# US 11,922,541 B1 · Enhancement of machine-generated product image > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,922,541 B1 - Document ID: US11922541B1 - Status: Granted - Kind: B1 - Application number: 18/203,534 - Filed: 2023-05-30 - Granted: 2024-03-05 - Earliest claimed: 2023-02-08 - Assignees: Typeface Inc. - Applicants: Typeface Inc. - Inventors: Abhay Parasnis; Kang Chen; Hari Srinivasan; Jonathan Moreira; Vishal Sood - Web page: https://patentgrep.com/patent/US11922541B1 ## CPC - G06F 3/0482: Interaction with lists of selectable items, e.g. menus - G06F 3/04812: Interaction techniques based on cursor appearance or behaviour, e.g. being affected by the presence of displayed objects - G06F 3/0484: for the control of specific functions or operations, e.g. selecting or manipulating an object, an image or a displayed text element, setting a parameter value or selecting a range - G06F 3/04845: for image manipulation, e.g. dragging, rotation, expansion or change of colour - G06F 40/103: Formatting, i.e. changing of presentation of documents (automatic justification G06F40/189; automatic line break hyphenation G06F40/191) - G06F 40/186: Templates - G06F 40/216: using statistical methods - G06F 40/30: Semantic analysis - G06F 40/44: Statistical methods, e.g. probability models - G06F 40/56: Natural language generation - G06N 3/0475: Generative networks - G06N 5/022: Knowledge engineering; Knowledge acquisition - G06T 5/50: using two or more images, e.g. averaging or subtraction - G06T 5/77: Retouching; Inpainting; Scratch removal - G06T 7/11: Region-based segmentation - G06T 7/194: involving foreground-background segmentation - G06T 11/00: Two-dimensional [2D] image generation - G06V 20/62: Text, e.g. of license plates, overlay texts or captions on TV images - G06T 2200/24: involving graphical user interfaces [GUIs] - G06T 2207/20084: Artificial neural networks [ANN] - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING ## Abstract Methods, systems, and computer programs are presented for enhancing a machine-generated product image. One method includes an operation for receiving a request on a user interface (UI) to generate an image, where the request comprises a description of the image to be generated and identification of a product for inclusion in the image. The method further includes operations for generating, by a generative artificial intelligence (GAI) model, a first image based on the request, analyzing the first image to identify a presentation of the product in the first image, and selecting a product image from a database of product images based on the identification of the product. The method further includes replacing the presentation of the product in the first image with the selected product image to obtain a second image, and causing presentation in the UI of the second image. ## Claims ### Claim 1 A computer-implemented method comprising: receiving a request on a user interface (UI) to generate an image, the request comprising a description of the image to be generated and identification of an asset for inclusion in the image; generating, by a generative artificial intelligence (GAT) model, a first image based on the description of the image and the asset for inclusion; analyzing the first image generated by the GAI model to identify a location of an image of the asset in the first image; selecting an asset image, from a database of images, of the asset; replacing the image of the asset in the first image with the selected asset image of the asset to obtain a second image; and causing presentation in the UI of the second image. ### Claim 2 (depends on 1) The method as recited in claim 1, wherein the GAI model is affinitized by customizing the GAI model with training data that includes asset images in the database of images. ### Claim 3 (depends on 1) The method as recited in claim 1, wherein replacing the presentation of the asset in the first image further comprises: inserting the selected asset image in the first image to obtain the second image; and postprocessing the second image after the inserting to optimize lighting and a representation of the asset in the second image. ### Claim 4 (depends on 3) The method as recited in claim 3, wherein the postprocessing includes adjusting lighting and blending, fixing luminosity with reference to an asset surrounding and enhancing contour masks in the second image. ### Claim 5 (depends on 1) The method as recited in claim 1, wherein analyzing the first image to identify a presentation of the asset further comprises: generating a mask for the asset in the first image, wherein the mask is used to replace the presentation of the asset in the first image. ### Claim 6 (depends on 1) The method as recited in claim 1, further comprising: generation a plurality of variations of enhanced GAI images of the asset; and presenting the plurality of variations on the UI. ### Claim 7 (depends on 1) The method as recited in claim 1, wherein analyzing the first image generated by the GAI model further comprises: removing a background in the first image; and search for the presentation of the asset in the image with the removed background. ### Claim 8 (depends on 1) The method as recited in claim 1, wherein analyzing the first image generated by the GAI model further comprises: utilizing text recognition in the first image to find text associated with the asset. ### Claim 9 (depends on 1) The method as recited in claim 1, wherein analyzing the first image generated by the GAI model further comprises: performing aspect ratio comparison to compare the asset to a presentation of the asset in the first image. ### Claim 10 (depends on 1) The method as recited in claim 1, further comprising: utilizing a template to generate several items in the UT, the template comprising a plurality of operations, each operation comprising an option to enter a description to generate the several items. ### Claim 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: receiving a request on a user interface (UI) to generate an image, the request comprising a description of the image to be generated and identification of an asset for inclusion in the image; generating, by a generative artificial intelligence (GAI) model, a first image based on the description of the image and the asset for inclusion; analyzing the first image generated by the GAI model to identify a location of an image of the asset in the first image; selecting an asset image, from a database of images, of the asset; replacing the image of the asset in the first image with the selected asset image of the asset to obtain a second image; and causing presentation in the UI of the second image. ### Claim 12 (depends on 11) The system as recited in claim 11, wherein the GAI model is affinitized by customizing the GAI model with training data that includes asset images in the database of images. ### Claim 13 (depends on 11) The system as recited in claim 11, wherein replacing the presentation of the asset in the first image further comprises: inserting the selected asset image in the first image to obtain the second image; and postprocessing the second image after the inserting to optimize lighting and a representation of the asset in the second image. ### Claim 14 (depends on 13) The system as recited in claim 13, wherein the postprocessing includes adjusting lighting and blending, fixing luminosity with reference to an asset surrounding, and enhancing contour masks in the second image. ### Claim 15 (depends on 11) The system as recited in claim 11, wherein analyzing the first image to identify a presentation of the asset further comprises: generating a mask for the asset in the first image, wherein the mask is used to replace the presentation of the asset in the first image. ### Claim 16 A non-transitory machine-readable storage medium including instructions that, when executed by a machine, cause the machine to perform operations comprising: receiving a request on a user interface (UI) to generate an image, the request comprising a description of the image to be generated and identification of an asset for inclusion in the image; generating, by a generative artificial intelligence (GAI) model, a first image based on the description of the image and the asset for inclusion; analyzing the first image generated by the GAT model to identify a location of an image of the asset in the first image; selecting an asset image, from a database of images, of the asset; replacing the image of the asset in the first image with the selected asset image of the asset to obtain a second image; and causing presentation in the UT of the second image. ### Claim 17 (depends on 16) The non-transitory machine-readable storage medium as recited in claim 16, wherein the GAT model is affinitized by customizing the GAT model with training data that includes asset images in the database of images. ### Claim 18 (depends on 16) The non-transitory machine-readable storage medium as recited in claim 16, wherein replacing the presentation of the asset in the first image further comprises: inserting the selected asset image in the first image to obtain the second image; and postprocessing the second image after the inserting to optimize lighting and a representation of the asset in the second image. ### Claim 19 (depends on 18) The non-transitory machine-readable storage medium as recited in claim 18, wherein the postprocessing includes adjusting lighting and blending, fixing luminosity with reference to an asset surrounding, and enhancing contour masks in the second image. ### Claim 20 (depends on 16) The non-transitory machine-readable storage medium as recited in claim 16, wherein analyzing the first image to identify a presentation of the asset further comprises: generating a mask for the asset in the first image, wherein the mask is used to replace the presentation of the asset in the first image.