AI engineering glossary · Generative media multimodal
What is Q-Former?
Q-Former: A lightweight transformer introduced with BLIP-2 that uses a fixed set of learnable query vectors to pull the most useful information out of a frozen image encoder and pass it to a language model.
Q-Former: an example
32 learnable queries condense hundreds of patch features into 32 vectors for the language model.
Related terms
More Generative media multimodal terms
- Realtime speech interaction
- Reparameterisation trick
- Residual vector quantisation
- Reverse diffusion process
- RNN-Transducer
- Sample rate
- Score distillation sampling
- Score-based generative model
Where you learn it
Q-Former is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.