AI engineering glossary · Generative media multimodal
What is latent space?
Latent space: The compressed, learned coordinate system where a model represents data as vectors. Points near each other correspond to similar content, so moving through it, or blending two points, produces smooth changes in the decoded output.
Latent space: an example
Averaging the latent vectors of two face photos and decoding gives a face that visibly blends both.
Related terms
- Variational autoencoder
- Latent diffusion model
- Disentangled representation
More Generative media multimodal terms
- LLaVA
- LoRA fine-tuning for diffusion
- Mean opinion score
- Mel spectrogram
- MFCC
- Mode collapse
- Multimodal embedding
- Multimodal model
Where you learn it
Latent space is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.