AI engineering glossary · Generative media multimodal
What is noise schedule?
Noise schedule: The rule that sets how much noise is added at each step of the forward diffusion process. Common choices are linear and cosine schedules. The schedule controls how quickly the signal is destroyed and strongly affects training stability and the quality of generated images.
Noise schedule: an example
A cosine schedule keeps more of the image signal in early steps than a linear one, which helped improve results at low resolutions.
Related terms
- Forward diffusion process
- Diffusion model
- Signal-to-noise ratio
More Generative media multimodal terms
- Normalizing flow
- Object hallucination
- Omni model
- Outpainting
- Perceiver resampler
- Phoneme
- Pix2Pix
- Projector layer
Where you learn it
Noise schedule is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.