Generative model for item image selection

A computer program product comprising a non-transitory computer readable storage medium having instructions encoded thereon that, when executed by a processor of a computer system, cause the computer system to perform steps comprising:

• receiving a prompt for an item image generation model, the prompt configured to request the item image generation model to generate item images for an item;
• executing the item image generation model using the prompt to generate a set of item images;
• evaluating each of the set of item images to determine performance data of each of the set of item images;
• and
• iteratively improving the set of item images by performing a set of steps comprising:
• updating the prompt based on the performance data of each of the set of item images to obtain a new prompt,
• executing, using the new prompt, the item image generation model to generate a new set of item images, and
• evaluating the new set of item images to determine performance data of each of the new set of item images.

A computer system comprising:

• a processor;
• and
• a non-transitory computer readable storage medium having instructions encoded thereon that, when executed by the processor, cause the processor to:
• receive a prompt for an item image generation model, the prompt configured to request the item image generation model to generate item images for an item,
• execute the item image generation model using the prompt to generate a set of item images,
• evaluate each of the set of item images to determine performance data of each of the set of item images, and
• iteratively improve the set of item images by causing the processor to:
• update the prompt based on the performance data of each of the set of item images to obtain a new prompt,
• execute, using the new prompt, the item image generation model to generate a new set of item images, and
• evaluate the new set of item images to determine performance data of each of the new set of item images.