# US 2026/0099680 A1 · Alternative and asynchronous digital content generation using machine learning > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2026/0099680 A1 - Document ID: US20260099680A1 - Status: Published application - Kind: A1 - Application number: 18/910,902 - Filed: 2024-10-09 - Published: 2026-04-09 - Earliest claimed: 2024-10-09 - Assignees: Adobe Inc. - Applicants: Adobe Inc. - Inventors: Benjamin Paul Olsem; Tom M. Nguyen - Web page: https://patentgrep.com/patent/US20260099680A1 ## CPC - G06T 11/60: Creating or editing images; Combining images with text - G06F 40/30: Semantic analysis - G06F 40/40: Processing or translation of natural language (natural language analysis G06F40/20; semantic analysis G06F40/30) - G06F 40/56: Natural language generation - G06T 2200/24: involving graphical user interfaces [GUIs] - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) ## Abstract Alternative and asynchronous digital content generation techniques using machine learning are described. In one or more examples, a single input is received specifying one or more characteristics of digital content to be generated using generative artificial intelligence (AI) as implemented using one or more machine-learning models. A processing device detects that the single input specifies a plurality of alternatives to be used in the generation of the digital content. A plurality of prompt alternatives are then generated, each prompt alternative corresponding to a respective alternative of the plurality of alternatives. A plurality of digital content is received that is generated by the one or more machine-learning models using the generative artificial intelligence responsive to processing of the plurality of prompt alternatives. The plurality of digital content is presented for display in a user interface. ## Claims ### Claim 1 A method comprising: receiving, by a processing device, a single input specifying one or more characteristics of digital content to be generated using generative artificial intelligence (AI) as implemented using one or more machine-learning models; detecting, by the processing device, that the single input specifies a plurality of alternatives to be used in the generation of the digital content; forming, by the processing device, a plurality of prompt alternatives, each said prompt alternative corresponding to a respective alternative of the plurality of alternatives; receiving, by the processing device, a plurality of digital content generated by the one or more machine-learning models using the generative artificial intelligence responsive to processing of the plurality of prompt alternatives; and presenting, by the processing device, the plurality of digital content for display in a user interface. ### Claim 2 (depends on 1) The method as described in claim 1, wherein the detecting is performed by detecting text in the single input as indicating the plurality of alternatives. ### Claim 3 (depends on 1) The method as described in claim 1, wherein the detecting is performed using natural language understanding implemented by the one or more machine-learning models. ### Claim 4 (depends on 1) The method as described in claim 1, wherein a first said prompt alternative includes a first said alternative and a second said prompt alternative includes a second said alternative, the first said prompt alternative being independent of inclusion of the second said alternative and the second said prompt alternative being independent of inclusion of the first said prompt alternative. ### Claim 5 (depends on 1) The method as described in claim 1, wherein the presenting includes presenting the plurality of prompt alternatives for display in the user interface as associated with respective items of the plurality of digital content generated for respective said prompt alternatives. ### Claim 6 (depends on 5) The method as described in claim 5, wherein the presenting includes initially presenting the plurality of prompt alternatives for display in the user interface along with respective placeholders and then replacing the respective placeholders with the respective items of the plurality of digital content. ### Claim 7 (depends on 1) The method as described in claim 1, further comprising identifying a respective said machine-learning model from a plurality of said machine-learning models to receive a respective said prompt alternative and communicating the respective said prompt alternative to the respective said machine-learning model. ### Claim 8 (depends on 7) The method as described in claim 7, wherein a first said prompt alternative is communicated to a first said machine-learning model and a second said prompt alternative is communicated to a second said machine-learning model that is different than the first said machine-learning model. ### Claim 9 (depends on 8) The method as described in claim 8, wherein the receiving includes receiving a first said digital content from the first said machine-learning model having a digital content type that is different from a second said digital content that is received from the second said machine-learning model. ### Claim 10 A computing device comprising: a processing device; and a computer-readable storage medium storing instructions that, responsive to execution by the processing device, causes the processing device to perform operations including: receiving a first input specifying one or more digital content characteristics; generating a first prompt configured to cause one or more machine-learning models to generate a first set of digital content based on the first input using generative artificial intelligence (AI); receiving a second input specifying an edit to the first prompt, the second input received prior to receipt of a first set of digital content generated using generative artificial intelligence (AI) responsive to the first prompt; generating a second prompt configured to cause the one or more machine-learning models to generate a second set of digital content based on the second input; and presenting the first set of digital content and the second set of digital content for display in a user interface. ### Claim 11 (depends on 10) The computing device as described in claim 10, wherein the second input is received during processing of the first prompt by the one or more machine-learning models. ### Claim 12 (depends on 10) The computing device as described in claim 10, further comprising presenting the first prompt for display in the user interface responsive to the generating of the first prompt. ### Claim 13 (depends on 12) The computing device as described in claim 12, wherein the receiving of the edit to the first input is performed via the user interface by editing text of the first prompt. ### Claim 14 (depends on 13) The computing device as described in claim 13, further comprising presenting the second prompt for display in the user interface along with the first prompt responsive to the generating of the second prompt responsive to the receiving of the edit. ### Claim 15 (depends on 10) The computing device as described in claim 10, wherein the presenting includes presenting the first prompt in conjunction with the first set of digital content and the second prompt in conjunction with the second set of digital content. ### Claim 16 (depends on 10) The computing device as described in claim 10, wherein the presenting includes initially presenting the first prompt for display in the user interface along with one or more respective placeholders and then replacing the one or more respective placeholders with the first set of digital content. ### Claim 17 (depends on 16) The computing device as described in claim 16, wherein the initially presenting is performed during the receiving of the second input. ### Claim 18 One or more computer-readable storage media storing instructions that, responsive to execution by a processing device, causes the processing device to perform operations comprising: detecting a single input as specifying a plurality of alternatives to be used in digital content generation; forming a plurality of prompt alternatives, each said prompt alternative corresponding to a respective alternative of the plurality of alternatives; communicating the plurality of prompt alternatives for processing by one or more machine-learning models using generative artificial intelligence; and receiving a plurality of digital content generated responsive to processing of the plurality of prompt alternatives, respectively, by the one or more machine-learning models. ### Claim 19 (depends on 18) The one or more computer-readable storage media as described in claim 18, further comprising identifying a respective said machine-learning model from a plurality of said machine-learning models to receive a respective said prompt alternative and the communicating includes communicating the respective said prompt alternative to the respective said machine-learning model. ### Claim 20 (depends on 18) The one or more computer-readable storage media as described in claim 18, wherein the detecting is performed by detecting text in the single input indicating the plurality of alternatives using natural language understanding implemented by the one or more machine-learning models.