AI engineering glossary · Generative media multimodal
What is cross-attention conditioning?
Cross-attention conditioning: The mechanism by which a text prompt steers an image generator. Image features act as queries and the text encoder's token vectors act as keys and values, so each image region can attend to the words that describe it at every denoising layer.
Cross-attention conditioning: an example
When the prompt says 'a red kurta', attention maps from the word 'red' highlight the clothing region of the latent.
Related terms
More Generative media multimodal terms
- Cross-modal retrieval
- CycleGAN
- Deepfake
- Denoising diffusion implicit model
- Denoising diffusion probabilistic model
- Denoising strength
- Diffusion model
- Diffusion sampler
Where you learn it
Cross-attention conditioning is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.