A method and apparatus for automatically generating a door head shot

Abstract

The present application relates to the technical field of image processing, in particular to a kind of automatically generating door head photo method and device, the method is executed by server, there is picture generation platform and target large language model in the server, the method includes: through the picture generation platform, the picture component of user input is obtained, and the picture component is analyzed and spliced processing is carried out, to generate promote prompt;After that, the promote prompt is sent to target large language model, so that target large language model according to the promote prompt carries out rendering picture processing, and generates final door head photo.The above scheme does not need user to personally carry out the production process of door head photo, just by providing some material photo or text, a variety of different styles of door head photo can be quickly generated, not only greatly simplifies the operation process, but also significantly improves the efficiency.

Description

Technical Field

[0001] This invention relates to the field of image processing technology, and specifically to a method and apparatus for automatically generating storefront photos. Background Technology

[0002] A storefront sign refers to the sign or logo displayed at the entrance or facade of a shop, business, or organization.

[0003] Current storefront photo generation typically relies on users designing, producing, and photographing the photos themselves, or outsourcing to professional design companies. Users completing the entire process themselves need certain design capabilities, production skills, and the necessary photography equipment and techniques. For example, users need to design the storefront layout, select suitable materials for production, and then use a camera or other photographic equipment to obtain the photo. Users entrusting a professional design company to produce the storefront photo requires a professional design team to design the storefront based on the user's needs and requirements, then arrange the production and photography processes, and finally provide the user with the storefront photo.

[0004] Whether you design and produce it yourself or commission a design company, it requires a lot of time and effort. Moreover, once the storefront photo is produced in the traditional way, it is difficult to make effective adjustments if users find anything unsatisfactory during actual use. Summary of the Invention

[0005] In view of this, the present invention provides a method and apparatus for automatically generating storefront photos, so as to solve the problem that traditional storefront photo generation methods require a lot of time and effort.

[0006] In a first aspect, the present invention provides a method for automatically generating storefront photos, the method being executed by a server, the server running an image generation platform and a target large language model, the method comprising:

[0007] The image generation platform obtains image components input by the user, parses and stitches these components together to generate a promotion message; the image components include store exterior, product display, and brand logo.

[0008] The "promote" message is sent to the target large language model, so that the target large language model can render the image according to the "promote" message and generate the final storefront photo.

[0009] The above solution builds an image generation platform on the server. This platform acquires image components input by the user, parses and stitches them together to generate a promotional message. This message is then sent to a target large-scale language model, which renders the image based on the message and generates the final storefront photo. Users do not need to manually create the storefront photo; they can quickly generate various styles simply by providing some source photos or text. This greatly simplifies the process and significantly improves efficiency, allowing users to obtain satisfactory storefront photos in a short time. The generated storefront photo allows users to fine-tune it to achieve the desired effect. Therefore, users can adjust and optimize the details of the storefront photo according to their preferences and actual needs, thus meeting personalized requirements.

[0010] In one optional implementation, the image generation platform is built based on the following steps:

[0011] Obtain and download the Stable Diffusion model file; the Stable Diffusion model file includes model weights and configuration files;

[0012] The model file is placed in the target directory, and the model is configured according to the requirements of the target platform to build the image generation platform. The model configuration of the image generation platform includes a user interface module, an image parsing module, a keyword processing module, and a result display module.

[0013] In one optional implementation, the step of obtaining the image components input by the user through the image generation platform, parsing and splicing the image components to generate a promote prompt includes:

[0014] The user-input image component is obtained through the user interface module of the image generation platform;

[0015] The image parsing module parses the image components to extract key information;

[0016] The keyword processing module of the image generation platform uses the extracted key information to construct a complete promotion prompt; the key information includes text content, object type, and color scheme.

[0017] In one optional implementation, the target large language model is an Llama3 model, which is constructed based on the following steps:

[0018] Obtain and install the Ollam framework;

[0019] Based on the Ollama framework, download and launch the Llama3 model.

[0020] In one optional implementation, sending the promote prompt to the target large language model, so that the target large language model renders the image according to the promote prompt and generates the final storefront photo, includes:

[0021] The promoted prompt is used as input and fed into the target large language model through the API interface;

[0022] The target large language model performs model reasoning based on the promote prompt to obtain the storefront photo information, and performs image rendering processing based on the storefront photo information to generate the final storefront photo.

[0023] The final storefront photo is sent to the image generation platform, and the image is displayed through the result display module of the image generation platform.

[0024] In an optional implementation, the method further includes:

[0025] The image generation platform obtains the modification information input by the user, and then further parses and splices the modification information to generate a prompt message for modification.

[0026] The "promote" modification prompt is sent to the target large language model, so that the target large language model can adjust elements and re-render the image according to the "promote" modification prompt, and generate the modified storefront photo.

[0027] Secondly, the present invention provides an automatic storefront photo generation device, wherein the device is executed by a server, the server running an image generation platform and a target large language model, and the device includes:

[0028] The "promote" prompt generation module is used to obtain image components input by the user through the image generation platform, and to parse and stitch the image components to generate a "promote" prompt; the image components include store exterior, product display and brand logo;

[0029] The final storefront photo generation module is used to send the promote prompt to the target large language model, so that the target large language model can render the image according to the promote prompt and generate the final storefront photo.

[0030] Thirdly, the present invention provides a computer device, comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the computer instructions to perform an automatic method for generating storefront photos as described in the first aspect or any corresponding embodiment.

[0031] Fourthly, the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to perform an automatic method for generating storefront photos according to the first aspect or any corresponding embodiment described above.

[0032] Fifthly, the present invention provides a computer program product, including computer instructions for causing a computer to execute an automatic method for generating storefront photos as described in the first aspect or any corresponding embodiment thereof.

[0033] The technical solution provided by this invention may include the following beneficial effects:

[0034] This invention constructs an image generation platform on a server. This platform acquires image components input by the user, parses and stitches these components together to generate a promotional message. This promotional message is then sent to a target large-scale language model, which renders the image based on the message and generates the final storefront photo. Users do not need to manually create the storefront photo; they can quickly generate various styles simply by providing some source photos or text. This greatly simplifies the process and significantly improves efficiency, allowing users to obtain satisfactory storefront photos in a short time. The generated storefront photo allows users to fine-tune it to achieve the desired effect. Therefore, users can adjust and optimize the details of the storefront photo according to their preferences and actual needs, thus meeting personalized requirements. Attached Figure Description

[0035] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0036] Figure 1 This is a flowchart illustrating a method for automatically generating storefront photos according to an embodiment of the present invention;

[0037] Figure 2 This is a flowchart illustrating another method for automatically generating storefront photos according to an embodiment of the present invention;

[0038] Figure 3 This is a structural block diagram of an automatic door sign photo generation device according to an embodiment of the present invention;

[0039] Figure 4 This is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. Detailed Implementation

[0040] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0041] According to an embodiment of the present invention, an embodiment of an automatic method for generating storefront photos is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0042] This embodiment provides a method for automatically generating storefront photos. This method is executed by a server connected to a client. The server runs an image generation platform and a target large language model. Figure 1 This is a flowchart of a method for automatically generating storefront photos according to an embodiment of the present invention, such as... Figure 1 As shown, the process includes the following steps:

[0043] Step S101: Obtain the image components input by the user through the image generation platform, and parse and stitch the image components to generate a promotion prompt; the image components include store exterior, product display and brand logo.

[0044] Furthermore, in this embodiment, the user first accesses a designated URL through the client's browser to enter a self-built image generation platform. On the platform, the user prepares image and text materials according to the prompts. These image components may include key elements such as store exterior, product display, and brand logo. The image generation platform parses the uploaded image components, identifies and extracts key information for each component, such as color, shape, and layout. Then, based on the parsed image component information, i.e., key information, the image generation platform automatically concatenates this image component information into a complete descriptive text, i.e., a "promote" prompt. The "promote" prompt contains all the key information needed to generate the storefront photo, such as store exterior features, product display methods, and brand logo location.

[0045] Step S102: The promote prompt is sent to the target large language model so that the target large language model can render the image according to the promote prompt and generate the final storefront photo.

[0046] Furthermore, in this embodiment, the server sends the promote prompt generated in step S101 to the target large language model running on the server. Upon receiving the promote prompt, the target large language model uses its internal deep learning algorithm and neural network structure to understand and parse the prompt. Based on the parsing results, the target large language model begins rendering the image. During this process, the target large language model gradually generates various parts of the storefront photo based on the description in the promote prompt, such as the store exterior, product display area, and brand logo. After a period of rendering processing, the target large language model generates the final storefront photo. This storefront photo not only meets the user's original needs but also has a high degree of personalization and customization. After receiving the generated storefront photo, the image generation platform displays it to the user for preview and selection. The user can choose the most satisfactory one from multiple generated storefront photos for download and use.

[0047] In summary, this embodiment constructs an image generation platform on the server. This platform acquires image components input by the user, parses and stitches these components to generate a promotional message. This promotional message is then sent to a target large language model, which renders the image based on the message and generates the final storefront photo. Users do not need to manually create the storefront photo; they can quickly generate various styles simply by providing some source photos or text. This greatly simplifies the process and significantly improves efficiency, allowing users to obtain satisfactory storefront photos in a short time. The generated storefront photo allows users to fine-tune it to achieve the desired effect. Therefore, users can adjust and optimize the details of the storefront photo according to their preferences and actual needs, thus meeting personalized requirements.

[0048] This embodiment provides another method for automatically generating storefront photos. This method is executed by a server that connects to the client. The server runs an image generation platform and a target large language model. Figure 2 This is a flowchart of another method for automatically generating storefront photos according to an embodiment of the present invention, such as... Figure 2 As shown, the process includes the following steps:

[0049] Step S201: Obtain the image component input by the user through the user interface module of the image generation platform.

[0050] Furthermore, in this embodiment, the user first accesses a designated URL through a browser to enter a self-built image generation platform. The image generation platform provides an intuitive and easy-to-use user interface module designed to receive various materials uploaded by the user. Users can follow the prompts to select and upload different types of image materials in the platform's submission form. These image materials include, but are not limited to, store names and logos, decorative and design elements, business hours information, contact information, introductions to featured products and services, and other promotional slogans. The user interface module is responsible for receiving and storing these user-uploaded image components, preparing them for subsequent image parsing and processing.

[0051] Step S202 involves using the image parsing module of the image generation platform to parse the image components and extract key information. This image generation platform can be a Stable Diffusion model.

[0052] In one alternative implementation, the image generation platform is built based on the following steps:

[0053] Obtain and download the Stable Diffusion model file; this Stable Diffusion model file includes model weights and configuration files;

[0054] Place the model file in the target directory and configure the model according to the requirements of the target platform to build the image generation platform. The model configuration of the image generation platform includes a user interface module, an image parsing module, a keyword processing module, and a result display module.

[0055] Furthermore, when building the image generation platform, the Stable Diffusion model file is first obtained. The downloaded model file includes model weights (in .ckpt or .pth format, etc.) and configuration files (such as YAML or JSON files). The downloaded model weight file and configuration file are unzipped and placed in a pre-defined target directory. This target directory has sufficient storage space and is easily accessible for subsequent model configuration and operation. Next, this embodiment performs the necessary configuration of the Stable Diffusion model. The configuration process includes installing necessary dependency libraries, setting environment variables, and adjusting model parameters. The configured image generation platform has multiple modules, including a user interface module for users to upload images and interact; an image parsing module for parsing images and extracting key information; a keyword processing module for further processing the extracted keywords; and a result display module for displaying the generated storefront photos.

[0056] Step S203: The keyword processing module of the image generation platform uses the extracted key information to generate a complete promotion prompt; the key information includes text content, object type, and color scheme.

[0057] Furthermore, once a user uploads the required image components, the image generation platform's image parsing module performs detailed analysis and processing. This module utilizes image processing technology and algorithms to extract key information elements from the image components—the critical information. These elements primarily include text content (such as store name, opening hours, etc.), object type (such as logos, decorations, etc.), and color scheme. After extracting this critical information, the image parsing module, according to preset rules and logic, assembles it into a complete promotion prompt. This promotion prompt accurately reflects all the information the user wants to display in the storefront photo.

[0058] Step S204: The promote prompt is sent to the target large language model so that the target large language model can render the image according to the promote prompt and generate the final storefront photo.

[0059] In one optional implementation, step S203 includes:

[0060] The promote prompt is used as input and fed into the target large language model via the API interface;

[0061] The target large language model performs model inference based on the promote prompt to obtain the storefront photo information, and performs image rendering processing based on the storefront photo information to generate the final storefront photo.

[0062] The final storefront photo is sent to the image generation platform, and the image is displayed through the platform's result display module.

[0063] Furthermore, in this embodiment, the image generation platform sends the generated "promote" message to the target large language model running on the server. This target large language model is a specially trained deep learning model with powerful text understanding and generation capabilities. Once the "promote" message is received, the target large language model renders the image based on the information in the message. Specifically, the target large language model parses the text content, object type, and color scheme information in the "promote" message, and then uses its generation capabilities to transform this information into a high-quality storefront photo. After rendering, the target large language model returns the generated storefront photo to the image generation platform. Upon receiving the image, the platform displays it to the user through the user interface module. The user can choose the most satisfactory one from multiple generated storefront photos to download and use. Simultaneously, the user can also upload new images or modify text to adjust the effect of the storefront photo until the desired level of satisfaction is achieved.

[0064] In one alternative implementation, the target large language model is an Llama3 model, which is built based on the following steps:

[0065] Obtain and install the Ollam framework;

[0066] Based on the Ollama framework, download and start the Llama3 model.

[0067] Furthermore, the Ollama framework is a tool for managing and running language models. During installation, the system automatically configures necessary environment variables and dependencies to ensure the framework runs correctly on the local server. Once the Ollama framework is successfully installed, it can be used to download Llama3 models. After downloading, the Llama3 model is launched using the Ollama framework. During startup, the framework loads the model's files, initializes the model's parameters, and allocates the necessary memory and computing resources. Once successfully launched, the Llama3 model can receive input (such as the aforementioned "promote" prompt) and perform inference and processing to generate the required output (such as a storefront photo).

[0068] In one alternative implementation, the method further includes:

[0069] The image generation platform obtains the modification information input by the user, and then parses and splices the modification information again to generate a prompt message for modification.

[0070] The prompt to modify the image is sent to the target large language model so that the target large language model can adjust the elements and re-render the image based on the prompt, and generate the modified storefront photo.

[0071] Furthermore, if users are not satisfied with the generated image or want to further adjust its effects, they can upload new images or modify text to provide new materials. The image generation platform will then retrieve these new materials and reassemble them into a new "promote" message. This new message is then provided to the target language model, which will re-render the image based on the new message, generating a new image that is returned to the image generation platform for display to the user. In this way, users can continuously adjust the image until they achieve a satisfactory result.

[0072] In summary, this embodiment constructs an image generation platform on the server. This platform acquires image components input by the user, parses and stitches these components to generate a promotional message. This promotional message is then sent to a target large language model, which renders the image based on the message and generates the final storefront photo. Users do not need to manually create the storefront photo; they can quickly generate various styles simply by providing some source photos or text. This greatly simplifies the process and significantly improves efficiency, allowing users to obtain satisfactory storefront photos in a short time. The generated storefront photo allows users to fine-tune it to achieve the desired effect. Therefore, users can adjust and optimize the details of the storefront photo according to their preferences and actual needs, thus meeting personalized requirements.

[0073] This embodiment also provides an automatic storefront photo generation device, which is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0074] This embodiment provides an automatic door sign photo generation device, such as... Figure 3 As shown, it includes:

[0075] The promote prompt generation module 301 is used to obtain the image components input by the user through the image generation platform, and to parse and stitch the image components to generate the promote prompt; the image components include store appearance, product display and brand logo;

[0076] The final storefront photo generation module 302 is used to send the promotion prompt to the target large language model, so that the target large language model can render the image according to the promotion prompt and generate the final storefront photo.

[0077] In some alternative implementations, the image generation platform is built based on the following steps:

[0078] Obtain and download the Stable Diffusion model file; this Stable Diffusion model file includes model weights and configuration files;

[0079] Place the model file in the target directory and configure the model according to the requirements of the target platform to build the image generation platform. The model configuration of the image generation platform includes a user interface module, an image parsing module, a keyword processing module, and a result display module.

[0080] In some alternative implementations, the promote prompt generation module 301 is further configured to:

[0081] The user-input image component is obtained through the user interface module of the image generation platform;

[0082] The image component is analyzed using the image parsing module of the image generation platform to extract key information;

[0083] The keyword processing module of the image generation platform uses the extracted key information to construct a complete promotion prompt; the key information includes text content, object type, and color scheme.

[0084] In some alternative implementations, the target large language model is an Llama3 model, which is built based on the following steps:

[0085] Obtain and install the Ollam framework;

[0086] Based on the Ollama framework, download and start the Llama3 model.

[0087] In some alternative implementations, the final storefront photo generation module 302 is further configured to:

[0088] The prompt is used as input and fed into the target large language model via the API interface.

[0089] The target large language model performs model inference based on the promote prompt to obtain the storefront photo information, and performs image rendering processing based on the storefront photo information to generate the final storefront photo.

[0090] The final storefront photo is sent to the image generation platform, and the image is displayed through the platform's result display module.

[0091] In some alternative implementations, the device is also used for:

[0092] The image generation platform obtains the modification information input by the user, and then parses and splices the modification information again to generate a prompt message for modification.

[0093] The prompt to modify the image is sent to the target large language model so that the target large language model can adjust the elements and re-render the image based on the prompt, and generate the modified storefront photo.

[0094] Further functional descriptions of the above modules and units are the same as those in the corresponding embodiments described above, and will not be repeated here.

[0095] In this embodiment, an automatic signboard photo generation device is presented in the form of a functional unit. Here, a unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that execute one or more software or fixed programs, and / or other devices that can provide the above-mentioned functions.

[0096] In summary, this embodiment constructs an image generation platform on the server. This platform acquires image components input by the user, parses and stitches these components to generate a promotional message. This promotional message is then sent to a target large language model, which renders the image based on the message and generates the final storefront photo. Users do not need to manually create the storefront photo; they can quickly generate various styles simply by providing some source photos or text. This greatly simplifies the process and significantly improves efficiency, allowing users to obtain satisfactory storefront photos in a short time. The generated storefront photo allows users to fine-tune it to achieve the desired effect. Therefore, users can adjust and optimize the details of the storefront photo according to their preferences and actual needs, thus meeting personalized requirements.

[0097] Please see Figure 4 , Figure 4 This is a schematic diagram of the structure of a computer device provided in an optional embodiment of the present invention, such as... Figure 4As shown, the computer device includes one or more processors 10, memory 20, and interfaces for connecting the components, including high-speed interfaces and low-speed interfaces. The components communicate with each other via different buses and can be mounted on a common motherboard or otherwise installed as needed. The processors can process instructions executed within the computer device, including instructions stored in or on memory to display graphical information of a GUI on external input / output devices (such as display devices coupled to the interfaces). In some alternative implementations, multiple processors and / or multiple buses can be used with multiple memories and multiple memory modules, if desired. Similarly, multiple computer devices can be connected, each providing some of the necessary operations (e.g., as a server array, a group of blade servers, or a multiprocessor system). Figure 4 Take a processor 10 as an example.

[0098] Processor 10 may be a central processing unit, a network processor, or a combination thereof. Processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The programmable logic device may be a complex programmable logic device (CAMP), a field-programmable gate array (FPGA), a general-purpose array logic (GDA), or any combination thereof.

[0099] The memory 20 stores instructions executable by at least one processor 10 to cause at least one processor 10 to perform the method shown in the above embodiments.

[0100] The memory 20 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the computer device. Furthermore, the memory 20 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some alternative embodiments, the memory 20 may optionally include memory remotely located relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0101] The memory 20 may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as flash memory, hard disk or solid-state drive; the memory 20 may also include a combination of the above types of memory.

[0102] The computer device also includes a communication interface 30 for communicating with other devices or communication networks.

[0103] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code, which, when accessed and executed by the computer, processor, or hardware, implements the methods shown in the above embodiments.

[0104] A portion of this invention can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to the invention through the operation of the computer. Those skilled in the art will understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executing the instructions, or the computer compiling the instructions and then executing the corresponding compiled program, or the computer reading and executing the instructions, or the computer reading and installing the instructions and then executing the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to a computer.

[0105] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and all such modifications and variations fall within the defined scope.

Claims

1. A method for automatically generating storefront photos, characterized in that, The method is executed by a server, which runs an image generation platform and a target large language model. The method includes: The image generation platform obtains image components input by the user, parses and stitches these components together to generate a promotion message; the image components include store exterior, product display, and brand logo. The "promote" message is sent to the target large language model, so that the target large language model can render the image according to the "promote" message and generate the final storefront photo.

2. The method according to claim 1, characterized in that, The image generation platform is built based on the following steps: Obtain and download the Stable Diffusion model file; the Stable Diffusion model file includes model weights and configuration files; Place the model file in the target directory and configure the model according to the requirements of the target platform to build the image generation platform; The model configuration of the image generation platform includes a user interface module, an image parsing module, a keyword processing module, and a result display module.

3. The method according to claim 2, characterized in that, The process of obtaining user-inputted image components through the image generation platform, parsing and splicing the image components to generate a promotional message includes: The user-input image component is obtained through the user interface module of the image generation platform; The image components are analyzed by the image parsing module of the image generation platform to extract key information; The keyword processing module of the image generation platform uses the extracted key information to construct a complete promotion prompt; the key information includes text content, object type, and color scheme.

4. The method according to claim 1, characterized in that, The target large language model is the Llama3 model, which is built based on the following steps: Obtain and install the Ollam framework; Based on the Ollama framework, download and launch the Llama3 model.

5. The method according to claim 2, characterized in that, The step of sending the promote prompt to the target large language model, so that the target large language model can render the image according to the promote prompt and generate the final storefront photo, includes: The promoted prompt is used as input and fed into the target large language model through the API interface; The target large language model performs model reasoning based on the promote prompt to obtain the storefront photo information, and performs image rendering processing based on the storefront photo information to generate the final storefront photo. The final storefront photo is sent to the image generation platform, and the image is displayed through the result display module of the image generation platform.

6. The method according to any one of claims 1 to 5, characterized in that, The method further includes: The image generation platform obtains the modification information input by the user, and then further parses and splices the modification information to generate a prompt message for modification. The "promote" modification prompt is sent to the target large language model, so that the target large language model can adjust elements and re-render the image according to the "promote" modification prompt, and generate the modified storefront photo.

7. An automatic device for generating storefront photos, characterized in that, The device is executed by a server, which runs an image generation platform and a target large language model. The device includes: The "promote" prompt generation module is used to obtain image components input by the user through the image generation platform, and to parse and stitch the image components to generate a "promote" prompt; the image components include store exterior, product display and brand logo; The final storefront photo generation module is used to send the promote prompt to the target large language model, so that the target large language model can render the image according to the promote prompt and generate the final storefront photo.

8. A computer device, characterized in that, include: The system includes a memory and a processor, which are interconnected and the memory stores computer instructions. The processor executes the computer instructions to perform an automatic method for generating storefront photos according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing a computer to perform an automatic method for generating storefront photos according to any one of claims 1 to 6.

10. A computer program product, characterized in that, Includes computer instructions for causing a computer to execute a method for automatically generating storefront photos according to any one of claims 1 to 6.

Images