AI engineering glossary · Generative media multimodal
What is pix2Pix?
Pix2Pix: A conditional GAN for paired image-to-image translation that learns a mapping from an input image to a target image, using an adversarial loss plus a pixel-wise reconstruction loss. It needs aligned training pairs.
Pix2Pix: an example
Trained on pairs of building outlines and photos, Pix2Pix turns a new outline into a realistic facade.
Related terms
More Generative media multimodal terms
- Projector layer
- Prosody
- PSNR
- Q-Former
- Realtime speech interaction
- Reparameterisation trick
- Residual vector quantisation
- Reverse diffusion process
Where you learn it
Pix2Pix is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.