View source for 18634588. GENERATING IMAGE SCENARIOS BASED ON LLM PROMPTS (Snap Inc.)

=GENERATING IMAGE SCENARIOS BASED ON LLM PROMPTS=


==Organization Name==

[[:Category:Snap Inc.|Snap Inc.]]


[[Category:Snap Inc.]]

==Inventor(s)==

[[:Category:Nathan Kenneth Boyd of Los Angeles CA US|Nathan Kenneth Boyd of Los Angeles CA US]][[Category:Nathan Kenneth Boyd of Los Angeles CA US]]

[[:Category:Evan Spiegel of Los Angeles CA US|Evan Spiegel of Los Angeles CA US]][[Category:Evan Spiegel of Los Angeles CA US]]

[[:Category:Celia Nicole Mourkogiannis of Los Angeles CA US|Celia Nicole Mourkogiannis of Los Angeles CA US]][[Category:Celia Nicole Mourkogiannis of Los Angeles CA US]]

==GENERATING IMAGE SCENARIOS BASED ON LLM PROMPTS==


This abstract first appeared for US patent application 18634588 titled 'GENERATING IMAGE SCENARIOS BASED ON LLM PROMPTS

==Original Abstract Submitted==

Methods and systems are disclosed for suggesting scenarios for an image using one or more machine learning models based on an output of an LLM. The methods and systems generate, by a device of a user, a first prompt comprising a demographic of a person and a date, and process the first prompt by a large language model (LLM) to generate a plurality of ideas relevant to the person on that date, each idea comprising a respective description and vibe. The methods and systems generate a second prompt comprising a selected idea from the plurality of ideas and a request for a plurality of scenarios that are relevant to the selected idea, process the second prompt by the LLM to generate the plurality of scenarios that are relevant to the selected idea, and present an individual content item corresponding to an individual scenario of the plurality of scenarios.



[[Category:G06T11/60]]
[[Category:G06F16/532]]
[[Category:G06F40/40]]
[[Category:CPC_G06T11/60]]