Utilizing machine learning to select resizing models in generating resized digital design documents

A system comprising:

• one or more memory components;
• and
• one or more processing devices coupled to the one or more memory components, the one or more processing devices to perform operations comprising:
• selecting, utilizing a machine learning model, a first resizing model from a plurality of resizing models based on digital design elements of a digital design document;
• generating a resized digital design document from the digital design document utilizing the first resizing model;
• determining, utilizing a design critic model, that the resized digital design document fails to satisfy a design critic threshold;
• and
• selecting, utilizing the machine learning model, a second resizing model from the plurality of resizing models to generate a second resized digital document from the digital design document.

A non-transitory computer-readable medium storing executable instructions which, when executed by at least one processing device, cause the at least one processing device to perform operations comprising:

• generating a feature representation of a digital design document comprising a first dimension and digital design elements that fit within the first dimension;
• selecting, utilizing a machine learning model, a resizing model from a plurality of resizing models based on the feature representation of the digital design document;
• and
• generating a resized digital design document having a second dimension different than the first dimension by modifying the digital design elements utilizing the resizing model to fit within the second dimension.