Generating Descriptions of Image Relationships

In a digital medium environment to generate a description of a visual transformation between a source digital image and a target digital image, a system comprising:

• a feature module implemented at least partially in hardware of a computing device to:
• receive the source digital image and the target digital image;
• and
• generate a source feature sequence from the source digital image and a target feature sequence from the target digital image, features of the source feature sequence each represent a portion of the source digital image and features of the target feature sequence each represent a portion of the target digital image;
• a relationship module implemented at least partially in the hardware of the computing device to:
• determine a visual relationship between the source digital image and the target digital image using cross-attention between the features of the source feature sequence and the features of the target feature sequence;
• and
• generate the description of the visual transformation based on the visual relationship;
• and
• a rendering module implemented at least partially in the hardware of the computing device to render the description in a user interface of a display device.

One or more computer-readable storage media comprising instructions stored thereon that, responsive to execution by a computing device in a digital medium environment to generate a description of a visual transformation between a source digital image and a target digital image, cause operations of the computing device including:

• generating a source feature sequence from a source feature map extracted from the source digital image and generating a target feature sequence from a target feature map extracted from the target digital image, features of the source feature sequence each represent a portion of the source digital image and features of the target feature sequence each represent a portion of the target digital image;
• determining a visual relationship between the source digital image and the target digital image using cross-attention between the features of the source feature sequence and the features of the target feature sequence and cross-attention between the features of the target feature sequence and the features of the source feature sequence;
• generating the description of the visual transformation based on the visual relationship;
• and
• rendering the description of the visual transformation as text in a user interface.