Method and device for calling image model of household appliance, server, and computer-readable storage medium

Abstract

The present application relates to the field of image processing technology, and discloses a method for calling an image model of a home appliance, including: obtaining a prompt text input by a user, determining the type and design style of the home appliance; loading a home appliance design model corresponding to the type of home appliance as an underlying calling model; loading a design style model corresponding to the design style as a style consistency model; inputting the prompt text and the sketch input by the user into the underlying calling model and the style consistency model, and outputting a design image. The method meets the needs of the home appliance industry and home appliance companies for personalized home appliance design and personalized design style, and avoids the design images being stereotyped and unrecognizable. It is conducive to enabling AI automated design tools to meet the personalized design needs of the home appliance industry and home appliance companies, and improving the degree of intelligence. The present application also discloses a calling device, a server, and a computer-readable storage medium for the image model of a home appliance.

Description

Technical Field

[0001] The present application relates to the field of image processing technology, for example, to a method and device for calling an image model of a household appliance, a server, and a computer-readable storage medium. Background Art

[0002] At present, with the advancement and development of AI (Artificial Intelligence), there is an urgent need to apply AI to the field of design.

[0003] The related technology discloses an AIGC (Artificial Intelligence Generated Content) painting generation algorithm based on SD (Stable Diffusion) and controllable generation. The prompt words and sketches are input into the SD model, and the design drawings that meet the user's needs are output to realize AI automated design.

[0004] In the process of implementing the embodiments of the present disclosure, it is found that there are at least the following problems in the related art:

[0005] AI automated design tools cannot meet the personalized design needs of the home appliance industry and home appliance companies, and their level of intelligence is insufficient.

[0006] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present application, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention

[0007] In order to provide a basic understanding of some aspects of the disclosed embodiments, a brief summary is given below. The summary is not an extensive review, nor is it intended to identify key / critical components or delineate the scope of protection of these embodiments, but rather serves as a prelude to the detailed description that follows.

[0008] The embodiments of the present disclosure provide a method and device for calling an image model of a home appliance device, a server, and a computer-readable storage medium, so that AI automated design tools can meet the personalized design needs of the home appliance industry and home appliance companies and improve the level of intelligence.

[0009] In some embodiments, the method includes: obtaining prompt text input by the user, determining the type of home appliance and the design style; loading the home appliance design model corresponding to the home appliance type as the underlying calling model; loading the design style model corresponding to the design style as the style consistency model; inputting the prompt text and the sketch input by the user into the underlying calling model and the style consistency model, and outputting the design image.

[0010] In some embodiments, the device includes: a determination module, configured to obtain prompt text input by a user, and determine the type of home appliance and the design style; a first loading module, configured to load a home appliance design model corresponding to the home appliance type as an underlying calling model; a second loading module, configured to load a design style model corresponding to the design style as a style consistency model; an output module, configured to input the prompt text and the sketch input by the user into the underlying calling model and the style consistency model, and output a design image.

[0011] In some embodiments, the device includes a processor and a memory storing program instructions, and the processor is configured to execute the calling method for the home appliance image model when running the program instructions.

[0012] In some embodiments, the server includes: a server body; and the calling device for the home appliance image model is installed on the server body.

[0013] In some embodiments, the computer-readable storage medium stores program instructions, and when the program instructions are executed, the computer executes the calling method for the household appliance image model.

[0014] The method and device for calling the image model of a home appliance, the server, and the computer-readable storage medium provided in the embodiments of the present disclosure can achieve the following technical effects:

[0015] First, determine the type of home appliance and design style to be designed based on the prompt text entered by the user, then load the home appliance design model corresponding to the home appliance type and the design style model corresponding to the design style, and then input the prompt text entered by the user and the sketch entered by the user into the home appliance design model and the design style model to output the design image. Since the home appliance design model and the design style model meet the needs of the home appliance industry and home appliance companies for personalized home appliance design and personalized design style, the output design image also meets the needs of the home appliance industry and home appliance companies for personalized home appliance design and personalized design style, avoiding the design images being stereotyped and unrecognizable. This is conducive to enabling AI automated design tools to meet the personalized design needs of the home appliance industry and home appliance companies and improve the level of intelligence.

[0016] The above general description and the following description are exemplary and explanatory only and are not intended to limit the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] One or more embodiments are exemplarily described by corresponding drawings, which do not limit the embodiments. Elements with the same reference numerals in the drawings are shown as similar elements, and the drawings do not constitute a scale limitation, and wherein:

[0018] Figure 1 is a schematic diagram of a method for calling a household appliance image model provided by an embodiment of the present disclosure;

[0019] Figure 2 is a schematic diagram of another method for calling a household appliance image model provided by an embodiment of the present disclosure;

[0020] Figure 3 is a schematic diagram of another method for calling a household appliance image model provided by an embodiment of the present disclosure;

[0021] Figure 4 is a schematic diagram of another method for calling a household appliance image model provided by an embodiment of the present disclosure;

[0022] Figure 5 is an application schematic diagram provided by an embodiment of the present disclosure;

[0023] Figure 6 is a schematic diagram of a device for calling an image model of a household appliance provided by an embodiment of the present disclosure;

[0024] Figure 7 is a schematic diagram of another device for calling an image model of a household appliance provided by an embodiment of the present disclosure;

[0025] Figure 8 It is a schematic diagram of a server provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0026] In order to be able to understand the features and technical contents of the embodiments of the present disclosure in more detail, the implementation of the embodiments of the present disclosure is described in detail below in conjunction with the accompanying drawings. The attached drawings are for reference only and are not used to limit the embodiments of the present disclosure. In the following technical description, for the convenience of explanation, a full understanding of the disclosed embodiments is provided through multiple details. However, one or more embodiments can still be implemented without these details. In other cases, to simplify the drawings, well-known structures and devices can be simplified for display.

[0027] The terms "first", "second", etc. in the specification and claims of the embodiments of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the terms used in this way can be interchanged where appropriate, so as to describe the embodiments of the embodiments of the present disclosure described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions.

[0028] Unless otherwise stated, the term "plurality" means two or more.

[0029] In the embodiment of the present disclosure, the character " / " indicates that the preceding and following objects are in an "or" relationship. For example, A / B indicates: A or B.

[0030] The term "and / or" is a description of the association relationship between objects, indicating that three relationships can exist. For example, A and / or B means: A or B, or, A and B.

[0031] The term "correspondence" may refer to an association relationship or a binding relationship. The correspondence between A and B means that there is an association relationship or a binding relationship between A and B.

[0032] Combination Figure 1 As shown, the embodiment of the present disclosure provides a method for calling an image model of a household appliance, comprising:

[0033] S101, the server obtains the prompt text input by the user and determines the type and design style of the home appliance.

[0034] S102, the server loads the home appliance design model corresponding to the home appliance type as the underlying calling model.

[0035] S103: The server loads a design style model corresponding to the design style as a style consistency model.

[0036] S104, the server inputs the prompt text and the sketch input by the user into the underlying call model and the style consistency model, and outputs the design image.

[0037] Using the calling method for the image model of home appliance provided by the embodiment of the present disclosure, the type of home appliance to be designed and the design style are first determined according to the prompt text input by the user, and then the home appliance design model corresponding to the home appliance type and the design style model corresponding to the design style are loaded, and then the prompt text input by the user and the sketch input by the user are input into the home appliance design model and the design style model, and the design image is output. Since the home appliance design model and the design style model meet the personalized home appliance design and personalized design style needs of the home appliance industry and home appliance companies, the output design image also meets the personalized home appliance design and personalized design style needs of the home appliance industry and home appliance companies, avoiding the design image being stereotyped and unrecognizable. It is conducive to making AI automated design tools meet the personalized design needs of the home appliance industry and home appliance companies and improve the degree of intelligence.

[0038] It should be noted that the underlying call model may be a Lora model, which is used to generate a home appliance design corresponding to the home appliance type, such as generating a design for an air conditioner body and a refrigerator body, etc. The style consistency model may be a Lora model, which is used to make the home appliance design meet the design style, for example, based on the air conditioner body and refrigerator body obtained through the underlying call model, an air conditioner image of a first design style, a refrigerator image of a first design style, an air conditioner image of a second design style, and a refrigerator image of a second design style are generated, and the design style remains consistent for the same design style requirements, and the design style remains inconsistent for the different design style requirements.

[0039] Optionally, the acquisition of the design style model includes: the server acquires the SD model. The server adjusts the SD model according to the multiple first training sets to obtain the corresponding primary design style model. The first training set includes multiple home appliance images and prompt text labels corresponding to the home appliance images. The server performs a high-quality image effect test on the primary design style model, and uses the best-tested primary design style model corresponding to the same design style as the secondary design style model. The server determines the design style model based on the secondary design style model.

[0040] Specifically, the prompt text label may be one or more of a home appliance model, a design style, a home appliance material, and a home appliance color.

[0041] In this way, multiple home appliance images and the prompt text labels corresponding to the home appliance images are used as the first training link, the SD model is adjusted to obtain a primary design style model, and then the primary design style model is tested for high-quality image effects to screen out the optimal primary design style model corresponding to each design style, and then the design style model is determined based on multiple optimal primary design style models. The design style model meets the personalized home appliance design and personalized design style needs of the home appliance industry and home appliance companies, so that the output design image also meets the personalized home appliance design and personalized design style needs of the home appliance industry and home appliance companies, avoiding the design image being stereotyped and unrecognizable. It is conducive to making AI automated design tools meet the personalized design needs of the home appliance industry and home appliance companies and improve the degree of intelligence.

[0042] Optionally, the server determines the design style model according to the secondary design style model, including: classifying the corresponding secondary design style model according to the design style to obtain the design style model.

[0043] This is conducive to more accurately loading the design style model corresponding to the design style.

[0044] Optionally, the server adjusts the SD model according to the multiple first training sets to obtain a corresponding primary design style model, including: the server collects multiple home appliance images. The server obtains a home appliance image data set according to the main home appliances in the home appliance image data. The server obtains corresponding prompt text labels according to the home appliance image data set. The server inputs the home appliance image data set and the corresponding prompt text labels as the first training set into the SD model for training to obtain the corresponding primary design style model.

[0045] In this way, it is helpful to obtain the first training set that meets the personalized home appliance design and personalized design style needs of the home appliance industry and home appliance companies based on the main home appliances in the home appliance image data and the corresponding prompt text labels, so as to better adjust the SD model and obtain a better primary design style model. The design style model meets the personalized home appliance design and personalized design style needs of the home appliance industry and home appliance companies, so that the output design image also meets the personalized home appliance design and personalized design style needs of the home appliance industry and home appliance companies, avoiding the design images being stereotyped and unrecognizable. It is helpful for AI automated design tools to meet the personalized design needs of the home appliance industry and home appliance companies and improve the degree of intelligence.

[0046] Optionally, the server obtains the home appliance image data set based on the main home appliance in the home appliance image data, including: the server removes the background in the home appliance image data, retains the main home appliance in the home appliance image data, and obtains the home appliance image data set.

[0047] In this way, removing the background and retaining the main appliance is conducive to reducing the interference of the background in the appliance image data in the first training set on the model training. This is conducive to more accurately adjusting the SD model and obtaining a more accurate primary design style model. The design style model meets the personalized home appliance design and personalized design style needs of the home appliance industry and home appliance companies, so that the output design image also meets the personalized home appliance design and personalized design style needs of the home appliance industry and home appliance companies, avoiding the design image being stereotyped and unrecognizable. It is conducive to making AI automated design tools meet the personalized design needs of the home appliance industry and home appliance companies and improve the degree of intelligence.

[0048] Optionally, the server obtains corresponding prompt text labels according to the home appliance image dataset, including: the server automatically annotates the home appliance image dataset to obtain corresponding prompt text labels.

[0049] In this way, automatic labeling is conducive to improving the speed of obtaining prompt text labels, thereby facilitating faster acquisition of the first training set, and further facilitating faster adjustment of the SD model, and faster acquisition of the primary design style model. The design style model can meet the personalized home appliance design and personalized design style needs of the home appliance industry and home appliance companies, so that the output design image can also meet the personalized home appliance design and personalized design style needs of the home appliance industry and home appliance companies, avoiding the design images being stereotyped and unrecognizable. It is conducive to making AI automated design tools meet the personalized design needs of the home appliance industry and home appliance companies and improve the degree of intelligence.

[0050] Optionally, the server performs a high-quality image effect test on the primary design style model, and uses the best-tested primary design style model corresponding to the same design style as the secondary design style model, including: the server determines the primary design style output image corresponding to the primary design style model. The server classifies the primary design style output images according to the corresponding design styles. The server performs an effect test on the i-th category of primary design style output images, and selects the corresponding primary design style output image with the best evaluation as the secondary design style output image. The server determines the primary design style model corresponding to the secondary design style output image as the i-th secondary design style model. Wherein, i=1, 2, ..., N; N is the type of design style.

[0051] In this way, by testing the effect of the primary design style output image corresponding to the primary design style model, the primary design style model corresponding to the primary design style output image with the best evaluation is screened out as the secondary design style model. The types of design styles correspond to the number of secondary design style models, covering every design style. The design style model meets the personalized home appliance design and personalized design style needs of the home appliance industry and home appliance companies, so that the output design image also meets the personalized home appliance design and personalized design style needs of the home appliance industry and home appliance companies, avoiding the design images that are all the same and unrecognizable. It is conducive to making AI automated design tools meet the personalized design needs of the home appliance industry and home appliance companies and improve the degree of intelligence.

[0052] Optionally, evaluating the primary design style output image as optimal includes: the server weighting the design style index of the i-th type of primary output image. The server uses the primary design style output image with the highest weighted design style index as the i-th optimally evaluated primary design style output image.

[0053] This helps to more accurately and objectively screen out the best evaluated primary design style output image, so that the screened secondary design style model is more accurate and objective and meets the personalized design needs of the home appliance industry and home appliance companies.

[0054] Optionally, before the server adjusts the SD model according to the multiple first training sets to obtain the corresponding primary design style model, the method further includes: when the amount of data in the first training set is less than or equal to a set amount, regularizing the first training set to obtain a second training set. Adjust the SD model according to the second training set to obtain the corresponding primary design style model.

[0055] In this way, when the data amount of the first training set is small, regularizing the first training set is beneficial to improving the quality of the first training set and the quality of model training.

[0056] Optionally, the server inputs the prompt text and the sketch input by the user into the underlying call model and the style consistency model, and outputs the design image, including: the server inputs the prompt text into the underlying call model to obtain the home appliance design image. The server inputs the home appliance design image and the prompt text into the style consistency model to obtain the style consistency image. The server inputs the style consistency image and the sketch input by the user into the style consistency model, and outputs the design image.

[0057] In this way, the prompt text input by the user is first input into the home appliance design model, and then the output home appliance design image and the prompt text input by the user are input into the design style model, and then the output design image and the rough draft input by the user are input into the design style model. Figure 1 The design style model is input to output the design image. Since the home appliance design model and the design style model meet the needs of the home appliance industry and home appliance companies for personalized home appliance design and personalized design style, the output design image also meets the needs of the home appliance industry and home appliance companies for personalized home appliance design and personalized design style, avoiding the design image being stereotyped and unrecognizable. This is conducive to making AI automated design tools meet the personalized design needs of the home appliance industry and home appliance companies and improve the degree of intelligence.

[0058] Combination Figure 2 As shown, the embodiment of the present disclosure provides another method for calling an image model of a household appliance, including:

[0059] S201, the server obtains the SD model.

[0060] S202: The server adjusts the SD model according to a plurality of first training sets to obtain a corresponding primary design style model. The first training set includes a plurality of home appliance images and prompt text labels corresponding to the home appliance images.

[0061] S203, the server performs a high-quality image effect test on the primary design style model, and uses the best-tested primary design style model corresponding to the same design style as a secondary design style model.

[0062] S204: The server determines a design style model according to the secondary design style model.

[0063] S205, the server obtains the prompt text input by the user and determines the type and design style of the home appliance.

[0064] S206: The server loads the home appliance design model corresponding to the home appliance type as the underlying calling model.

[0065] S207: The server loads a design style model corresponding to the design style as a style consistency model.

[0066] S208, the server inputs the prompt text and the sketch input by the user into the underlying call model and the style consistency model, and outputs the design image.

[0067] The calling method for the image model of home appliance provided by the embodiment of the present disclosure is adopted, and multiple home appliance images and prompt text labels corresponding to the home appliance images are used as the first training link, and the SD model is adjusted to obtain a primary design style model, and then the primary design style model is tested for high-quality image effects, and the optimal primary design style model corresponding to each design style is screened out, and then the design style model is determined according to multiple optimal primary design style models. First, the type of home appliance to be designed and the design style are determined according to the prompt text input by the user, and then the home appliance design model corresponding to the home appliance type and the design style model corresponding to the design style are loaded, and then the prompt text input by the user and the sketch input by the user are input into the home appliance design model and the design style model, and the design image is output. Since the home appliance design model and the design style model meet the personalized home appliance design and personalized design style needs of the home appliance industry and home appliance companies, the output design image also meets the personalized home appliance design and personalized design style needs of the home appliance industry and home appliance companies, avoiding the design image being stereotyped and unrecognizable. It is conducive to making AI automated design tools meet the personalized design needs of the home appliance industry and home appliance companies and improve the degree of intelligence.

[0068] Combination Figure 3 As shown, the embodiment of the present disclosure provides another method for calling an image model of a household appliance, including:

[0069] S301, the server obtains the prompt text input by the user and determines the type and design style of the home appliance.

[0070] S302: The server loads a home appliance design model corresponding to the home appliance type as an underlying calling model.

[0071] S303: The server loads a design style model corresponding to the design style as a style consistency model.

[0072] S304, the server inputs the prompt text into the underlying call model to obtain a home appliance design image.

[0073] S305: The server inputs the home appliance design image and the prompt text into a style consistency model to obtain a style consistency image.

[0074] S306, the server inputs the style-consistent image and the sketch input by the user into a style-consistent model, and outputs a design image.

[0075] The calling method for the image model of the home appliance provided by the embodiment of the present disclosure first determines the type of home appliance to be designed and the design style according to the prompt text input by the user, then loads the home appliance design model corresponding to the home appliance type and the design style model corresponding to the design style, then inputs the prompt text input by the user into the home appliance design model, then inputs the output home appliance design image and the prompt text input by the user into the design style model, and then inputs the output design image and the rough draft input by the user into the design style model. Figure 1 The design style model is input to output the design image. Since the home appliance design model and the design style model meet the needs of the home appliance industry and home appliance companies for personalized home appliance design and personalized design style, the output design image also meets the needs of the home appliance industry and home appliance companies for personalized home appliance design and personalized design style, avoiding the design image being stereotyped and unrecognizable. This is conducive to making AI automated design tools meet the personalized design needs of the home appliance industry and home appliance companies and improve the degree of intelligence.

[0076] Combination Figure 4 As shown, the embodiment of the present disclosure provides another method for calling an image model of a household appliance, including:

[0077] S401, the server fine-tunes the SD model according to the second training set to obtain a first number of primary home appliance category basic models. The second training set includes home appliance design images and prompt text labels.

[0078] S402, the server performs a high-quality image effect test on a first number of primary home appliance category basic models, and selects primary home appliance category basic models that meet the test conditions as a second number of secondary home appliance category basic models.

[0079] S403, the server integrates the second number of secondary home appliance category basic models to obtain a home appliance design model.

[0080] S404, the server obtains the prompt text input by the user and determines the type and design style of the home appliance.

[0081] S405, the server loads the home appliance design model corresponding to the home appliance type as the underlying calling model.

[0082] S406: The server loads a design style model corresponding to the design style as a style consistency model.

[0083] S407, the server inputs the prompt text and the sketch input by the user into the underlying call model and the style consistency model, and outputs the design image.

[0084] The first number is greater than or equal to the second number.

[0085] The calling method for the image model of home appliance provided by the embodiment of the present disclosure is adopted. The SD model is first fine-tuned according to the home appliance design image and the prompt text label to obtain the first number of primary home appliance category basic models, and then the first number of primary home appliance category basic models are tested for high-quality image effects to screen out the second number of secondary home appliance category basic models, and the second number of secondary home appliance category basic models are merged to obtain the home appliance design model. First, the home appliance type and design style to be designed are determined according to the prompt text input by the user, and then the home appliance design model corresponding to the home appliance type and the design style model corresponding to the design style are loaded, and then the prompt text input by the user and the sketch input by the user are input into the home appliance design model and the design style model, and the design image is output. Since the home appliance design model and the design style model meet the personalized home appliance design and personalized design style needs of the home appliance industry and home appliance companies, the output design image also meets the personalized home appliance design and personalized design style needs of the home appliance industry and home appliance companies, avoiding the design image being stereotyped and unrecognizable. It is conducive to making AI automated design tools meet the personalized design needs of the home appliance industry and home appliance companies and improve the degree of intelligence.

[0086] Combination Figure 5 As shown, in actual application, the prompt text input by the user is input into the underlying calling model, the home appliance design image is output, and then the prompt text input by the user is input into the style consistency model to output the design image.

[0087] The underlying call model is the loaded home appliance design model corresponding to the home appliance type. The home appliance design model is obtained as follows: the second training set is input into the SD model to obtain the primary home appliance category basic model, and then the primary home appliance category basic model is judged whether it meets the test conditions, and the primary home appliance category basic model that meets the test conditions is selected as the secondary home appliance category basic model. Then the secondary home appliance category basic model is integrated to obtain the home appliance design model.

[0088] The style consistency model loads the design style model corresponding to the design style. The design style model is obtained as follows: the first training set is input into the SD model to obtain the primary design style model, and the primary design style output image is output. The primary design style output image is judged whether the test passes. If it passes, the primary design style model is used as the secondary design style model, and then the design style models of different design styles are determined according to the secondary design style model.

[0089] Combination Figure 6As shown, the embodiment of the present disclosure provides a device 200 for calling an image model of a home appliance, including a determination module 501, a first loading module 502, a second loading module 503 and an output module 504. The determination module 501 is configured to obtain a prompt text input by a user and determine the type and design style of the home appliance. The first loading module 502 is configured to load a home appliance design model corresponding to the home appliance type as an underlying calling model. The second loading module 503 is configured to load a design style model corresponding to the design style as a style consistency model. The output module 504 is configured to input the prompt text and the sketch input by the user into the underlying calling model and the style consistency model, and output the design image.

[0090] The calling device 200 for the image model of home appliance provided by the embodiment of the present disclosure is used to first determine the type of home appliance and the design style to be designed based on the prompt text input by the user, then load the home appliance design model corresponding to the home appliance type and the design style model corresponding to the design style, and then input the prompt text input by the user and the sketch input by the user into the home appliance design model and the design style model, and output the design image. Since the home appliance design model and the design style model meet the personalized home appliance design and personalized design style needs of the home appliance industry and home appliance companies, the output design image also meets the personalized home appliance design and personalized design style needs of the home appliance industry and home appliance companies, avoiding the design image being stereotyped and unrecognizable. This is conducive to enabling AI automated design tools to meet the personalized design needs of the home appliance industry and home appliance companies and improve the degree of intelligence.

[0091] Combination Figure 7 As shown, the embodiment of the present disclosure provides a device 300 for calling an image model of a household appliance, including a processor 600 and a memory 601. Optionally, the device 300 may also include a communication interface 602 and a bus 603. The processor 600, the communication interface 602, and the memory 601 may communicate with each other through the bus 603. The communication interface 602 may be used for information transmission. The processor 600 may call the logic instructions in the memory 601 to execute the calling method for the image model of a household appliance of the above embodiment.

[0092] In addition, the logic instructions in the memory 601 described above can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product.

[0093] The memory 601 is a computer-readable storage medium that can be used to store software programs and computer executable programs, such as program instructions / modules corresponding to the method in the embodiment of the present disclosure. The processor 600 executes the function application and data processing by running the program instructions / modules stored in the memory 601, that is, the calling method for the image model of the household appliance in the above embodiment is implemented.

[0094] The memory 601 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and an application required for at least one function; the data storage area may store data created according to the use of the terminal device, etc. In addition, the memory 601 may include a high-speed random access memory and may also include a non-volatile memory.

[0095] Combination Figure 8 As shown, an embodiment of the present disclosure provides a server 100, including: a server body, and the above-mentioned calling device 200 (300) for the image model of household appliances. The calling device 200 (300) for the image model of household appliances is installed on the server body. The installation relationship described here is not limited to placement inside the server body, but also includes installation connections with other components of the server 100, including but not limited to physical connections, electrical connections or signal transmission connections. It can be understood by those skilled in the art that the calling device 200 (300) for the image model of household appliances can be adapted to a feasible server body, thereby realizing other feasible embodiments.

[0096] An embodiment of the present disclosure provides a computer-readable storage medium storing computer-executable instructions, wherein the computer-executable instructions are configured to execute the above-mentioned calling method for the image model of a household appliance.

[0097] The technical solution of the embodiment of the present disclosure can be embodied in the form of a software product, which is stored in a storage medium and includes one or more instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in the embodiment of the present disclosure. The aforementioned storage medium may be a non-transient storage medium, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, and other media that can store program codes.

[0098] The above description and the accompanying drawings fully illustrate the embodiments of the present disclosure so that those skilled in the art can practice them. Other embodiments may include structural, logical, electrical, process and other changes. The embodiments represent only possible changes. Unless explicitly required, separate components and functions are optional, and the order of operation may vary. The parts and features of some embodiments may be included in or replace the parts and features of other embodiments. Moreover, the words used in this application are only used to describe the embodiments and are not used to limit the claims. As used in the description of the embodiments and the claims, unless the context clearly indicates, the singular forms of "a", "an" and "the" are intended to include plural forms as well. Similarly, the term "and / or" as used in this application refers to any and all possible combinations of listings containing one or more associated ones. In addition, when used in the present application, the term "comprise" and its variants "comprises" and / or comprising refer to the presence of stated features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or groups thereof. In the absence of further restrictions, the elements defined by the sentence "comprising a ..." do not exclude the presence of other identical elements in the process, method or device comprising the elements. In this article, each embodiment may focus on the differences from other embodiments, and the same and similar parts between the various embodiments may refer to each other. For the methods, products, etc. disclosed in the embodiments, if they correspond to the method part disclosed in the embodiments, then the relevant parts can refer to the description of the method part.

[0099] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software may depend on the specific application and design constraints of the technical solution. The technicians may use different methods for each specific application to implement the described functions, but such implementations should not be considered to exceed the scope of the embodiments of the present disclosure. The technicians may clearly understand that, for the convenience and simplicity of description, the specific working processes of the systems, devices and units described above may refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here.

[0100] In the embodiments disclosed herein, the disclosed methods and products (including but not limited to devices, equipment, etc.) can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units can be only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between each other shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms. The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to implement this embodiment. In addition, each functional unit in the embodiment of the present disclosure may be integrated in a processing unit, or each unit may exist physically alone, or two or more units may be integrated in one unit.

[0101] The flowchart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to the embodiment of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. In some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. In the description corresponding to the flowchart and the block diagram in the accompanying drawings, the operations or steps corresponding to different boxes can also occur in a different order from the order disclosed in the description, and sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. Each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented by a dedicated hardware-based system that performs the specified functions or actions, or may be implemented by a combination of dedicated hardware and computer instructions.

Claims

1. A method for calling an image model of a household appliance, characterized in that: include: Get the prompt text entered by the user to determine the type and design style of the home appliance; Load the home appliance design model corresponding to the home appliance type as the underlying calling model; Loading a design style model corresponding to the design style as a style consistency model; Input the prompt text and the sketch input by the user into the underlying call model and the style consistency model, and output the design image; The acquisition of the home appliance design model includes: fine-tuning the stable diffusion SD model according to the second training set to obtain a first number of primary home appliance category basic models; the second training set includes home appliance design images and prompt text labels; performing a high-quality image effect test on the first number of primary home appliance category basic models, screening out the primary home appliance category basic models that meet the test conditions as the second number of secondary home appliance category basic models; fusing the second number of secondary home appliance category basic models to obtain the home appliance design model; The acquisition of a design style model includes: acquiring an SD model; adjusting the SD model according to a plurality of first training sets to obtain a corresponding primary design style model; the first training set includes a plurality of home appliance images and prompt text labels corresponding to the home appliance images; performing a high-quality image effect test on the primary design style model, and taking the best-tested primary design style model corresponding to the same design style as a secondary design style model; and determining a design style model according to the secondary design style model.

2. The method according to claim 1, characterized in that The SD model is adjusted according to the multiple first training sets to obtain the corresponding primary design style model, including: Collect multiple home appliance images; According to the main home appliances in the home appliance image data, a home appliance image data set is obtained; According to the home appliance image dataset, obtain the corresponding prompt text label; The home appliance image dataset and the corresponding prompt text labels are used as the first training set to input the SD model for training to obtain the corresponding primary design style model.

3. The method according to claim 2, characterized in that According to the main home appliances in the home appliance image data, a home appliance image dataset is obtained, including: The background in the home appliance image data is removed, and the main home appliances in the home appliance image data are retained to obtain a home appliance image dataset.

4. The method according to claim 1, characterized in that: The primary design style model is tested for high-quality image effects, and the best primary design style model corresponding to the same design style is used as the secondary design style model, including: Determining a primary design style output image corresponding to the primary design style model; Classifying the primary design style output images according to the corresponding design styles; Performing effect tests on the primary design style output images of the i-th category, and selecting the corresponding primary design style output images with the best evaluation as the secondary design style output images; Determine a primary design style model corresponding to the secondary design style output image as the i-th secondary design style model; Wherein, i=1, 2, ..., N; N is the type of design style.

5. The method according to any one of claims 1 to 4, characterized in that: The prompt text and the sketch input by the user are input into the underlying call model and the style consistency model, and the design image is output, including: Input the prompt text into the underlying call model to obtain the home appliance design image; Input the home appliance design image and the prompt text into the style consistency model to obtain a style consistent image; The style-consistent image and the sketch input by the user are input into the style-consistent model, and the design image is output.

6. A device for calling an image model of a household appliance, characterized in that: include: A determination module is configured to obtain a prompt text input by a user and determine a home appliance type and a design style; A first loading module is configured to load a home appliance design model corresponding to the home appliance type as a bottom-level calling model; A second loading module is configured to load a design style model corresponding to the design style as a style consistency model; An output module is configured to input the prompt text and the sketch input by the user into the underlying call model and the style consistency model, and output a design image; The acquisition of the home appliance design model includes: fine-tuning the stable diffusion SD model according to the second training set to obtain a first number of primary home appliance category basic models; the second training set includes home appliance design images and prompt text labels; performing a high-quality image effect test on the first number of primary home appliance category basic models, screening out the primary home appliance category basic models that meet the test conditions as the second number of secondary home appliance category basic models; fusing the second number of secondary home appliance category basic models to obtain the home appliance design model; The acquisition of a design style model includes: acquiring an SD model; adjusting the SD model according to a plurality of first training sets to obtain a corresponding primary design style model; the first training set includes a plurality of home appliance images and prompt text labels corresponding to the home appliance images; performing a high-quality image effect test on the primary design style model, and taking the best-tested primary design style model corresponding to the same design style as a secondary design style model; and determining a design style model according to the secondary design style model.

7. A device for calling an image model of a household appliance, comprising a processor and a memory storing program instructions, characterized in that: The processor is configured to execute the calling method for the household appliance image model according to any one of claims 1 to 5 when running the program instructions.

8. A server, characterized in that: include: Server body; The calling device for the image model of household appliances as described in claim 6 or 7 is installed on the server body.

9. A computer-readable storage medium storing program instructions, characterized in that: When the program instructions are executed, the computer is used to execute the calling method for the household appliance image model according to any one of claims 1 to 5.

Images