Multi-layer pre-generated content
Methods, systems, and computer programs are presented for the generation of content in advance to enable quickly customized communications for multiple types of customers. One method includes an operation for identifying components of an image design that specifies how the components are combined to generate an image. For one or more of the identified components, variations of the components are generated using one of several generative artificial intelligence (GAI) models. The method further includes detecting a request, comprising user attributes, for the image. For one or more of the identified components, a respective variation is selected based on the user attributes, and a response image is created utilizing the image design and the one or more selected variations. Further, the response image is presented on a computer user interface.
1. A computer-implemented method comprising:
identifying components of an image design that specifies how the components are combined to generate an image;
for one or more of the identified components, generating a plurality of variations of the component using one from a plurality of generative artificial intelligence (GAI) models;
detecting a request for the image, the request comprising user attributes;
for one or more of the identified components, selecting a respective variation from the plurality of variations based on the user attributes;
creating a response image, in response to the request, utilizing the image design and the one or more selected variations; and
causing presentation of the response image on a computer user interface.
2. The method as recited in claim 1 , wherein generating a plurality of variations further comprises:
generating a prompt for each variation with instructions for creating the variation; and
utilizing the generated prompt for each variation as input to one of the GAI models.
3. The method as recited in claim 1 , wherein a first component is for an image of an asset, wherein generating the plurality of variations comprises generating variations of the image of the asset.
4. The method as recited in claim 1 , wherein a second component is for a background, wherein generating the plurality of variations comprises generating variations of backgrounds.
5. The method as recited in claim 1 , wherein a third component is for a text block, wherein generating the plurality of variations comprises generating a plurality of text blocks.
6. The method as recited in claim 1 , wherein the variations are pregenerated independently of a user request, wherein the generated variations are associated with different user attributes.
7. The method as recited in claim 1 , further comprising:
for one or more of the identified components, generating the component in response to the request, the generating being based on one or more of the user attributes.
8. The method as recited in claim 7 , further comprising:
generating a prompt based on the user attributes in the request, wherein the prompt is used as input to one of the GAI models to generate the component.
9. The method as recited in claim 1 , wherein creating a response image includes combining pregenerated variations and components generated in response to the request.
10. The method as recited in claim 1 , wherein the request is for a publication that includes the image, the method further comprising:
creating the publication by including the response image, wherein causing presentation of the response image comprises presenting the publication in the computer user interface.
11. A system comprising:
a memory comprising instructions; and
one or more computer processors, wherein the instructions, when executed by the one or more computer processors, cause the system to perform operations comprising:
identifying components of an image design that specifies how the components are combined to generate an image;
for one or more of the identified components, generating a plurality of variations of the component using one from a plurality of generative artificial intelligence (GAI) models;
detecting a request for the image, the request comprising user attributes;
for one or more of the identified components, selecting a respective variation from the plurality of variations based on the user attributes;
creating a response image, in response to the request, utilizing the image design and the one or more selected variations; and
causing presentation of the response image on a computer user interface.
12. The system as recited in claim 11 , wherein generating a plurality of variations further comprises:
generating a prompt for each variation with instructions for creating the variation; and
utilizing the generated prompt for each variation as input to one of the GAI models.
13. The system as recited in claim 11 , wherein a first component is for an image of an asset, wherein generating the plurality of variations comprises generating variations of the image of the asset.
14. The system as recited in claim 11 , wherein a second component is for a background, wherein generating the plurality of variations comprises generating variations of backgrounds.
15. The system as recited in claim 11 , wherein a third component is for a text block, wherein generating the plurality of variations comprises generating a plurality of text blocks.
16. A non-transitory machine-readable storage medium including instructions that, when executed by a machine, cause the machine to perform operations comprising:
identifying components of an image design that specifies how the components are combined to generate an image;
for one or more of the identified components, generating a plurality of variations of the component using one from a plurality of generative artificial intelligence (GAI) models;
detecting a request for the image, the request comprising user attributes;
for one or more of the identified components, selecting a respective variation from the plurality of variations based on the user attributes;
creating a response image, in response to the request, utilizing the image design and the one or more selected variations; and
causing presentation of the response image on a computer user interface.
17. The non-transitory machine-readable storage medium as recited in claim 16 , wherein generating a plurality of variations further comprises:
generating a prompt for each variation with instructions for creating the variation; and
utilizing the generated prompt for each variation as input to one of the GAI models.
18. The non-transitory machine-readable storage medium as recited in claim 16 , wherein a first component is for an image of an asset, wherein generating the plurality of variations comprises generating variations of the image of the asset.
19. The non-transitory machine-readable storage medium as recited in claim 16 , wherein a second component is for a background, wherein generating the plurality of variations comprises generating variations of backgrounds.
20. The non-transitory machine-readable storage medium as recited in claim 16 , wherein a third component is for a text block, wherein generating the plurality of variations comprises generating a plurality of text blocks.