Skip to contentScholarGate
LibraryBookshelfDeskReview StudioAssistant
Sign in
On this page
IntuitionHow it worksWhen to use itStrengths & limitationsCommon pitfallsApplicationsFrequently asked🔒 Read the full methodSourcesRelated methods
Cite this pageSpotted an issue on this page? Report or suggest a fix →
Home›Deep learning›Diffusion Model
Machine learning

Diffusion Model

Denoising Diffusion Probabilistic Model (DDPM / Latent Diffusion) · Also known as: Difüzyon Modeli (DDPM / Stable Diffusion), difüzyon modeli, denoising diffusion model, DDPM, Stable Diffusion, latent diffusion model

A diffusion model is a generative deep-learning method, introduced by Ho, Jain and Abbeel in 2020 (DDPM), that learns to produce high-quality images, audio and molecular structures by reversing a step-by-step noising process. It has largely displaced GANs as the current state of the art in generative modelling.

ScholarGate
  1. Machine learning
  2. v1
  3. 2 Sources
  4. PUBLISHED
Cite this page →
Tools & resources
Download slides
Learn & explore

Read the full method

Members only

Sign in with a free account to read this section.

Sign in

Method map

The neighbourhood of related methods — select a node to explore.

Diffusion Model
Neural ODEPrincipal Component Anal…Score-Based Generative M…Variational AutoencoderExplainable GANGenerative Adversarial N…Normalizing FlowsVision TransformerWasserstein GANWeakly Supervised Diffus…

+1 more

When to use it

Use a diffusion model when you need to generate high-fidelity images, audio, or molecular structures and have a large dataset (around 1000 samples or more) or access to a pretrained model. It assumes substantial data or pretraining and requires GPU/TPU hardware; inference can be slow because sampling iterates over many denoising steps. With fewer than about 1000 samples the model cannot learn the denoising process well, and a simpler generator such as a variational autoencoder is safer.

Strengths & limitations

Strengths
  • Produces higher-quality and more diverse samples than GANs across images, audio and molecules.
  • Training is stable, avoiding the mode collapse and adversarial instability that plague GANs.
  • Latent-diffusion variants make high-resolution generation computationally tractable.
  • Naturally supports conditional generation, such as text-to-image prompting.
Limitations
  • Requires a large dataset or a pretrained model — small data leads to poor generation quality.
  • GPU/TPU hardware is required for training and practical use.
  • Inference is slow because sampling iterates over many denoising steps.
  • Below about 1000 samples the denoising process cannot be learned reliably.

Frequently asked

How is a diffusion model different from a GAN?

Both are generative, but a GAN trains a generator against a discriminator, which can be unstable and prone to mode collapse. A diffusion model instead learns to reverse a noising process step by step, giving more stable training and typically higher-quality, more diverse samples.

How much data do I need?

Training from scratch generally needs around 1000 samples or more; below that the denoising process cannot be learned well. With small data, fine-tune a pretrained model or use a simpler generator such as a variational autoencoder.

Why is generation slow?

Sampling starts from noise and applies the learned denoising step many times in sequence, so producing one sample requires many network passes. Latent-diffusion variants reduce the cost by working in a compressed latent space.

Do I need special hardware?

Yes. Diffusion models require GPU or TPU hardware for training and for practical inference; CPU-only use is generally impractical.

Sources

  1. Ho, J., Jain, A. & Abbeel, P. (2020). Denoising Diffusion Probabilistic Models. NeurIPS. link ↗
  2. Rombach, R., Blattmann, A., Lorenz, D., Esser, P. & Ommer, B. (2022). High-Resolution Image Synthesis with Latent Diffusion Models. CVPR. link ↗

How to cite this page

ScholarGate. (2026, June 1). Denoising Diffusion Probabilistic Model (DDPM / Latent Diffusion). ScholarGate. https://scholargate.app/en/deep-learning/diffusion-model

Related methods

Neural ODEPrincipal Component AnalysisScore-Based Generative ModelVariational Autoencoder

Which method?

Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.

  • Neural ODEDeep learning↔ compare
  • Principal Component AnalysisMachine learning↔ compare
  • Score-Based Generative ModelDeep learning↔ compare
  • Variational AutoencoderDeep learning↔ compare
Compare side by side →

Referenced by

Explainable GANGenerative Adversarial NetworkNormalizing FlowsVariational AutoencoderVision TransformerWasserstein GANWeakly Supervised Diffusion ModelWeakly supervised GAN

Similar methods

Multimodal Diffusion ModelLatent Diffusion ModelsSelf-supervised Diffusion ModelSemi-supervised Diffusion ModelExplainable Diffusion ModelScore-Based Generative ModelDomain-adaptive diffusion modelFine-Tuned Diffusion Model

Related reference concepts

Deep Generative ModelsDeep LearningStochastic OptimizationBackpropagation and OptimizationDeep Reinforcement LearningMachine Learning

Spotted an issue on this page? Report or suggest a fix →

ScholarGate — Diffusion Model (Denoising Diffusion Probabilistic Model (DDPM / Latent Diffusion)). Retrieved 2026-07-21 from https://scholargate.app/en/deep-learning/diffusion-model · Dataset: https://doi.org/10.5281/zenodo.20539026
Quick facts
Originator
Ho, J., Jain, A. & Abbeel, P.
Year
2020
Type
Generative deep learning (denoising diffusion)
Task
Generation of images, audio and molecular structures
MinSample
1000
Related methods
Neural ODEPrincipal Component AnalysisScore-Based Generative ModelVariational Autoencoder
ScholarGate

A content-first reference library for research methods — what each one is, how it works, and where it comes from.

Open data (CC-BY)

Explore

  • Library
  • Search the library…
  • Browse by field
  • Fields
  • Journey
  • Compare
  • Which method?

Reference

  • Subjects
  • Atlas
  • Glossary
  • Methodology
  • Philosophy

Your tools

  • Bookshelf
  • Desk
  • Chat

Company

  • About
  • Pricing
  • Contact
  • Suggest a method

Entries are compiled from published sources for reference. Verifying the accuracy and suitability of any information for your own use remains your responsibility.

© 2026 ScholarGate · A research-method reference library
  • Privacy
  • Cookies
  • Terms
  • Delete account