A method for generating a poster based on user input

IN607539BActive Publication Date: 2026-10-28UNIV OF ENG & MANAGEMENT JAIPUR
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
IN202411064457
Authority / Receiving Office
IN · IN
Patent Type
Patents
Current Assignee / Owner
Filing Date
2024-08-27
Publication Date
2026-10-28
Estimated Expiration
2044-08-27

AI Technical Summary

Technical Problem

Traditional graphic design for creating visually appealing posters is time-consuming and requires expertise, limiting accessibility for users without a design background.

Method used

A method leveraging AI technology that processes user inputs to generate text and designs, overlaying the response onto a predefined visual template to create a polished poster, utilizing the Flutter framework and integrating Google's Gemini for advanced AI capabilities.

Benefits of technology

Enables users of all skill levels to create professional-quality posters quickly and efficiently, enhancing productivity and creativity while democratizing graphic design.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

ABSTRACT A method (100) for generating a poster based on user input is disclosed, the method comprises receiving a text prompt from a user. Further, sending the text prompt to an API for processing by an AI model. Further, receiving a text response from the API, 5 wherein the text response is generated by the AI model based on the text prompt. Further, overlaying the text response onto a predefined visual template to create a poster. Thereafter, providing the generated poster as an output. <>
Need to check novelty before this filing date? Find Prior Art

Description

FIELD OF INVENTION

[0001] The present invention generally relates to graphic design, more specifically the present invention relates to a method for generating a poster based on user input.BACKGROUND OF THE INVENTION

[0002] The subject matter discussed in the background section should not be assumed to be prior art merely as a result of its mention in the background section. Similarly, a problem mentioned in the background section or associated with the subject matter of the background section should not be assumed to have been previously recognized in the prior art. The subject matter in the background section merely represents different approaches, which in and of themselves may also correspond to implementations of the claimed technology.

[0003] In recent years, advances in artificial intelligence (AI) and machine learning have revolutionized various industries, including creative design and content generation. The ability to generate compelling, contextually appropriate content based on user inputs has significant applications in marketing, advertising, and personal projects. Traditionally, creating visually appealing posters and other types of graphic content required a high level of skill and expertise in design and typography. Designers would need to carefully craft text and imagery to produce a visually balanced and effective composition. This process can be time-consuming and resource-intensive, particularly for users without a design background. As a result, there is a need for automated systems that can generate professional-looking posters quickly and easily, based on user-provided prompts. By leveraging AI technology, such a system can interpret user inputs and generate text and designs that are both aesthetically pleasing and tailored to the context of the user's prompt.

[0004] The proposed invention addresses this need by offering a method to create visually appealing posters from specific user prompts. The method involves sending the user's prompt to an API where an AI model processes the input and generates anappropriate textual response. This response is then overlaid onto a predefined visual template, producing a polished and attractive poster that meets the user's needs. This innovation provides a streamlined approach to poster design, allowing users to generate professional-quality content with minimal effort and expertise. It opens up new possibilities for individuals and businesses to create customized promotional materials, announcements, or personal projects with ease.

[0005] According to patent application number US20140307286A1 titled "Driver-based print preview, reduced size proofing, and virtual printing of documents" discloses the method for printing. The disclosed virtual printing and print preview systems and methods allow users to preview and proof a specialty print job on their in-house printers or computers. The printing systems and methods can be in the form of software, such as a printer driver, installed on a user's in-house printer or computer. The software allows the user to virtually print to other remote printing devices while preparing, previewing, and customizing the specialty print job on the user's in-house device.

[0006] However, there are many methods are available for printing based on user input. However, implementation of the method is cumbersome. Therefore, there is a need of generating a poster based on user input which is less time consuming.OBJECTIVES OF THE INVENTION

[0007] The objective of the invention is to provide the method for generating a poster based on user input.

[0008] Furthermore, the objective of the invention is to provide real-time advertisement generation.

[0009] Furthermore, the objective of the invention is to provide High Accuracy and Relevance.

[0010] Furthermore, the objective of the invention is to provide Enhanced User Experience.

[0011] Furthermore, the objective of the invention is to provide users with a diverse range of customization options, enabling them to experiment with different styles, formats, and messaging to effectively convey their brand identity and marketing objectives.

[0012] Furthermore, the objective of the invention is to provide inclusivity and accessibility in advertising by offering a platform that caters to users of diverse backgrounds and skill levels, ensuring that individuals with limited design expertise or resources can still create compelling advertisements to promote their businesses or initiatives.SUMMARY

[0013] The present invention relates to a method for generating a poster based on user input. The present invention introduces a pioneering Flutter application designed to revolutionize the advertising landscape by harnessing advanced generative artificial intelligence (AI) methodologies. Leveraging the flexible Flutter framework, the application offers users a sophisticated platform to generate diverse advertisements, encompassing posters and billboards, by providing inputs such as company name, advertisement domain, description, and imagery preferences. Confronting the challenge of the absence of specialized generative AI models tailored for advertisement generation, the project has developed a prototype capable of generating titles for each input prompt, representing a significant milestone in the application's development journey. Through meticulous research into AI frameworks, rigorous data collection, and thorough annotation, a bespoke AI model is under development. Furthermore, to enhance the application's AI capabilities, Google's Gemini is integrated as an interim solution. By seamlessly integrating these technologies, the application aspires to redefine advertising paradigms, offering a robust, technically sophisticated solution that not only creates compelling advertisements but also addresses communication barriers and drives innovation in marketing strategies

[0014] According to a main aspect, the present embodiments disclose a method for generating a poster based on user input. The method comprises receiving a text prompt from a user. Further, the method comprises sending the text prompt to an API for processing by an AI model. Further, the method comprises receiving a text response from the API, wherein the text response is generated by the AI model based on the text prompt. Further, the method comprises overlaying the text response onto a predefined visual template to create a poster. Thereafter, the method comprises providing the generated poster as an output.BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The accompanying drawings illustrate various embodiments of systems, methods, and embodiments of various other aspects of the disclosure. Any person with ordinary skills in the art will appreciate that the illustrated element boundaries (e.g. boxes, groups of boxes, or other shapes) in the figures represent one example of the boundaries. It may be that in some examples one element may be designed as multiple elements or that multiple elements may be designed as one element. In some examples, an element shown as an internal component of one element may be implemented as an external component in another and vice versa. Furthermore, elements may not be drawn to scale. Non-limiting and non-exhaustive descriptions are described with reference to the following drawings. The components in the figures are not necessarily to scale, emphasis instead being placed upon illustrating principles.

[0016] FIG. 1, illustrates a method for generating a poster based on user input;

[0017] FIG. 2, illustrates a workflow of the method for generating a poster based on user input; and

[0018] FIG. 3, illustrates a pictorial representation of the method for generating a poster based on user input.DETAIL DESCRIPTION

[0019] Some embodiments of this disclosure, illustrating all its features, will now be discussed in detail. The words "comprising," "having," "containing," and "including," and other forms thereof, are intended to be equivalent in meaning and be open-ended in that an item or items following any one of these words is not meant to be an exhaustive listing of such item or items, or meant to be limited to only the listed item or items.

[0020] It must also be noted that as used herein and in the appended claims, the singular forms "a," "an," and "the" include plural references unless the context clearly dictates otherwise. Although any systems and methods similar or equivalent to those described herein can be used in the practice or testing of embodiments of the present disclosure, the preferred, systems and methods are now described.

[0021] Embodiments of the present disclosure will be described more fully hereinafter with reference to the accompanying drawings in which like numerals represent like elements throughout the several figures, and in which example embodiments are shown. Embodiments of the claims may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. The examples set forth herein are non-limiting examples and are merely examples among other possible examples.

[0022] The present invention discloses a novel and effective method for generating a poster based on user input. The invention is a revolutionary system that leverages artificial intelligence (AI) to transform user-provided prompts into visually striking posters. By interpreting the user's text input, the AI model crafts a contextually appropriate and engaging response that can be seamlessly integrated into a predefined visual template. The present invention empowers individuals and organizations to create custom posters for a variety of purposes, such as marketing campaigns, event announcements, or personal projects. With its ability to generate professional-quality designs quickly and efficiently, the system democratizes graphic design, making itaccessible to users of all skill levels. By streamlining the creative process and producing polished, appealing visuals, the invention enhances productivity and creativity in a variety of fields.

[0023] FIG. 1, illustrates a method (100) for generating a poster based on user input. The method (100) comprises receiving a text prompt from a user, at step 102. Receiving a text prompt from a user involves accepting the inputted text through a designated interface. The method (100) must be designed to recognize and accurately capture the user's intended message, allowing for a variety of topics and subjects within the input. Once the text prompt is obtained, it is then processed further by the method's AI components. This initial step ensures that the AI model is provided with the necessary information to generate a response that aligns with the user's intent and the overall context of the prompt. Proper handling of the text prompt is essential for producing high-quality outputs that meet the desired expectations of the user.

[0024] In another embodiment, the method (100) comprises selecting the predefined visual template based on the category of the user input. Selecting the predefined visual template based on the category of the user input involves analyzing the provided text to determine its thematic category. The method (100) must accurately categorize the input prompt, recognizing keywords and contextual clues that suggest a particular theme or subject matter. Once the input is classified into a category, the method (100) proceeds to identify the most suitable visual template from a library of predefined designs. The selection process takes into account the unique characteristics of each category, ensuring that the chosen template aligns with the context and tone of the user's prompt. By selecting an appropriate visual template, the method (100) ensures that the final output is coherent, aesthetically appealing, and tailored to the category of the user input.

[0025] The method (100) comprises sending the text prompt to an API for processing by an AI model, at step 104. Sending the text prompt to an API for processing by an AI model involves establishing a secure connection between the input source and theAPI endpoint. The method (100) transmits the received text prompt to the API in a structured format, adhering to the API's specified communication protocols and data standards. The AI model within the API then processes the text prompt, utilizing advanced natural language processing techniques to interpret the user's intent and generate an appropriate response. Throughout the transmission, the method (100) ensures data integrity and confidentiality, safeguarding the user's information. By sending the text prompt to the API, the method enables the AI model to analyze the input and produce a response tailored to the user's specific prompt.

[0026] The method (100) comprises receiving a text response from the API, wherein the text response is generated by the AI model based on the text prompt, at step 106. Receiving a text response from the API, wherein the text response is generated by the AI model based on the text prompt, involves awaiting a reply from the API endpoint after sending the user's text prompt for processing. The method (100) must monitor for the response, which contains the AI model's interpretation and transformation of the original input. Once the response is received, the method checks the content for completeness and accuracy to ensure that it aligns with the expected output from the API. The received text response may include nuances and creative adjustments based on the AI model's analysis, which provides an appropriate answer to the user's input. After confirming the integrity of the text response, the method (100) may proceed to the next stage in the process, using the response to create a visually appealing output.

[0027] The method (100) comprises overlaying the text response onto a predefined visual template to create a poster, at step 108. Overlaying the text response onto a predefined visual template to create a poster involves taking the received text response and placing it onto a chosen visual design. The method must first prepare the predefined template, ensuring it is ready for integration with the text response. Using precise alignment and formatting techniques, the method positions the text response onto the visual template in a manner that enhances the overall aesthetic appeal of the poster. Factors such as text placement, size, and color are adjusted to complement the visualelements of the template and create a cohesive design. Once the overlay is complete, the method produces a finished poster that combines the visual and textual elements seamlessly, resulting in an engaging and polished final output.

[0028] In another embodiment, the method (100) comprises adjusting the visual layout of the text response on the predefined visual template based on a set of aesthetic rules, wherein the aesthetic rules include at least one of text size, text color, text placement, or visual balance. Adjusting the visual layout of the text response on the predefined visual template based on a set of aesthetic rules involves tailoring the presentation of the text to optimize the overall visual impact of the poster. The method begins by analyzing the text response in relation to the visual template, identifying areas where adjustments may be necessary. Using the set of aesthetic rules, the method modifies elements such as text size to ensure readability and consistency with the template's style.

[0029] Further, the method fine-tunes text color to harmonize with the visual scheme and improve contrast. The text placement is then carefully adjusted to achieve a balanced composition, taking into account the spatial arrangement of other design elements. Throughout this process, the method ensures visual balance, aiming for an appealing and cohesive layout. By applying these aesthetic rules, the method creates a polished and visually effective poster that adheres to the desired design principles.

[0030] The method (100) comprises providing the generated poster as an output, at step 110. Providing the generated poster as an output involves finalizing the design process and delivering the completed poster to the appropriate destination. The method (100) verifies the poster's visual integrity and aesthetic quality, ensuring that all components are properly aligned and that the overall design meets the desired standards. After confirming the poster's readiness, the method (100) proceeds to generate the final output, which may include converting the poster into a suitable file format.

[0031] Further, the method (100) makes the poster available for retrieval, either by storing it in a designated location or by providing a direct download link. In some cases, the method may facilitate immediate sharing or distribution of the poster through various channels. By offering the generated poster as an output, the method completes the process and enables the user to access and utilize the finished design for its intended purpose.

[0032] FIG. 2, illustrates a workflow of the method (100) for generating a poster based on user input.

[0033] In some embodiment, the workflow begins with prompt input from the user, at step 202, who provides a specific text prompt through an interface designed for user interaction. This input could be a phrase, sentence, or any form of textual content that the user wishes to transform into a visually appealing poster. The system captures the inputted text and proceeds to the next step.

[0034] Further, the prompt is then sent to an API for processing, at step 204. This involves transmitting the user-provided text prompt to an external service or an internal module where an AI model resides. The AI model is tasked with interpreting the user's input and generating an appropriate text response that aligns with the prompt's context.

[0035] Further, the AI model processes the prompt, the system receives a text response from the API, at step 206. This response contains the AI-generated text based on the user's input. The response is reviewed for consistency and relevance to ensure that it meets the expected standards of the workflow.

[0036] Further, overlaying the text response onto a predefined visual template to create a poster, at step 208. The text is positioned on the template using a set of aesthetic rules that govern aspects such as text size, placement, and color. The goal is to integrate the text response seamlessly with the visual elements of the template, resulting in a visually appealing and cohesive poster design.

[0037] Throughout the workflow, each step builds upon the previous one to create a streamlined process for transforming user input into a high-quality poster output.

[0038] FIG. 3, illustrates a pictorial representation of the method (100) for generating a poster based on user input.

[0039] In an embodiment, the user enters the prompt at adify.io. Adify.io is an interface designed for this purpose. The user's input can range from a single phrase to a more complex piece of text, which is meant to be transformed into a visually appealing design. This input is captured by the system for further processing.

[0040] In some embodiment, once the user has submitted the prompt, the system passes the prompt information to the Gemini API for processing. The API acts as an intermediary between the user input and the AI model, transmitting the prompt data in a structured manner for interpretation by the AI.

[0041] In an embodiment, the Gemini API processes the prompt and generates a response. If the AI model is unable to generate valid text that aligns with the user's input, the system will not proceed with overlaying text onto a template. In such cases, an appropriate response may be provided to the user, such as an error message or alternative suggestions.

[0042] In another embodiment if the AI model generates valid text based on the user's input, the system proceeds to the next step. The generated text is then overlayed onto a predefined visual template, creating a visually appealing poster. The text is adjusted according to a set of aesthetic rules to ensure it integrates seamlessly with the template and enhances the overall design.

[0043] FIG. 4, illustrates a computing device (400), showing various steps of the method (100). In an embodiment, FIG. 402 represent a computing device (400). Furthermore, the computing device (400) shows an option begin the method of generating a poster based on user input. The computing device provides a user-friendly interface for starting the process, guiding the user through the necessary steps.

[0044] In another embodiment, FIG. 404 represent the poster in which the user embedded text will be entered by the API. Furthermore, FIG. 404 allow the user toenter the prompt. The API allows the user to input the prompt, which serves as the foundation for the AI-generated text that will be integrated into the poster.

[0045] In another embodiment, FIG. 406 represent the poster with the prompt. The text response from the AI model is overlaid onto the visual design, creating a poster that combines the user's prompt with the chosen template. The FIG. 406 ensures that the final output accurately reflects the user's intent and is visually appealing.

[0046] It should be noted that the method (100) in any case could undergo numerous modifications and variants, all of which are covered by the same innovative concept; moreover, all of the details can be replaced by technically equivalent elements. In practice, the components used, as well as the numbers, shapes, and sizes of the components can be whatever according to the technical requirements. The scope of protection of the invention is therefore defined by the attached claims.

Claims

1. A method (100) for generating a poster based on user input, the method (100) comprises: receiving a text prompt from a user; sending the text prompt to an API for processing by an AI model; receiving a text response from the API, wherein the text response is generated by the AI model based on the text prompt; overlaying the text response onto a predefined visual template to create a poster; and providing the generated poster as an output.

2. The method (100) of claim 1, further comprises selecting the predefined visual template based on the category of the user input.

3. The method (100) of claim 1, further comprises adjusting the visual layout of the text response on the predefined visual template based on a set of aesthetic rules, wherein the aesthetic rules include at least one of text size, text color, text placement, or visual balance.