Generating and modifying digital images using a joint feature style latent space of a generative neural network

A system comprising:

• at least one storage device comprising:
• a digital image, an encoder comprising learned transformations, and a generative neural network comprising generative convolutional blocks;
• and
• at least one processor configured to cause the system to:
• generate style vectors for a first digital image from intermediate latent vectors utilizing the learned transformations of the encoder;
• determine a feature tensor from a first subset of the style vectors utilizing the generative convolutional blocks of the generative neural network;
• determine a joint feature style vector within a joint feature style space by combining a second subset of the style vectors and the feature tensor, the second subset of the style vectors including one or more style vectors not utilized in generating the feature tensor;
• generate a modified joint feature style vector by combining a joint feature style perturbation with the joint feature style vector within the joint feature style space;
• and
• generate a second digital image, utilizing the generative neural network, from the modified joint feature style vector.

A computer-implemented method comprising:

• generating, for a digital image, style vectors corresponding to a style space from intermediate latent vectors corresponding to an intermediate latent space;
• generating a joint feature style vector corresponding to a joint feature style space by:
• generating a feature tensor by passing a subset of the style vectors through a series of generative convolutional blocks of a generative neural network;
• and
• combining the feature tensor with a second subset of the style vectors;
• in response to user input indicating a digital image modification, determining a modification vector for at least one of the style space or the intermediate latent space;
• mapping the modification vector to the joint feature style space utilizing the series of generative convolutional blocks;
• generating, within the joint feature style space, a modified joint feature style vector by combining the joint feature style vector with the modification vector;
• and
• generating a modified digital image utilizing the generative neural network and the modified joint feature style vector.