AI engineering glossary · Generative media multimodal
What is LDM (latent diffusion model)?
Latent diffusion model (also called LDM): A diffusion model that runs its noising and denoising in the compact latent space of a pretrained autoencoder instead of on raw pixels. Working on much smaller tensors cuts memory and compute sharply while keeping detail, which made high-resolution image generation practical.
Latent diffusion model: an example
A 512 x 512 x 3 image is compressed to a 64 x 64 x 4 latent, about 48 times fewer values, and the denoiser only ever sees the latent.
Related terms
More Generative media multimodal terms
- Latent space
- LLaVA
- LoRA fine-tuning for diffusion
- Mean opinion score
- Mel spectrogram
- MFCC
- Mode collapse
- Multimodal embedding
Where you learn it
Latent diffusion model is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.