Diffusion Model
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.
Key highlights
- 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.
Intuition
This section is available to Pro members. Upgrade to Pro
How it works
This section is available to Pro members. Upgrade to Pro
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
- 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.
- 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.
Common pitfalls
This section is available to Pro members. Upgrade to Pro
Applications
This section is available to Pro members. Upgrade to Pro
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.
- 2.Rombach, R., Blattmann, A., Lorenz, D., Esser, P. & Ommer, B. (2022). High-Resolution Image Synthesis with Latent Diffusion Models. CVPR.
You have read it. What now?
Cite this page
ScholarGate. (2026, June 1). Diffusion Model. ScholarGate. https://scholargate.app/deep-learning/diffusion-model