AI engineering glossary · Generative media multimodal
What is consistency model?
Consistency model: A generative model trained so that any point along a noising trajectory maps directly to the same clean output, allowing one or a few steps of generation. It can be distilled from a diffusion model to gain large speedups at some cost in quality.
Consistency model: an example
A distilled consistency model produces a usable 512 x 512 image in 1 to 4 network calls instead of 50.
Related terms
- Latent consistency model
- Diffusion sampler
- Knowledge distillation
More Generative media multimodal terms
- Content provenance
- ControlNet
- Cross-attention conditioning
- Cross-modal retrieval
- CycleGAN
- Deepfake
- Denoising diffusion implicit model
- Denoising diffusion probabilistic model
Where you learn it
Consistency 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.