forum?id=CzceR82CYc)
[ Gotta Go Fast When Generating Data with
Score-Based Models](https://arxiv.org/abs/2105.14080)
[Elucidating the Design Space of Diffusion-Based Generative Models](https://arxiv.org/abs/2206.00364)
[Generative modeling by estimating gradients of the data distribution](https://proceedings.neurips.cc/paper/2019/hash/3001ef257407d5a371a96dcd947c7d93-Abstract.html)
[Structure-GuiExcerpt of 40,465 characters
Read on GitHub
Ling Yang
78
balabala
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:3d5d87f759c6cff8, topic:stable-diffusion, topic:diffusion-models, topic:text-to-image
matched fp:3d5d87f759c6cff8, topic:text-to-video, topic:text-to-3d, readme:video generation