Controlling the Output of a Generative Model by Latent Feature Vector Shifting

arXiv:2311.08850v2 Announce Type: replace
Abstract: State-of-the-art generative models (e.g. StyleGAN3 \cite{karras2021alias}) often generate photorealistic images based on vectors sampled from their latent space. However, the ability to control the output is limited. Here we present our novel method for latent vector shifting for controlled output image modification utilizing semantic features of the generated images. In our approach we use a pre-trained model of StyleGAN3 that generates images of realistic human faces in relatively high resolution. We complement the generative model …

abstract art arxiv control cs.cv feature feature vector generate generative generative models image images novel photorealistic photorealistic images space state type vector vectors