AI engineering glossary · Generative media multimodal
What is SDS (score distillation sampling)?
Score distillation sampling (also called SDS): A technique that uses a frozen text-to-image diffusion model as a critic to optimise another representation, such as a 3-D scene. Gradients from the diffusion model's noise prediction push renderings toward images that fit the prompt.
Score distillation sampling: an example
Each optimisation step renders the 3-D model from a random angle, adds noise, and uses the diffusion model's prediction to update the 3-D parameters.
Related terms
More Generative media multimodal terms
- Score-based generative model
- Short-time Fourier transform
- SigLIP
- Speaker diarisation
- Speaker embedding
- Spectrogram
- Speech-to-speech translation
- SSIM
Where you learn it
Score distillation sampling is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.