Generative models · MLD-0629
Latent diffusion model
A diffusion model that operates on a learned compressed representation rather than directly on raw data.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Generate high-resolution images with lower computational cost.
Original caveat
The autoencoder can limit recoverable detail.
Context and aliases
Level: Advanced. Stages: Architecture · Training · Inference.
Tags: DL · Generative AI · Vision.
Aliases: LDM.
Related concepts
Original references
- Denoising Diffusion Probabilistic Models ↗ · Consulted
- Deep Learning: online textbook ↗ · Consulted
- Flow Matching for Generative Modeling ↗ · Consulted
- Auto-Encoding Variational Bayes ↗ · Consulted
- Original reference URL ↗