Retouching digital images utilizing layer specific deep-learning neural networks

A non-transitory computer-readable medium storing instructions that, when executed by at least one processor, cause the at least one processor to perform operations comprising:

• receiving a first user input to modify a first feature of a digital image;
• receiving a second user input to modify a second feature of the digital image;
• modifying the first feature based on the first user input by utilizing a first neural network to modify a first frequency layer of the digital image;
• modifying the second feature based on the second user input by utilizing a second neural network to modify a second frequency layer of the digital image;
• and
• combining the modified first frequency layer and the modified second frequency layer to generate a modified digital image.

A system comprising:

• a memory device comprising a digital image, a first neural network, and a second neural network;
• and
• at least one computing device coupled to the memory device, the at least one computing device to cause the system to perform operations comprising:
• receiving a first user input to modify a first feature of a digital image;
• receiving a second user input to modify a second feature of the digital image;
• modifying the first feature based on the first user input by utilizing a first neural network to modify a first frequency layer of the digital image;
• modifying the second feature based on the second user input by utilizing a second neural network to modify a second frequency layer of the digital image;
• and
• combining the modified first frequency layer and the modified second frequency layer to generate a modified digital image.