Models & inference · Glossary term
What is Diffusion Model?
A generative model trained around a progressive noising process and a learned reverse process. Sampling usually begins from noise and applies repeated denoising steps, sometimes in a learned latent space.
“A model that generates images from noise.”
What is the common confusion about Diffusion Model?
Diffusion is a general generative framework, not an image-only technique.
Learn Diffusion Model in the course
Lessons that name Diffusion Model in a title or section
- Image Generation — Diffusion Models
A diffusion model learns to denoise. Train it to remove a tiny bit of noise from a noisy image, repeat that backwards a thousand times, and you have an image generator.
- Diffusion Models — DDPM from Scratch
Ho, Jain, Abbeel (2020) gave the field a recipe it could not quit. Destroy the data with noise over a thousand small steps. Train one neural net to predict the noise. Reverse the process at inference.
- Sampling Methods
Sampling is how AI explores the space of possibilities. Language: Python Implement inverse CDF, rejection, and importance sampling from scratch using only uniform random numbers.
Covered in Phase 01: Math Foundations, Phase 04: Computer Vision and Phase 08: Generative AI.
Related terms
- Latent SpaceA learned representation space whose coordinates encode factors useful to a model. It may be lower-dimensional than the input, but…
- VAE (Variational Autoencoder)A latent-variable model trained with a reconstruction objective and a regularization term that keeps an approximate posterior close to a…
- InferenceExecuting a trained model to produce predictions, scores, embeddings, or generated tokens without performing an ordinary training update…
- GAN (Generative Adversarial Network)A generator network tries to create realistic data while a discriminator network tries to tell real from fake.
More terms in Models & inference
- Attention
- Autoregressive
- CNN (Convolutional Neural Network)
- CUDA
- Decoder
- Decoding Strategy
- Encoder
- GAN (Generative Adversarial Network)
- GPT
- Inductive Bias
- Inference
- KV Cache
- LLM (Large Language Model)
- Logits
- MoE (Mixture of Experts)
- Nucleus Sampling (Top-p)
- Parameter
- Perplexity
- Quantization
- Self-Attention
- Speculative Decoding
- Stop Sequence
- Streaming
- Temperature
- Time to First Token (TTFT)
- Top-k Sampling
- Transformer
- VAE (Variational Autoencoder)
This entry comes from glossary/terms.md on GitHub. Browse all 250 glossary terms.