Makeup scheme generation method and apparatus, device, and storage medium

Abstract

The present application relates to the field of artificial intelligence, and discloses a makeup scheme generation method and apparatus, a device, and a storage medium. The method comprises: receiving a user appearance image and makeup description information of a target user sent by a user terminal, wherein the makeup description information indicates a makeup effect expected by the target user; on the basis of the user appearance image and the makeup description information, generating at least one user makeup image by means of a trained makeup effect generation model, wherein the at least one user makeup image is a makeup image generated by respectively applying at least one makeup effect to the user appearance image; and sending the at least one user makeup image to the user terminal, to instruct the user terminal to display the at least one user makeup image. That is, in the present application, a makeup effect generation model can be used to visually show a user how a makeup effect will actually look when applied on the user appearance, making it convenient for the user to determine whether the makeup is suitable for the user.

Description

Makeup plan generation method, device, equipment and storage medium

[0001] This application claims priority to Chinese patent application No. 202310786246.5 filed on June 29, 2023, with the invention name “Beauty makeup tracing method, device, equipment, storage medium and computer program”, and claims priority to Chinese patent application No. 202311253388.1 filed on September 26, 2023, with the invention name “Makeup plan generation method, device, equipment and storage medium”, all of which are incorporated by reference into this application. Technical Field

[0002] The present application relates to the field of artificial intelligence, and in particular to a makeup plan generation method, device, equipment and storage medium. Background Art

[0003] As living standards improve, people's pursuit of fashion is also becoming more and more sophisticated. They not only use exquisite makeup to show their charm, but also design their own outfits according to the needs of the occasion. Often, to achieve better makeup effects, people will imitate the makeup and clothing styles demonstrated by bloggers or models. However, the makeup and clothing styles demonstrated by bloggers or models may only be suitable for that blogger or model, and may not necessarily be suitable for others. If simply copied from reference, the ideal makeup effect may not be achieved due to individual differences. Therefore, there is an urgent need for a makeup plan generation method that can generate "customized" makeup and clothing plans suitable for those who love beauty.

[0004] Summary of the Invention

[0005] This application provides a makeup plan generation method, device, equipment, and storage medium that can generate personalized and customized makeup plans for users. The technical solution is as follows:

[0006] In a first aspect, a makeup plan generation method is provided, which is applied to a server, and the method includes:

[0007] Receive a user appearance image and makeup description information of a target user sent by a user terminal, wherein the makeup description information indicates a makeup effect desired by the target user; based on the user appearance image and the makeup description information, generate at least one user makeup image through a trained makeup effect generation model, wherein the at least one user makeup image is a makeup image generated by applying at least one makeup effect to the user appearance image; send the at least one user makeup image to the user terminal to instruct the user terminal to display the at least one user makeup image.

[0008] Thus, it can be seen that the server generates at least one user makeup image based on the user appearance image of the target user and the makeup description information provided by the target user through the makeup effect generation model. Since the user appearance image can accurately reflect the appearance characteristics of the target user, and the at least one user makeup image is a makeup image generated by applying at least one makeup effect to the user appearance image, the makeup effect in the user makeup image has a higher degree of layer fit with the user's appearance, and the original characteristics of the user's appearance are not changed, and the generated user makeup image is more realistic. Since the user makeup image can reflect the actual situation of the makeup effect applied to the target user's appearance, the target user can analyze and judge whether the makeup effect corresponding to the makeup description information is suitable for him / her based on the at least one user makeup image, and obtain a makeup plan that suits him / her by modifying the makeup description information.

[0009] Optionally, the generating at least one user makeup image based on the user appearance image and the makeup description information through a trained makeup effect generation model includes: obtaining a first geometric grid image corresponding to the user appearance image; generating at least one user makeup image based on the user appearance image, the first geometric grid image and the makeup description information through a trained makeup effect generation model.

[0010] That is, considering that the user's facial features and body shape not only have height information and width information, but also depth information, therefore, in order to ensure that the makeup effect is more in line with the user's actual face shape and body shape, when generating the user makeup image, it is also necessary to obtain the first geometric grid image of the target user to reflect the depth information of the target user's appearance, so that the makeup effect of the user makeup image output by the makeup effect generation model is better.

[0011] Optionally, the at least one user makeup image is generated by a trained makeup effect generation model based on the user appearance image, the first geometric grid image and the makeup description information, including: determining a target prompt template from a prompt template library based on the makeup description information, the prompt template library including multiple makeup prompt templates, each makeup prompt template including multiple makeup prompts describing a makeup effect; inputting the target prompt template, the user appearance image and the first geometric grid image into the makeup effect generation model to obtain the at least one user makeup image output by the makeup effect generation model.

[0012] That is, based on the makeup description information provided by the target user, the server can first enrich and improve the makeup description information provided by the target user through the prompt template library before analyzing the makeup effect expected by the target user, so as to improve the accuracy of the makeup description information and make the user makeup image output by the makeup effect generation model more accurate.

[0013] Optionally, before sending the at least one user makeup image to the user terminal, the method further includes: determining the display priority of each user makeup image in the at least one user makeup image; sorting the at least one user makeup image based on the display priority of the at least one user makeup image to obtain the image display order of the at least one user makeup image; sending the at least one user makeup image to the user terminal includes: sending the at least one user makeup image and the image display order to the user terminal to instruct the user terminal to display the at least one user makeup image according to the image display order.

[0014] Since the user makeup images with higher display priority are most likely to be the makeup effects that the target user likes, the user terminal can display the user makeup images with higher display priority in the order of image display, which makes it easier to guess the user's preferences and increase the target user's satisfaction.

[0015] Optionally, the method also includes: receiving a target makeup image sent by the user terminal, wherein the target makeup image is a makeup image determined by the target user based on the at least one user makeup image; determining a makeup implementation plan corresponding to the target makeup image, wherein the makeup implementation plan includes a plurality of sequentially associated makeup implementation steps and makeup prompt information corresponding to each makeup implementation step; and sending the makeup implementation plan to the user terminal to instruct the user terminal to display the makeup implementation plan.

[0016] When a target user provides a target makeup image, the server uses a trained makeup solution analysis model to infer the makeup implementation solution corresponding to the target makeup image, allowing the target user to imitate the makeup based on this solution. Furthermore, the makeup implementation solution includes multiple sequentially linked makeup implementation steps and corresponding makeup prompts for each step. The target user can refer to the corresponding makeup prompts for each step in turn and complete the entire makeup implementation solution in a similar "tracing" manner, greatly improving the efficiency of user makeup imitation and increasing user satisfaction.

[0017] Optionally, determining the makeup implementation plan corresponding to the target makeup image includes: inputting the target makeup image into a trained makeup plan analysis model, and obtaining the makeup implementation plan corresponding to the target makeup image output by the makeup plan analysis model.

[0018] That is, based on the trained makeup solution analysis model, the server can quickly determine the makeup implementation solution corresponding to the target makeup image. The makeup implementation solution includes multiple sequentially related makeup implementation steps and makeup prompt information corresponding to each makeup implementation step.

[0019] Optionally, the sending of the makeup implementation plan to the user terminal to instruct the user terminal to display the makeup implementation plan includes: sending makeup prompt information corresponding to a first makeup implementation step to the user terminal, the first makeup implementation step being any one of the makeup implementation steps in the makeup implementation plan; if a step jump instruction for skipping the first makeup implementation step is received from the user terminal, in response to the step jump instruction, sending makeup prompt information corresponding to a second makeup implementation step to the user terminal to instruct the user terminal to display the makeup prompt information corresponding to the second makeup implementation step, the second makeup implementation step being the next makeup implementation step adjacent to the first makeup implementation step in the makeup implementation plan.

[0020] When displaying the second makeup effect image, this application does not mechanically overlay the makeup texture data corresponding to the second makeup implementation step on the makeup effect image corresponding to the first makeup implementation step. Instead, it obtains the target user's real-time appearance image and, based on the real-time appearance image and the makeup texture data corresponding to the second makeup implementation step, generates the makeup effect image corresponding to the second makeup implementation step. In this way, the makeup effect image corresponding to each makeup implementation step is generated in real time based on the user's actual makeup progress, improving the real-time and accuracy of the makeup effect images corresponding to the makeup implementation steps.

[0021] Optionally, the makeup prompt information corresponding to the makeup implementation step includes one or more of step description information, makeup map data, makeup product information required for the makeup implementation step, and auxiliary tool information; wherein, the makeup map data includes makeup contour information and map positioning information, the makeup contour information indicates the contour of the makeup effect corresponding to the makeup implementation step, and the map positioning information indicates the position of the makeup effect corresponding to the makeup implementation step.

[0022] That is, displaying makeup prompt information in different areas can help users intuitively and comprehensively understand the specific implementation methods of the makeup steps, so that users can effectively imitate makeup.

[0023] In a second aspect, a makeup plan generation method is provided, which is applied to a user terminal, and the method includes:

[0024] Obtain a user appearance image and makeup description information of a target user, wherein the makeup description information indicates a makeup effect desired by the target user; send the user appearance image and the makeup description information to a server to instruct the server to generate at least one user makeup image based on the user appearance image and the makeup description information through a trained makeup effect generation model, wherein the at least one user makeup image is a makeup image generated by applying at least one makeup effect to the user appearance image; receive and display the at least one user makeup image sent by the server.

[0025] Optionally, before displaying the at least one user makeup image, the method further includes: receiving an image display order of the at least one user makeup image sent by the server; and displaying the at least one user makeup image includes: displaying the at least one user makeup image according to the image display order.

[0026] Optionally, after displaying the at least one user makeup image, the method further includes: determining a target makeup image based on the at least one user makeup image; sending the target makeup image to the server to instruct the server to determine a makeup implementation plan corresponding to the target makeup image, the makeup implementation plan including a plurality of sequentially associated makeup implementation steps and makeup prompt information corresponding to each makeup implementation step; receiving and displaying the makeup implementation plan sent by the server.

[0027] Optionally, the receiving and displaying of the makeup implementation plan sent by the server includes: receiving and displaying makeup prompt information corresponding to a first makeup implementation step sent by the server, the first makeup implementation step being any one of the makeup implementation steps in the makeup implementation plan; in response to a step jump operation triggered by the target user for skipping the first makeup implementation step, sending a step jump instruction to the server, the step jump instruction being used to request makeup prompt information corresponding to a second makeup implementation step, the second makeup implementation step being the next makeup implementation step adjacent to the first makeup implementation step in the makeup implementation plan; receiving and displaying makeup prompt information corresponding to the second makeup implementation step sent by the server.

[0028] Optionally, the makeup prompt information of the makeup implementation step includes one or more of step description information, makeup map data, makeup product information required for the makeup implementation step and auxiliary tool information; wherein, the makeup map data includes makeup contour information and map positioning information, the makeup contour information indicates the contour of the makeup effect corresponding to the makeup implementation step, and the map positioning information indicates the position of the makeup effect corresponding to the makeup implementation step.

[0029] Optionally, the makeup prompt information of the makeup implementation step includes the makeup map data; the display of the makeup prompt information corresponding to the second makeup implementation step includes: obtaining a real-time appearance image of the target user; based on the makeup map data corresponding to the second makeup implementation step, rendering the real-time appearance image with makeup effects to obtain a makeup rendering corresponding to the second makeup implementation step; and displaying the makeup rendering corresponding to the second makeup implementation step.

[0030] Optionally, the performing makeup effect rendering on the real-time appearance image based on the makeup map data corresponding to the second makeup implementation step to obtain a makeup effect map corresponding to the second makeup implementation step includes: generating a second geometric grid image corresponding to the real-time appearance image; determining a makeup rendering position in the real-time appearance image based on the map positioning information corresponding to the second makeup implementation step and the second geometric grid image; based on the makeup rendering position, performing makeup effect rendering on the real-time appearance image according to the makeup contour information corresponding to the second makeup implementation step to obtain a makeup effect map corresponding to the second makeup implementation step.

[0031] Optionally, the makeup prompt information of the makeup implementation step also includes the step description information, the makeup product information and the auxiliary tool information; the method also includes: displaying the step description information corresponding to the second makeup implementation step, the makeup product information corresponding to the second makeup implementation step and the auxiliary tool information corresponding to the second makeup implementation step; wherein, the makeup effect picture, the step description information, the makeup product information and the auxiliary tool information are respectively displayed in different areas, and the display areas of the step description information, the makeup product information and the auxiliary tool information surround the display area of ​​the makeup effect picture.

[0032] In a third aspect, a makeup plan generation device is provided, wherein the device has the function of implementing the makeup plan generation method of the first aspect. The device includes at least one module, which is configured to implement the makeup plan generation method of the first aspect.

[0033] In a fourth aspect, a makeup plan generation device is provided, wherein the device has the function of implementing the makeup plan generation method of the second aspect. The device includes at least one module, which is configured to implement the makeup plan generation method of the second aspect.

[0034] In a fifth aspect, a server is provided, wherein the server is a computing device cluster, the computing device cluster includes at least one computing device, and each computing device includes a processor and a memory;

[0035] The processor of the at least one computing device is used to execute computer program instructions stored in the memory of the at least one computing device, so that the computing device cluster implements the makeup plan generation method described in the first aspect above.

[0036] In the sixth aspect, a terminal is provided, comprising a memory and a processor, wherein the memory is used to store a computer program, and the processor is used to execute computer program instructions stored in the memory, so that the terminal implements the makeup plan generation method described in the second aspect above.

[0037] In the seventh aspect, a computer-readable storage medium is provided, wherein the storage medium stores computer program instructions. When the computer program instructions are executed on a server, the server executes the makeup plan generation method described in the first aspect.

[0038] In an eighth aspect, a computer-readable storage medium is provided, wherein the storage medium stores computer program instructions. When the computer program instructions are executed on a terminal, the terminal executes the makeup plan generation method described in the second aspect.

[0039] In a ninth aspect, a computer program product comprising instructions is provided. When the instructions are executed on a server, the server executes the steps of the makeup plan generation method described in the first aspect. Alternatively, a computer program is provided. When the computer program is executed on a server, the server executes the makeup plan generation method described in the first aspect.

[0040] In a tenth aspect, a computer program product comprising instructions is provided. When the instructions are executed on a terminal, the terminal executes the steps of the makeup plan generation method described in the second aspect. Alternatively, a computer program is provided. When the computer program is executed on a terminal, the terminal executes the makeup plan generation method described in the second aspect.

[0041] The technical effects obtained in the above-mentioned third to tenth aspects are similar to the technical effects obtained by the corresponding technical means in the first aspect, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] FIG1 is a schematic diagram of an implementation environment provided by an embodiment of the present application;

[0043] FIG2 is a flow chart of a makeup plan generation method provided in an embodiment of the present application;

[0044] FIG3 is a flow chart of another makeup plan generation method provided in an embodiment of the present application;

[0045] FIG4 is a schematic diagram of displaying makeup prompt information provided by an embodiment of the present application;

[0046] FIG5 is a schematic diagram of the architecture of a makeup plan generation system provided in an embodiment of the present application;

[0047] FIG6 is a schematic diagram of a process for generating a user makeup effect image provided by an embodiment of the present application;

[0048] FIG7 is a flow chart of a makeup generation solution provided in an embodiment of the present application;

[0049] FIG8 is a schematic diagram of a process for generating a user's outfit effect diagram provided by an embodiment of the present application;

[0050] FIG9 is a schematic structural diagram of a makeup plan generating device provided in an embodiment of the present application;

[0051] FIG10 is a schematic diagram of the structure of another makeup plan generating device provided in an embodiment of the present application;

[0052] FIG11 is a schematic diagram of the structure of a computing device provided in an embodiment of the present application;

[0053] FIG12 is a schematic diagram of the structure of a computing device cluster provided in an embodiment of the present application;

[0054] FIG13 is a schematic diagram of a network connection relationship of a computing device provided in an embodiment of the present application;

[0055] FIG14 is a schematic structural diagram of a terminal provided in an embodiment of the present application. DETAILED DESCRIPTION

[0056] In order to make the objectives, technical solutions and advantages of the embodiments of the present application clearer, the implementation methods of the present application will be further described in detail below with reference to the accompanying drawings.

[0057] Before explaining in detail the makeup plan generation method provided in the embodiment of the present application, the application scenarios and implementation environment involved in the embodiment of the present application are first introduced.

[0058] As people's living standards continue to improve, beauty and everyday style have become a daily focus for those who value beauty, and they must complete them daily. Most beauty enthusiasts rely on independent learning to complete these tasks. Take beauty, for example. There are many styles in the beauty field, such as European and American makeup, Korean makeup, and Hong Kong style, and beauty styles are constantly being updated. At the same time, everyone has different face shapes, skin tones, and preferences. Therefore, appropriately applying a desired beauty style to a specific individual is a typical personalized and customized solution design and implementation process.

[0059] In other words, if you need to apply a beauty makeup style to a specific user and achieve a satisfactory effect for the user, you must ensure that the beauty makeup style is suitable for the user's face shape, skin color, preferences, etc.; at the same time, you must ensure that the user can use beauty makeup products to successfully complete the makeup process in order to apply the beauty makeup style to their own face shape.

[0060] Beauty influencers / bloggers promote beauty products by showcasing their makeup techniques and personal charm. However, it can be difficult to determine whether the products that look good on others will work for viewers / buyers. This could be because the product or style isn't suitable for the viewer / buyer's individual circumstances; or because the numerous and complex steps involved in a makeup routine make it difficult for viewers / buyers to achieve the same look using the same products.

[0061] As an example, when a beauty anchor is live streaming and selling products, they will showcase the beauty products through product introductions, personal charm, and the effects of the anchor's use. A beauty product that looks good when used on the beauty anchor's face may not necessarily be suitable for viewers / buyers.

[0062] Similarly, e-commerce platforms selling beauty products often use pre-installed model images to showcase makeup trials on product pages. These seemingly perfect results are limited to the model's overall style and may not necessarily apply to the buyer. Therefore, even if a buyer purchases the same makeup product, they may choose to return it if it doesn't achieve the desired results, or even give up trying it if they don't achieve the desired results.

[0063] As another example, after introducing a beauty product, a beauty blogger will use the corresponding beauty product to apply makeup on the spot and explain the makeup steps to demonstrate the beauty effect of the beauty product. However, since the makeup skills of the viewer / buyer are different from those of the beauty blogger, even if the viewer / buyer imitates the beauty blogger's makeup steps, he or she will still not be able to achieve the same beauty.

[0064] Beyond the beauty and cosmetics sector, outfit of the day (OOTD) content is also a hot topic on internet apps. Bloggers and models showcase outfit suggestions and experiences, providing buyers with references and recommendations. However, similar to makeup, viewers and buyers only see the blogger or model, not themselves. Furthermore, everyone's body shape and style vary greatly, so viewers and buyers may not be suited to the blogger's or model's style, and their body shape may not allow them to achieve the same look.

[0065] To summarize, the current methods of recommending / displaying beauty and fashion are all about showing the makeup plans of bloggers / models, rather than viewers / buyers. As a result, viewers / buyers may find it difficult to achieve the desired makeup effect due to personal differences, makeup skills, etc. after simply referring to and copying them.

[0066] Based on this, the embodiment of the present application provides a makeup plan generation method, which generates a makeup plan suitable for the target user through the makeup effects of some models accumulated by the large model, the experience and skills explained by the anchor / bloggers, etc., so that the target user can complete the makeup through a method similar to "tracing" (a traditional method of learning calligraphy, which refers to copying on paper printed with red characters or hollow red characters, and is one of the best training methods for beginners to learn to write).

[0067] In other words, the makeup plan generation method provided in the embodiment of the present application can act as an image consultant for the target user based on a large number of existing makeup effects, makeup experience and makeup skills, so as to provide the target user with personalized and customized makeup plans according to the actual needs of the target user, and can also guide the user to complete the entire makeup process based on the makeup plan.

[0068] Please refer to Figure 1, which is a schematic diagram of an implementation environment shown in this embodiment. The implementation environment includes at least one user terminal 110 and a server 120. The user terminal 110 can be connected to the server 120 for communication. The communication connection can be a wired or wireless connection, which is not limited in this embodiment of the application.

[0069] In some embodiments, user terminal 110 is configured to intelligently interact with a target user, collect a user appearance image of the target user, and makeup description information describing the target user's desired makeup effect, and then transmit the user appearance image to server 120. After receiving the user appearance image and makeup description information, server 120 first determines at least one makeup effect based on the makeup description information; then applies the at least one makeup effect to the user appearance image to generate at least one user makeup image; and then transmits the at least one user makeup image to user terminal 110. User terminal 110 receives and displays the at least one user makeup image transmitted by server 120 for the target user to browse and select.

[0070] In some embodiments, user terminal 110 may determine a target makeup image and send it to server 120, requesting server 120 to provide a makeup implementation solution corresponding to the target makeup image. After receiving the target makeup image, server 120 determines a makeup implementation solution corresponding to the target makeup image, which includes multiple sequentially associated makeup implementation steps and makeup prompt information corresponding to each makeup implementation step, and sends the makeup implementation solution to user terminal 110. User terminal 110 receives and displays the makeup implementation solution sent by server 120 for the target user to imitate and perform makeup.

[0071] In a specific implementation, the user terminal 110 can be any electronic product that can interact with the user through one or more methods such as a keyboard, touchpad, touch screen, remote control, voice interaction, or handwriting device, such as a personal computer (PC), mobile phone, smart phone, personal digital assistant (PDA), Pocket PC (PPC), tablet computer, smart car computer, smart TV, etc. The server 120 can be a standalone server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery network (CDN), and big data and artificial intelligence platforms, or a cloud computing service center.

[0072] Those skilled in the art should understand that the above-mentioned user terminal 110 and server 120 are only examples. Other existing or future terminals or servers that are applicable to the embodiments of the present application should also be included in the scope of protection of the embodiments of the present application and are included here by reference.

[0073] It should be noted that the application scenarios and implementation environments described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided by the embodiments of the present application. Ordinary technicians in this field can know that with the emergence of new application scenarios and the evolution of the implementation environment, the technical solutions provided by the embodiments of the present application are also applicable to similar technical problems.

[0074] Next, the makeup plan generation method provided in the embodiment of the present application is explained in detail.

[0075] Referring to Figure 2 , an embodiment of the present application provides a makeup plan generation method for generating at least one user makeup image based on a user appearance image and makeup description information. The at least one user makeup image is generated by applying at least one makeup effect to the user appearance image. For example, using the method as applied to the user terminal 110 and server 120 shown in Figure 1 , the makeup plan generation method may include the following steps 201 through 205 .

[0076] Step 201: The user terminal obtains the user appearance image and makeup description information of the target user.

[0077] The makeup description information indicates the makeup effect desired by the target user. The makeup description information may include multiple makeup descriptive words or a paragraph of makeup description content, which is not limited in this embodiment of the application.

[0078] In one possible implementation, the process of obtaining the target user's appearance image is as follows: the user terminal may use its own camera or a camera connected to the user terminal to capture real-time video data of the target user, and determine the target user's appearance image based on the video data; or the target user may upload a user appearance image of their own to the user terminal, and the user appearance image may be an image captured at another time using another device. This embodiment of the present application is not limited to this.

[0079] In one possible implementation, the process of obtaining the target user's makeup description information is as follows: the user terminal uses its own voice receiving device, or a voice receiving device connected to the user terminal, to collect the makeup description information input by the target user through voice; or the target user manually enters the makeup description information in the user terminal interface. This embodiment of the application is not limited to this.

[0080] It should be noted that in all embodiments of the present application, "makeup" includes at least two dimensions: beauty makeup and dressing style. Therefore, the makeup description information can be understood as beauty makeup description information, which is used to indicate the beauty makeup effect that the target user expects in facial makeup; the makeup description information can also be understood as dressing description information, which is used to indicate the styling effect that the target user expects in clothing.

[0081] In some embodiments, to accurately identify specific makeup areas and obtain a more accurate user image, when the makeup description information is beauty makeup description information, the user appearance image can be a facial image of the target user to highlight the target user's facial features. When the makeup description information is clothing description information, the user appearance image can be a full-body image of the target user to highlight the target user's body features.

[0082] Of course, the user terminal may also obtain a partial image of the target user's corresponding part based on the makeup description information provided by the target user and use it as the user's appearance image; or the user terminal may directly obtain a full-body image of the target user, and then determine the specific part that needs to be made up based on the makeup description information provided by the target user, and then determine the partial area image of the made-up part in the full-body image as the user's appearance image. This embodiment of the present application is not limited to this.

[0083] Step 202: The user terminal sends a user appearance image and makeup description information to the server to instruct the server to generate at least one user makeup image.

[0084] The user terminal can directly send the user's appearance image and makeup description information to the server. After receiving the user's appearance image and makeup description information, the server automatically executes the following step 203. The user terminal can also send a makeup design request to the server, and include the user's appearance image and makeup description information in the request. The server responds to the makeup design request and executes the following step 203 based on the included user appearance image and makeup description information. This embodiment of the application does not limit the manner in which the user terminal sends the user's appearance image and makeup description information.

[0085] Step 203: The server receives the user appearance image and makeup description information sent by the user terminal, and generates at least one user makeup image based on the user appearance image and makeup description information using a trained makeup effect generation model.

[0086] The at least one user-created makeup image is generated by applying at least one makeup effect to the user's appearance image. Specifically, the user's appearance image maintains its facial features and skeletal structure, and the at least one makeup effect is overlaid on the corresponding parts of the user's appearance image via texture rendering to generate the user-created makeup image. This is done by not regenerating an image that satisfies the at least one makeup effect based on the user's appearance image and the makeup effect, thereby ensuring the authenticity of the user-created makeup image.

[0087] In some embodiments, considering that the user's facial features and body shape have not only height information and width information, but also depth information, therefore, in order to ensure that the makeup effect is more in line with the user's actual face shape and body shape, when generating the user makeup image, it is also necessary to obtain the first geometric grid image of the target user to reflect the depth information of the target user's appearance, so that the makeup effect of the user makeup image output by the makeup effect generation model is better.

[0088] In one possible implementation, the implementation process of step 203 may be: obtaining a first geometric grid image corresponding to the user appearance image; generating at least one user makeup image through a trained makeup effect generation model based on the user appearance image, the first geometric grid image and the makeup description information.

[0089] The first geometric mesh image can be generated from a two-dimensional image of the user's appearance. For example, a mesh surface graph is generated based on the mesh data corresponding to the user's appearance image to obtain the first geometric mesh image corresponding to the user's appearance image. This embodiment of the present application does not limit the method for generating the first geometric mesh image; reference may be made to relevant mesh generation algorithms.

[0090] Optionally, the user terminal's hardware information can be adjusted to enable the user terminal to directly acquire three-dimensional user appearance features, thereby generating a first geometric mesh image of the target user based on the three-dimensional user appearance features. For example, the user terminal can be connected to a depth camera to capture a three-dimensional image of the user's appearance, thereby generating the first geometric mesh image. This can provide richer details of the target user's appearance and a more three-dimensional and natural portrait.

[0091] It should be noted that the first geometric grid image can be generated by the user terminal and then sent to the server, or the server can generate the first geometric grid image corresponding to the user appearance image based on the user appearance image. The embodiment of the present application does not impose any restrictions on this.

[0092] In some embodiments, the implementation process of generating at least one user makeup image through a makeup effect generation model based on the user appearance image, the first geometric grid image and the makeup description information includes the following steps (1)-(2).

[0093] (1) Based on the makeup description information, determine the target prompt template from the prompt template library.

[0094] The prompt template library includes a plurality of makeup prompt templates, and each makeup prompt template includes a plurality of makeup prompts describing a makeup effect.

[0095] It should be noted that the makeup description information for the same makeup effect is different for different users. For users engaged in makeup design, the makeup description information used when describing a makeup effect will be detailed, comprehensive, and accurate; while for ordinary users, the makeup description information used when describing a makeup effect may be relatively monotonous, incomplete, and inaccurate. Based on this, based on the makeup description information provided by the target user, the server can enrich and improve the makeup description information provided by the target user based on the prompt template library before analyzing the makeup effect expected by the target user, so as to improve the accuracy of the makeup description information and make the user makeup image output by the makeup effect generation model more accurate.

[0096] In one possible implementation, keyword matching is performed between the makeup description information and multiple makeup prompt templates in the prompt template library, the number of matching words between each makeup prompt template and the makeup description information is determined, and the makeup prompt template with the largest number of matching words is determined as the target prompt template.

[0097] Optionally, at least one candidate prompt template may be determined from a plurality of makeup prompt templates based on a matching word threshold, and then a target prompt template may be determined from the at least one candidate prompt template based on a template selection strategy.

[0098] In another possible implementation, semantic matching is performed between the makeup description information and multiple makeup prompt templates in the prompt template library, the semantic similarity between each makeup prompt template and the makeup description information is determined, and the makeup prompt template with the highest semantic similarity is determined as the target prompt template.

[0099] Optionally, at least one candidate prompt template may be determined from a plurality of makeup prompt templates based on a similarity threshold, and then a target prompt template may be determined from the at least one candidate prompt template based on a template selection strategy.

[0100] As an example, the above template selection strategy can be user preferences, template ratings, number of template uses, makeup difficulty, etc., and the embodiments of the present application do not impose any restrictions on this.

[0101] In some embodiments, the number of target prompt templates can be one or more. When a large number of user makeup images need to be output, multiple target prompt templates can be selected from the prompt template library to increase the diversity of the makeup effects, so that the makeup effect generation model can output more user makeup images with higher accuracy. This embodiment of the present application does not impose any restrictions on this.

[0102] (2) Inputting the target prompt template, the user appearance image and the first geometric grid image into the makeup effect generation model to obtain at least one user makeup image output by the makeup effect generation model.

[0103] It should be understood that the makeup effect generation model is equivalent to an expert system in the field of beauty and fashion, which may include at least one network model. This makeup effect generation model is trained using a large amount of user information / images such as makeup styles, makeup plans, beauty products, and clothing items. It has the ability to generate personalized and customized makeup effects based on the user's appearance image and makeup prompts, and render the makeup effects onto the user's appearance image, allowing users to intuitively understand the actual makeup effect after using the makeup effect.

[0104] In one possible implementation, the makeup effect generation model first generates at least one makeup effect based on the target prompt template; then, based on the first geometric grid image and the user appearance image, the at least one makeup effect is rendered on the user appearance image to generate at least one user makeup image.

[0105] Since user makeup images are output by the makeup effect generation model, the number of user makeup images can be adjusted by adjusting the output volume of the makeup effect generation model. For example, if the output volume of the makeup effect generation model is set to 10, the makeup effect generation model will output 10 user makeup images based on the target prompt template, the user's appearance image, and the first geometric grid image.

[0106] It should be noted that, in the at least one user makeup image, the makeup effects of each user makeup image are not exactly the same. Since "makeup" in the embodiment of the present application includes beauty makeup and / or clothing, different makeup effects refer to different beauty makeup effects and / or different clothing effects.

[0107] For example, if the makeup effect is a beauty effect, in the 10 output user beauty images, the lip beauty effect of the first and second user beauty images can be the same, and the eye makeup effect of the third, fourth, and seventh user beauty images can be the same. In other words, as long as there is only one difference in the beauty effect between the two user beauty images, the two user beauty images are considered different.

[0108] As another example, if the makeup effect is a clothing effect, in the 10 output user outfit images, the first and second user outfit images have the same shirt, and the third, fourth, and seventh user outfit images have the same pants. In other words, if there is only one different item in each user outfit image, the two user outfit images are considered different.

[0109] Step 204: The server sends at least one user makeup image to the user terminal to instruct the user terminal to display the at least one user makeup image.

[0110] In some embodiments, based on the generated at least one user makeup image, the server may also determine a display priority for each user makeup image in the at least one user makeup image; and based on the display priority of the at least one user makeup image, the at least one user makeup image may be sorted to obtain an image display order for the at least one user makeup image. In this case, the server may send the at least one user makeup image to the user terminal by sending the at least one user makeup image and the image display order to the user terminal, thereby instructing the user terminal to display the at least one user makeup image according to the image display order.

[0111] Among them, the display priority of each user's makeup image can be determined based on a preset evaluation mechanism and continuous feedback from users using various makeup templates. This embodiment of the present application does not impose any restrictions on this.

[0112] As an example, the evaluation mechanism may include makeup complexity, user style matching, etc. The higher the makeup complexity, the lower the display priority; the higher the user style matching, the higher the display priority.

[0113] In one possible implementation, based on the display priority of the at least one user makeup image, the at least one user makeup image may be sorted in descending order of display priority to determine an image display order for the at least one user makeup image. Because user makeup images with higher display priorities are more likely to be makeup effects preferred by the target user, the user terminal may display user makeup images with higher display priorities at the front of the display order, making it easier to predict the user's preferences and thereby increasing the target user's satisfaction.

[0114] Step 205: The user terminal receives and displays at least one user makeup image sent by the server.

[0115] In some embodiments, if the server also sends the image display order of at least one user makeup image, the implementation process of step 205 includes: receiving the image display order of the at least one user makeup image sent by the server, and displaying the at least one user makeup image according to the image display order.

[0116] In some embodiments, if the server does not send the image display order and only sends the at least one user makeup image, the implementation process of step 205 includes: receiving the at least one user makeup image sent by the server, and the user terminal displays the at least one user makeup image in a random order; or, the user terminal may also display the at least one user makeup image in sequence according to the reception order; or, the user terminal may also determine the display priority of each user makeup image according to user preferences, historical data, etc. in the above manner, and then determine the image display order of the at least one user makeup image based on the display priority of each user makeup image, and then display the at least one user makeup image according to the image display order.

[0117] That is, the operation of determining the image display order can be performed by the server or by the user terminal, and the embodiment of the present application does not limit this.

[0118] In an embodiment of the present application, the server generates at least one user makeup image based on the user appearance image of the target user and the makeup description information provided by the target user through a makeup effect generation model. Since the user appearance image can accurately reflect the appearance characteristics of the target user, and the at least one user makeup image is a makeup image generated by applying at least one makeup effect to the user appearance image, the makeup effect in the user makeup image has a higher degree of layer fit with the user's appearance, and the original characteristics of the user's appearance are not changed, and the generated user makeup image is more realistic. Since the user makeup image can reflect the actual situation of the makeup effect applied to the appearance of the target user, the target user can analyze and judge whether the makeup effect corresponding to the makeup description information is suitable for him / her based on the at least one user makeup image, and obtain a makeup plan suitable for him / her by modifying the makeup description information.

[0119] Based on the above embodiment, please refer to Figure 3. This embodiment of the present application also provides another makeup solution generation method, which generates a makeup implementation solution corresponding to a target makeup image based on the target makeup image. The makeup implementation solution includes multiple sequentially associated makeup implementation steps and makeup prompt information corresponding to each makeup implementation step. Similarly, using the method applied to the user terminal 110 and server 120 shown in Figure 1 as an example, the makeup solution generation method may include the following steps 206-210.

[0120] Step 206: The user terminal determines a target makeup image based on at least one user makeup image.

[0121] The target makeup image is a makeup image determined by the target user based on the at least one user makeup image. Therefore, the process of determining the target makeup image includes the following methods.

[0122] In a first implementation manner, after the user terminal displays at least one user makeup image, a user makeup image selected by a target user is determined as a target makeup image.

[0123] In a second implementation, if the target user does not select a target makeup image from at least one displayed user makeup image within a preset time period, the first user makeup image displayed in the front is determined as the target makeup image.

[0124] In the first and second implementations described above, the target makeup image is one of at least one user makeup image provided by the server. In this case, steps 206 through 210 are sequential with steps 201 through 205. That is, steps 201 through 210 are executed sequentially to complete the entire makeup plan generation method.

[0125] In a third implementation, after the user terminal displays at least one user-made-up image, if the target user browses through the at least one user-made-up image and fails to select a satisfactory user-made-up image, the target user can upload a self-made-up image on the user terminal to serve as the target made-up image. In other words, the target made-up image is a made-up image uploaded by the target user.

[0126] For the third implementation method, if the target makeup image is a user-uploaded makeup image, step 206 can be discontinuous with step 205. Specifically, steps 201 through 205 are performed independently to provide the target user with at least one user-uploaded makeup image, allowing them to understand how a specific makeup effect would work for them. Steps 206 through 210 are then performed independently to generate a makeup implementation plan for the target makeup image, facilitating their makeup application.

[0127] Step 207: The user terminal sends the target makeup image to the server to instruct the server to determine a makeup implementation solution corresponding to the target makeup image.

[0128] The makeup implementation plan is a specific implementation plan for achieving the makeup effect of the target makeup image. In other words, the makeup implementation plan is the detailed implementation information that guides the target user to restore or imitate the same makeup effect on their own appearance.

[0129] In some embodiments, the makeup implementation scheme includes a plurality of sequentially associated makeup implementation steps and makeup prompt information corresponding to each makeup implementation step.

[0130] As an example, taking the target makeup image as a beauty makeup effect applied to the user appearance image of the target user, the makeup implementation plan may include specific makeup steps to achieve the beauty makeup effect on the target user's face, as well as specific instructions for each makeup step.

[0131] As another example, taking the target makeup image as a dressing effect applied to the user appearance image of the target user, the makeup implementation plan may include specific dressing steps to achieve the dressing effect on the appearance of the target user, as well as specific instructions for each dressing step.

[0132] Step 208: The server receives the target makeup image sent by the user terminal, and determines a makeup implementation solution corresponding to the target makeup image.

[0133] In some embodiments, the process of determining the makeup implementation solution corresponding to the target makeup image is as follows: inputting the target makeup image into a trained makeup solution analysis model, and obtaining the makeup implementation solution corresponding to the target makeup image output by the makeup solution analysis model.

[0134] In one possible implementation, the makeup prompt information corresponding to a makeup implementation step includes one or more of step description information, makeup texture data, makeup product information required for the makeup implementation step, and auxiliary tool information. The makeup texture data includes makeup outline information and texture positioning information. The makeup outline information indicates the outline of the makeup effect corresponding to the makeup implementation step, and the texture positioning information indicates the location of the makeup effect corresponding to the makeup implementation step.

[0135] As an example, taking the makeup map data as eye shadow map data, since applying eye shadow often involves multiple steps and different colors need to be superimposed / blended at different positions around the eyes, the makeup contour information in the eye shadow map data can be the specific application shape of each color of eye shadow, and the map positioning information indicates the specific application position of each color of eye shadow.

[0136] Step 209: The server sends the makeup implementation plan to the user terminal to instruct the user terminal to display the makeup implementation plan.

[0137] It should be noted that when the server sends the makeup implementation plan to the user terminal, it can send the entire makeup implementation plan to the user terminal at once, instructing the user terminal to sequentially display the makeup prompt information corresponding to each makeup implementation step in the makeup implementation plan. Of course, the server can also send makeup prompt information corresponding to any makeup implementation step to the user terminal based on the makeup needs of the target user, and this embodiment of the application does not limit this.

[0138] Step 210: The user terminal receives and displays the makeup implementation plan sent by the server.

[0139] In some embodiments, the process in which the server sends the makeup implementation plan step by step by interacting with the user terminal is as follows: the server sends makeup prompt information corresponding to the first makeup implementation step to the user terminal, and the user terminal receives and displays the makeup prompt information corresponding to the first makeup implementation step. In response to the step jump operation triggered by the target user for skipping the first makeup implementation step, the user terminal sends a step jump instruction to the server, and the step jump instruction is used to request the makeup prompt information corresponding to the second makeup implementation step. After receiving the step jump instruction sent by the user terminal for skipping the first makeup implementation step, the server sends the makeup prompt information corresponding to the second makeup implementation step to the user terminal in response to the step jump instruction, and the user terminal receives and displays the makeup prompt information corresponding to the second makeup implementation step.

[0140] The first makeup implementation step is any one of the makeup implementation steps in the makeup implementation scheme, and the second makeup implementation step is the next makeup implementation step adjacent to the first makeup implementation step in the makeup implementation scheme.

[0141] It should be understood that the above-mentioned step jump instruction for skipping the first makeup implementation step can be triggered after the target user browses and executes the specific makeup corresponding to the first makeup implementation step. At this time, the target user executes the first makeup implementation step while imitating the makeup, that is, the sequence jumps to the second makeup implementation step. The above-mentioned step jump instruction for skipping the first makeup implementation step can also be triggered when the target user browses the makeup prompt information for the first makeup implementation step but does not execute the specific makeup. At this time, the target user does not execute the first makeup implementation step while imitating the makeup, that is, the first makeup implementation step is skipped.

[0142] As an example, if the makeup implementation scheme includes makeup implementation step 1, makeup implementation step 2, makeup implementation step 3, makeup implementation step 4 and makeup implementation step 5, the process of the server and the user terminal sending the makeup implementation scheme step by step can be: the server sends makeup prompt information a corresponding to makeup implementation step 1 to the user terminal, and after the user terminal receives and displays the makeup prompt information a, it detects whether the target user triggers the step jump operation for skipping the first makeup implementation step. If the user terminal detects that the target user has triggered the step jump operation, it sends a step jump instruction to the server. The server receives and responds to the step jump instruction, and sends makeup prompt information b corresponding to makeup implementation step 2 to the user terminal. After the user terminal receives and displays the makeup prompt information b, it continues to execute the step of detecting whether the target user has triggered the step jump operation. In this way, through the interaction between the server and the user terminal, the user terminal is instructed to display the makeup implementation plan to the target user, that is, to display the makeup prompt information a corresponding to makeup implementation step 1, the makeup prompt information b corresponding to makeup implementation step 2, the makeup prompt information c corresponding to makeup implementation step 3, the makeup prompt information d corresponding to makeup implementation step 4 and the makeup prompt information e corresponding to makeup implementation step 5 in sequence.

[0143] As described above, the makeup prompt information for a makeup implementation step includes one or more of step description information, makeup texture data, makeup product information required for the makeup implementation step, and auxiliary tool information. The makeup texture data includes makeup outline information and texture positioning information. The makeup outline information indicates the outline of the makeup effect corresponding to the makeup implementation step, and the texture positioning information indicates the location of the makeup effect corresponding to the makeup implementation step.

[0144] As an example, for the same makeup implementation step, based on the step description information corresponding to the makeup implementation step, the low-rank adaptation of large language lodels (LORA) mapping model is used to generate the corresponding makeup contour information and mapping positioning information, thereby obtaining the makeup mapping data corresponding to the makeup implementation step. The specific implementation process can be found in the relevant existing technology and will not be explained in detail here.

[0145] The LoRa model is a model that requires only a small amount of data for training. When generating images, the LoRa model is used in conjunction with a larger model to adjust the output image. For example, the larger model is like a person without makeup, while the LoRa model is like that person having makeup, plastic surgery, or cosplay, but the underlying foundation is still the larger model. Of course, the LoRa model isn't limited to people; there are corresponding LoRa models for various scenes, anime, and genres.

[0146] In the case where the makeup prompt information of the second makeup implementation step includes makeup map data, the user terminal can display the makeup effect map corresponding to the second makeup implementation step, and the implementation process includes the following steps (1)-(3).

[0147] (1) Obtain the real-time appearance image of the target user.

[0148] In a possible implementation, the user terminal may capture the appearance image of the target user in real time through a camera built into the user terminal or a camera connected to the user terminal to obtain the real-time appearance image of the target user at the current moment.

[0149] As previously mentioned, if the step jump instruction is triggered after the target user browses and executes the specific makeup corresponding to the first makeup implementation step, at this time, the target user has already executed the first makeup implementation step while imitating the makeup, and the real-time appearance image is the makeup image of the target user after completing the first makeup implementation step. If the step jump instruction is triggered after the target user browses the makeup prompt information for the first makeup implementation step but does not execute the specific makeup, at this time, the target user has not executed the first makeup implementation step while imitating the makeup, and the real-time appearance image is the makeup image of the target user before browsing the first makeup implementation step.

[0150] That is, after receiving the makeup prompt information corresponding to the second makeup step, the user terminal executes the above step (1) to obtain the real-time appearance image of the target user, and then executes the following step (2) based on the real-time appearance image and the makeup prompt information corresponding to the second makeup step.

[0151] (2) Based on the makeup map data corresponding to the second makeup implementation step, the real-time appearance image is rendered with makeup effects to obtain a makeup effect map corresponding to the second makeup implementation step.

[0152] The makeup effect image corresponding to the second makeup implementation step is generated based on the makeup texture data corresponding to the second makeup implementation step, by applying the makeup effect corresponding to the second makeup implementation step to the real-time appearance image.

[0153] Considering that the user's facial features and body shape not only have height and width information, but also depth information, in order to ensure that the makeup effect is more in line with the user's actual appearance, when generating the makeup rendering, it is also necessary to obtain the second geometric grid image corresponding to the real-time appearance image to reflect the depth information of the target user's current appearance, so that the makeup effect presented in the makeup rendering is better.

[0154] The second geometric mesh image can be generated from a two-dimensional real-time appearance image. For example, a mesh surface graph is generated based on the mesh data corresponding to the real-time appearance image to obtain the second geometric mesh image corresponding to the real-time appearance image. This embodiment of the present application does not limit the method for generating the second geometric mesh image; reference may be made to related mesh generation algorithms.

[0155] In one possible implementation method, the implementation process of generating a makeup effect map corresponding to the second makeup implementation step is: generating a second geometric grid image corresponding to the real-time appearance image; then, based on the texture positioning information corresponding to the second makeup implementation step and the second geometric grid image, determining the makeup rendering position in the real-time appearance image; then, based on the makeup rendering position, performing makeup effect rendering on the real-time appearance image according to the makeup contour information corresponding to the second makeup implementation step, to obtain a makeup effect map corresponding to the second makeup implementation step.

[0156] Among them, the texture positioning information may include texture position coordinates, texture position corresponding to human bone points, etc. Based on the texture positioning information and the second geometric grid image, the makeup rendering position indicated by the texture positioning information can be determined in the real-time appearance image.

[0157] It should be noted that the specific implementation method of determining the rendering position in the real-time appearance image based on the mapping position coordinates and the mapping position corresponding to the human skeleton point can be referred to the relevant existing technology, and the embodiments of the present application do not limit this.

[0158] In addition, after determining the makeup rendering position, the augmented reality kit (AR Kit) that comes with / installed on the user terminal can be used to render the makeup effect on the real-time appearance image according to the makeup contour information corresponding to the second makeup implementation step, thereby achieving mixed rendering of the virtual content layer and the real-time content layer.

[0159] (3) Display the makeup effect diagram corresponding to the second makeup implementation step.

[0160] The user terminal displays the makeup effect diagram corresponding to the second makeup implementation step in the display interface, which is convenient for the user to imitate and perform makeup.

[0161] Based on the above steps (1)-(3), it can be seen that, considering that the target user may have performed the makeup of the first makeup implementation step or may not have performed the makeup of the first makeup implementation step, when displaying the second makeup effect picture, the embodiment of the present application does not mechanically continue to superimpose the makeup texture data corresponding to the second makeup implementation step on the makeup effect picture corresponding to the first makeup implementation step, but obtains the real-time appearance image of the target user, and generates the makeup effect picture corresponding to the second makeup implementation step based on the real-time appearance image and the makeup texture data corresponding to the second makeup implementation step. In this way, the makeup effect pictures corresponding to each makeup implementation step are generated in real time according to the actual makeup progress of the user, thereby improving the real-time and accuracy of the makeup effect pictures corresponding to the makeup implementation steps.

[0162] If the makeup prompt information for a makeup implementation step also includes step description information, makeup product information, and auxiliary tool information, the user terminal may simultaneously display the step description information, makeup effect image, makeup product information, and auxiliary tool information corresponding to the second makeup implementation step. The makeup effect image, step description information, makeup product information, and auxiliary tool information are displayed in separate areas, and the display areas for the step description information, makeup product information, and auxiliary tool information surround the display area for the makeup effect image.

[0163] As an example, referring to FIG4 , the display interface of the user terminal is divided into five areas, namely, top, middle, bottom, left and right, to simultaneously display the step description information, makeup effect diagram, makeup product information and auxiliary tool information corresponding to the second makeup implementation step.

[0164] Among them, the middle area, as the largest display area, can be used to display the makeup effect diagram of the second makeup implementation step, that is, the rendered image after the real-time appearance image of the target user is superimposed with the makeup map data, so that the user can imitate the makeup. The upper area displays the step description information of the second makeup implementation step, and the step description information is used to indicate the specific implementation process of the second makeup implementation step. Optionally, the key information in the step description information can be displayed visually, and at the same time, more detailed and more friendly step description information can be provided to the target user through voice prompts. The left area is used to display the makeup product information of the second makeup implementation step, and the makeup product information may include product diagrams, brands, specifications and other information of specific recommended products determined based on the context. The right area is used to display auxiliary tool information when implementing the second makeup step, such as beauty brushes, eyebrow pencils, accessories, etc.; if there is no specific recommended brand, the type and characteristics of the specific tool are clearly displayed, and this embodiment of the application does not limit this.

[0165] Optionally, the current completion progress of the makeup implementation plan can also be displayed on the left side of the lower area, which can be displayed in the form of a percentage; the right side of the lower area can present a comparison between the second makeup implementation step and the total makeup implementation step, so that the target user can understand the current makeup step and the overall makeup progress.

[0166] In an embodiment of the present application, the user terminal can also obtain the target makeup image determined by the target user, and send the target makeup image to the server to request the server to provide a makeup implementation solution corresponding to the target makeup image. That is, when the target user provides the target makeup image, the server can use the trained makeup solution analysis model to infer the makeup implementation solution corresponding to the target makeup image, so that the target user can imitate makeup based on the makeup implementation solution. Moreover, the makeup implementation solution includes a plurality of sequentially associated makeup implementation steps and makeup prompt information corresponding to each makeup implementation step. The target user can refer to the makeup prompt information corresponding to each makeup implementation step in turn, and complete the entire makeup implementation solution in a manner similar to "tracing", which greatly improves the efficiency of the user's imitation of makeup and increases user satisfaction.

[0167] Based on the makeup plan generation method shown in the above embodiment, the present application can generate personalized and customized user makeup effect pictures for users based on two trained AI generated content (AI generated content, AIGC) large models: makeup effect generation model and makeup plan analysis model; it can also generate makeup implementation plans based on the target makeup images provided by the user to guide the user to imitate and complete the entire makeup.

[0168] The makeup effect generation model and makeup solution analysis model may include multiple sub-models, requiring extensive learning and computational analysis to generate user makeup images and implementation solutions. Therefore, considering computing power requirements and resource consumption, the makeup effect generation model and makeup solution analysis model can be deployed on a cloud server. Specifically, the server shown in Figures 1-3 is a cloud server, or a cloud computing server center.

[0169] Referring to the makeup scheme generation system shown in FIG5 , the makeup scheme generation system includes a user terminal and a cloud server. Among them, the user terminal includes: an image acquisition device (such as a camera), an image output device (such as a display screen), an audio input device (such as a microphone), an audio output device (such as a speaker) and a user-end processing system, etc.; the user-end processing system includes an interconnected image acquisition and Mesh generation system, an intelligent interactive feedback system and an AR layered rendering system, etc. The cloud server includes a cloud processing system, which includes an AIGC large model, a prompt template library, a recommendation and evaluation system, a task control and scheduling system, etc. Among them, the AIGC large model includes a makeup effect generation model and a makeup scheme analysis model.

[0170] On the user terminal side, the image acquisition and mesh generation system is connected to the image acquisition device and image output device to capture user appearance images, real-time appearance images, etc., and generate corresponding geometric mesh images. The intelligent interactive feedback system is connected to the image acquisition device, image output device, audio input device, and audio output device, etc., to interact with the target user and collect user input text, voice commands, and other information. Among them, the image acquisition device is used to collect video data of the target user; the image output device is used to display images and information, such as displaying at least one user makeup image and makeup generation plan; the audio input device is used to collect the target user's voice interaction commands; and the audio output device is used to play audio, such as playing step-by-step instructions for makeup implementation steps.

[0171] When the user-side processing system executes the makeup solution generation method, the image acquisition and mesh generation system is configured to, in a first phase, receive a target user's appearance image / video data sent by an image acquisition device, generate a first geometric mesh image corresponding to the user's appearance image, and then transmit the first geometric mesh image to the intelligent interactive feedback system. In a second phase, the image acquisition and mesh generation system is further configured to receive real-time appearance image / video data of the target user sent by the image acquisition device, generate a second geometric mesh image corresponding to the real-time appearance image, and then transmit the second geometric mesh image to the AR layered rendering system. The intelligent interactive feedback system is configured to, in a first phase, receive the target user's appearance image sent by the image acquisition device, receive makeup description information of the target user sent by an audio input device, and provide feedback to the image output device on at least one user makeup image. In a second phase, the intelligent interactive feedback system is further configured to receive a target makeup image determined by the target user, receive a step jump instruction sent by the audio input device, provide feedback on a makeup implementation solution corresponding to the target makeup image to the image output device, and provide feedback on step description information of the makeup implementation steps in the makeup implementation solution to the audio output device. The AR layered rendering system is used to receive the makeup texture data corresponding to any makeup implementation step sent by the cloud server in the second stage, and based on the makeup texture data, perform makeup effect rendering on the real-time user appearance image provided by the image acquisition device to generate a makeup effect image corresponding to the makeup implementation step.

[0172] On the cloud server side, the task control and scheduling system receives input information such as commands, videos, and images from user terminals, performs task decomposition and scheduling, and coordinates the backend AIGC large model (including the makeup effect generation model and makeup solution analysis model), the prompt template library, and the recommendation and evaluation system to complete a complex personalized makeup solution generation task and provide feedback to the user terminal. The prompt template library, which includes multiple makeup prompt templates, is used to enrich and refine makeup description information in the first phase to determine the target prompt template corresponding to the makeup description. The makeup effect generation model is used in the first phase to generate at least one user makeup image based on the user's appearance image, the first geometric grid image corresponding to the user's appearance image, and the target prompt template. The recommendation and evaluation system is used in the first phase to evaluate the display priority of each user makeup image and, based on the display priority of the at least one user image, determine the image display order of the at least one user makeup image. The makeup solution analysis model is used in the second phase to generate a makeup implementation solution corresponding to the target makeup image provided by the user terminal.

[0173] To sum up, the user terminal and the cloud server implement the makeup plan generation method provided in the embodiment of the present application through end-cloud collaboration. In this way, by utilizing the powerful computing power advantage of the cloud, personalized makeup plan generation services can be provided to multiple user terminals at the same time.

[0174] Since the makeup scheme generation method of the present application includes two scenarios, beauty makeup and dressing, and its implementation process includes two stages, the first stage generates a user makeup image, which may include a user beauty makeup image and a user dressing image; the second stage generates a makeup implementation plan, which may include a beauty makeup implementation plan and a dressing implementation plan.

[0175] Next, the specific process of executing the makeup plan generation method in two scenarios is described in detail.

[0176] Based on the above FIG5 , taking the generation of personalized beauty solutions as an example, the processes of generating user beauty images in the first stage and generating beauty implementation solutions in the second stage are respectively described in detail.

[0177] Referring to FIG6 , in the first stage, the user terminal interacts with the cloud server to provide the target user with a user beauty image, and the process includes the following steps 1-6.

[0178] 1. The user terminal obtains the target user's facial image and beauty description information.

[0179] The beauty description information indicates the beauty effect expected by the target user. For example, the beauty description information can be Korean makeup, suitable for daily work, friendly and energetic, etc.

[0180] 2. The image acquisition and mesh generation system generates a corresponding facial mesh image based on the facial image of the target user.

[0181] 3. The intelligent interactive feedback system sends the target user's facial image, facial grid image, and beauty description information to the cloud server.

[0182] 4. Based on the beauty description information, the cloud server determines the target beauty template through the prompt template library and sends the target beauty template to the makeup effect generation model.

[0183] 5. The makeup effect generation model generates at least one user makeup image based on the facial image, the facial mesh image, and the target makeup template.

[0184] In a specific implementation, the makeup effect generation model can be a beauty makeup effect generation model to generate at least one user beauty makeup image.

[0185] 6. The recommendation and evaluation system evaluates the display priority of each user's beauty image, thereby determining the image display order of the at least one user's beauty image, and sends the at least one user's beauty image and the image display order to the user terminal.

[0186] The user terminal receives at least one user beauty makeup image and displays the at least one user beauty makeup image in the order in which the images are displayed. The target user interacts with the user terminal through the intelligent interactive feedback system to determine the target beauty makeup image. If the target user is satisfied with the currently displayed user beauty makeup images and selects the target beauty makeup image, the process proceeds to Phase 2. If the target user is dissatisfied with the currently displayed user beauty makeup images and is unable to select the target beauty makeup image, the target user may provide some additional beauty makeup description information through the intelligent interactive feedback system. In response to the newly provided beauty makeup description information, the user terminal jumps to Step 3 above and loops through the subsequent steps until the target user selects the target beauty makeup image from the at least one user beauty makeup image displayed on the user terminal.

[0187] Referring to FIG. 7 , in the second stage, the user terminal interacts with the cloud server to provide a beauty makeup implementation solution for the target user, including the following steps 1-6.

[0188] 1. The user terminal obtains the real-time facial image of the target user.

[0189] 2. The image acquisition and mesh generation system generates a corresponding real-time facial mesh image based on the real-time facial image of the target user.

[0190] 3. An intelligent interactive feedback system interacts with the target user in a way that any user terminal can understand, such as natural language and text, to obtain the target beauty image determined by the target user and send the target beauty image to the cloud server.

[0191] 4. The cloud server determines the beauty implementation plan corresponding to the target beauty image through the makeup plan analysis model. The beauty implementation plan includes multiple sequentially associated beauty implementation steps and beauty prompt information corresponding to each beauty implementation step.

[0192] 5. The makeup solution analysis model sends the makeup prompt information corresponding to the Mth makeup implementation step to the user terminal. The makeup prompt information includes makeup map data, step description information, makeup product information and auxiliary tool information.

[0193] In specific implementation, the makeup solution analysis model can be a beauty makeup solution analysis model to generate a beauty makeup implementation solution corresponding to the target beauty makeup image.

[0194] 6. The AR layered rendering system of the user terminal performs makeup effect rendering on the real-time facial image of the target user based on the makeup texture data corresponding to the Mth makeup implementation step, obtains the makeup effect picture corresponding to the Mth makeup implementation step, and displays the makeup effect picture, step description information, makeup product information and auxiliary tool information.

[0195] In this way, the target user refers to the makeup effect picture corresponding to the Mth beauty makeup implementation step, follows the step instruction information corresponding to the Mth beauty makeup implementation step, and uses the makeup product information and auxiliary tool information corresponding to the Mth beauty makeup implementation step to "trace" to complete the makeup operation of the Mth beauty makeup implementation step.

[0196] Among them, the above-mentioned Mth beauty makeup implementation step is any beauty makeup implementation step in the beauty makeup implementation plan.

[0197] In addition, the intelligent interactive feedback system is also used to detect the target user's feedback on the Mth beauty implementation step, and in response to the step jump operation triggered by the target user, send a step jump instruction to the server. The target user's feedback on the current process may include: repeating the current step, skipping the current step, proceeding to the next step, etc. This embodiment of the application does not limit this, and the corresponding instructions are not limited to the above-mentioned step jump instructions.

[0198] That is, when displaying the makeup implementation plan, the target user can independently control the display progress, so that they can apply makeup in a similar way to "tracing".

[0199] The makeup solution analysis model in the server receives and responds to the step jump instruction, sending the makeup prompt information corresponding to the M+1th makeup implementation step to the user terminal. The user terminal repeats steps 4-6 until the entire makeup implementation solution is displayed to the target user.

[0200] To sum up, the makeup solution generation method provided in this application is applied in beauty makeup scenarios. It can not only generate personalized user makeup images according to the actual needs of the target users, so that users can understand their own beauty makeup effects; it can also provide specific and complete beauty makeup implementation solutions based on the target beauty makeup images, so that target users can use a similar "tracing" method to apply makeup to achieve the desired beauty makeup effect.

[0201] Based on Figure 5 above, the following describes the process of generating a user outfit image in detail, using the example of generating a personalized outfit plan. Since the outfit implementation plan does not involve a detailed, complex implementation process, the user can complete the outfit process by following the instructions. That is, after generating a user outfit image, the target user can refer to the outfit items in the user outfit image and select similar, personal items to complete the outfit. Therefore, when generating a personalized outfit plan for a target user, only the first stage can be executed to generate at least one user outfit image, without the need for the second stage.

[0202] Referring to FIG8 , the process of the user terminal interacting with the cloud server to provide the target user with a user outfit image includes the following steps 1-6.

[0203] 1. The user terminal obtains the target user's full-body image and outfit description information.

[0204] 2. The image acquisition and mesh generation system generates a corresponding full-body mesh image based on the full-body image of the target user.

[0205] 3. The intelligent interactive feedback system sends the target user's full-body image, full-body grid image, and outfit description information to the cloud server.

[0206] The outfit description information indicates the outfit effect desired by the target user, for example, today's outfit recommendation, American style, office lady, moderate price, etc.

[0207] 4. Based on the outfit description information, the cloud server determines the target outfit template through the prompt template library and sends the target outfit template to the makeup effect generation model.

[0208] 5. The makeup effect generation model generates at least one user outfit image based on the full-body image, full-body mesh image, and target outfit template.

[0209] In a specific implementation, the makeup effect generation model can be a dressing effect generation model to generate at least one user dressing image.

[0210] 6. The recommendation and evaluation system evaluates the display priority of each user's outfit image, thereby determining the image display order of the at least one user's outfit image, and sends the at least one user's outfit image and the image display order to the user terminal.

[0211] Among them, the display priority of each user's outfit images can be determined based on the target user's historical data, current fashion trends, etc.

[0212] The user terminal receives at least one user outfit image and displays the at least one user outfit image in the order in which the images are displayed. The target user interacts with the user terminal through the intelligent interactive feedback system to determine the target outfit image. If the target user is satisfied with the currently displayed user outfit image and selects the target outfit image from it, the operation ends. If the target user is not satisfied with the currently displayed user outfit image and cannot select the target outfit image from it, the target user can provide some new outfit description information through the intelligent interactive feedback system. In response to the newly provided outfit description information, the user terminal jumps to step 3 above and loops through the subsequent steps until the target user can select the target outfit image from the at least one user outfit image displayed on the user terminal.

[0213] It should be noted that for complex dressing styles such as layering, if the user cannot complete the entire dressing process based on the target dressing image, they can also send the target dressing image to the cloud server and enter the second stage to obtain the dressing implementation solution corresponding to the target dressing image. This embodiment of the application does not limit this.

[0214] To sum up, the makeup plan generation method provided in this application can be applied in the dressing scene to generate personalized user dressing images based on the actual body shape and dressing needs of the target user, so that the user can understand the dressing effect in his or her actual dressing situation, and thus quickly find a dressing style that satisfies and suits him or her.

[0215] Furthermore, while the makeup and makeup scheme generation method provided in the embodiments of this application focuses on the two scenarios of "beauty makeup" and "outfitting," the inventive concept of this application is applicable to any scenario involving personalized and customized scheme generation and the matching of multiple items. For example, interior decoration and interior furniture matching are also applicable.

[0216] Please refer to Figure 9, which is a schematic diagram of the structure of a makeup plan generation device provided in an embodiment of the present application. This makeup plan generation device 900 can be implemented by software, hardware, or a combination of both, forming part or all of the server shown in Figures 1-8. This makeup plan generation device 900 includes: a receiving module 901, a makeup image generation module 902, and a sending module 903.

[0217] Receiving module 901, configured to receive a user appearance image and makeup description information of a target user sent by a user terminal, where the makeup description information indicates a makeup effect desired by the target user;

[0218] A makeup image generation module 902 is configured to generate at least one user makeup image based on the user appearance image and makeup description information using a trained makeup effect generation model, wherein the at least one user makeup image is generated by applying at least one makeup effect to the user appearance image;

[0219] The sending module 903 is configured to send at least one user makeup image to a user terminal to instruct the user terminal to display the at least one user makeup image.

[0220] Optionally, the makeup image generation module 902 includes:

[0221] A grid image acquisition unit, configured to acquire a first geometric grid image corresponding to the user's appearance image;

[0222] The makeup image generation unit is used to generate at least one user makeup image based on the user appearance image, the first geometric grid image and the makeup description information through a trained makeup effect generation model.

[0223] Optionally, the makeup image generating unit includes:

[0224] A template selection subunit is used to determine a target prompt template from a prompt template library based on the makeup description information, wherein the prompt template library includes multiple makeup prompt templates, each of which includes multiple makeup prompts describing a makeup effect;

[0225] The makeup image generation subunit is used to input the target prompt template, the user appearance image and the first geometric grid image into the makeup effect generation model to obtain at least one user makeup image output by the makeup effect generation model.

[0226] Optionally, the sending module 903 is further configured to:

[0227] determining a display priority of each user-made-up image in at least one user-made-up image;

[0228] sorting the at least one user makeup image based on a display priority of the at least one user makeup image to obtain an image display order of the at least one user makeup image;

[0229] At least one user makeup image and an image display order are sent to a user terminal to instruct the user terminal to display the at least one user makeup image according to the image display order.

[0230] Optionally, the apparatus 900 further includes:

[0231] The receiving module 901 is further configured to receive a target makeup image sent by a user terminal, where the target makeup image is a makeup image determined by a target user based on at least one user makeup image;

[0232] A makeup scheme generation module is used to determine a makeup implementation scheme corresponding to a target makeup image. The makeup implementation scheme includes multiple sequentially associated makeup implementation steps and makeup prompt information corresponding to each makeup implementation step.

[0233] The sending module 903 is further configured to send the makeup implementation plan to the user terminal to instruct the user terminal to display the makeup implementation plan.

[0234] Optionally, the makeup plan generation module is specifically used to:

[0235] The target makeup image is input into the trained makeup solution analysis model to obtain the makeup implementation solution corresponding to the target makeup image output by the makeup solution analysis model.

[0236] Optionally, the sending module 903 is further configured to:

[0237] Sending makeup prompt information corresponding to a first makeup implementation step to the user terminal, where the first makeup implementation step is any one of the makeup implementation steps in the makeup implementation solution;

[0238] If a step jump instruction for skipping the first makeup implementation step is received from the user terminal, in response to the step jump instruction, makeup prompt information corresponding to the second makeup implementation step is sent to the user terminal to instruct the user terminal to display the makeup prompt information corresponding to the second makeup implementation step. The second makeup implementation step is the next makeup implementation step adjacent to the first makeup implementation step in the makeup implementation scheme.

[0239] Optionally, the makeup prompt information corresponding to the makeup implementation step includes one or more of step description information, makeup texture data, makeup product information required for the makeup implementation step, and auxiliary tool information;

[0240] The makeup map data includes makeup contour information and map positioning information. The makeup contour information indicates the contour of the makeup effect corresponding to the makeup implementation step, and the map positioning information indicates the position of the makeup effect corresponding to the makeup implementation step.

[0241] In an embodiment of the present application, the makeup scheme generating device 900 generates at least one user makeup image based on the user appearance image of the target user and the makeup description information provided by the target user through a makeup effect generation model. Since the user appearance image can accurately reflect the appearance characteristics of the target user, and the at least one user makeup image is a makeup image generated by applying at least one makeup effect to the user appearance image, the makeup effect in the user makeup image has a higher degree of layer fit with the user's appearance, and the original characteristics of the user's appearance are not changed, and the generated user makeup image is more realistic. Since the user makeup image can reflect the actual situation of the makeup effect applied to the appearance of the target user, the target user can analyze and judge whether the makeup effect corresponding to the makeup description information is suitable for him / her based on the at least one user makeup image, and obtain a makeup scheme suitable for him / her by modifying the makeup description information.

[0242] It should be noted that: when the makeup solution generation device 900 provided in the above embodiment generates at least one user makeup image based on the user appearance image and makeup description information, or generates a makeup implementation solution corresponding to the target makeup image based on the target makeup image, only the division of the above functional modules is used as an example. In actual application, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the makeup solution generation device 900 provided in the above embodiment and the makeup solution generation method embodiment belong to the same concept. The specific implementation process is detailed in the method embodiment and will not be repeated here.

[0243] The receiving module 901, the makeup image generation module 902, and the sending module 903 can all be implemented via software or hardware. For example, the implementation of the makeup image generation module 902 will be described below using the makeup image generation module 902 as an example. Similarly, the implementation of the receiving module 901 and the sending module 903 can refer to the implementation of the makeup image generation module 902.

[0244] As an example of a software functional unit, the makeup image generation module 902 may include code running on a computing instance. The computing instance may include at least one of a physical host (computing device), a virtual machine, and a container. Furthermore, the computing instance may be one or more. For example, the makeup image generation module 902 may include code running on multiple hosts / virtual machines / containers. It should be noted that the multiple hosts / virtual machines / containers used to run the code may be distributed in the same region or in different regions. Furthermore, the multiple hosts / virtual machines / containers used to run the code may be distributed in the same availability zone (AZ) or in different AZs, each AZ including one data center or multiple geographically close data centers. Typically, a region may include multiple AZs.

[0245] Similarly, multiple hosts / virtual machines / containers used to run the code can be distributed within the same virtual private cloud (VPC) or across multiple VPCs. Typically, a VPC is set up within a region. Cross-region communication between two VPCs within the same region, or between VPCs in different regions, requires a communication gateway within each VPC to interconnect the VPCs.

[0246] As an example of a hardware functional unit, the makeup image generation module 902 may include at least one computing device, such as a server. Alternatively, the makeup image generation module 902 may be implemented using an application-specific integrated circuit (ASIC) or a programmable logic device (PLD). The PLD may be a complex programmable logical device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL), or any combination thereof.

[0247] The multiple computing devices included in the makeup image generation module 902 can be distributed in the same region or in different regions. The multiple computing devices included in the makeup image generation module 902 can be distributed in the same AZ or in different AZs. Similarly, the multiple computing devices included in the makeup image generation module 902 can be distributed in the same VPC or in multiple VPCs. The multiple computing devices can be any combination of computing devices such as servers, ASICs, PLDs, CPLDs, FPGAs, and GALs.

[0248] It should be noted that, in other embodiments, the makeup image generation module 902 can be used to execute any step in the makeup plan generation method, the receiving module 901 can be used to execute any step in the makeup plan generation method, and the sending module 903 can be used to execute any step in the makeup plan generation method. The steps that the receiving module 901, the makeup image generation module 902 and the sending module 903 are responsible for implementing can be specified as needed. The full functions of the makeup plan generation device are realized by respectively implementing different steps in the makeup plan generation method through the receiving module 901, the makeup image generation module 902 and the sending module 903.

[0249] Please refer to Figure 10, which is a schematic diagram of the structure of a makeup plan generation device provided in an embodiment of the present application. The makeup plan generation device 1000 can be implemented by software, hardware, or a combination of both to form part or all of the user terminal shown in Figures 1-8. The makeup plan generation device 1000 includes: an acquisition module 1001, a sending module 1002, and a receiving module 1003.

[0250] An acquisition module 1001 is configured to acquire an appearance image and makeup description information of a target user, where the makeup description information indicates a makeup effect desired by the target user.

[0251] a sending module 1002 configured to send a user appearance image and makeup description information to a server, instructing the server to generate at least one user makeup image based on the user appearance image and the makeup description information using a trained makeup effect generation model, wherein the at least one user makeup image is generated by applying at least one makeup effect to the user appearance image;

[0252] The receiving module 1003 is configured to receive and display at least one user makeup image sent by the server.

[0253] Optionally, the receiving module 1003 is further configured to:

[0254] receiving an image display order of at least one user-made image sent by a server;

[0255] At least one user makeup image is displayed in an image display order.

[0256] Optionally, the apparatus 1000 further includes:

[0257] a determination module, configured to determine a target makeup image based on at least one user makeup image;

[0258] The sending module 1002 is further configured to send the target makeup image to the server to instruct the server to determine a makeup implementation solution corresponding to the target makeup image, wherein the makeup implementation solution includes a plurality of sequentially associated makeup implementation steps and makeup prompt information corresponding to each makeup implementation step;

[0259] The receiving module 1003 is further used to receive and display the makeup implementation plan sent by the server.

[0260] Optionally, the receiving module 1003 is further configured to:

[0261] A first receiving unit is configured to receive and display makeup prompt information corresponding to a first makeup implementation step sent by the server, where the first makeup implementation step is any one of the makeup implementation steps in the makeup implementation solution;

[0262] a control unit, configured to, in response to a step jump operation triggered by a target user for skipping a first makeup implementation step, send a step jump instruction to a server, wherein the step jump instruction is configured to request makeup prompt information corresponding to a second makeup implementation step, where the second makeup implementation step is a next makeup implementation step adjacent to the first makeup implementation step in the makeup implementation scheme;

[0263] The second receiving unit is used to receive and display makeup prompt information corresponding to the second makeup implementation step sent by the server.

[0264] Optionally, the makeup prompt information of the makeup implementation step includes one or more of step description information, makeup texture data, makeup product information required for the makeup implementation step, and auxiliary tool information;

[0265] The makeup map data includes makeup contour information and map positioning information. The makeup contour information indicates the contour of the makeup effect corresponding to the makeup implementation step, and the map positioning information indicates the position of the makeup effect corresponding to the makeup implementation step.

[0266] Optionally, the makeup prompt information of the makeup implementation step includes makeup map data; the second receiving unit is specifically configured to:

[0267] An image acquisition subunit, used to acquire a real-time appearance image of a target user;

[0268] A rendering subunit, configured to perform makeup effect rendering on the real-time appearance image based on the makeup map data corresponding to the second makeup implementation step, to obtain a makeup effect image corresponding to the second makeup implementation step;

[0269] The display subunit is used to display the makeup effect diagram corresponding to the second makeup implementation step.

[0270] Optionally, the rendering subunit is specifically configured to:

[0271] generating a second geometric mesh image corresponding to the real-time appearance image;

[0272] Determining a makeup rendering position in the real-time appearance image based on the texture positioning information corresponding to the second makeup implementation step and the second geometric mesh image;

[0273] Based on the makeup rendering position, the real-time appearance image is rendered with makeup effects according to the makeup contour information corresponding to the second makeup implementation step to obtain a makeup effect image corresponding to the second makeup implementation step.

[0274] Optionally, the makeup prompt information of the makeup implementation steps further includes step description information, makeup product information and auxiliary tool information; and the second receiving unit is further configured to:

[0275] Displaying step description information corresponding to the second makeup implementation step, makeup product information corresponding to the second makeup implementation step, and auxiliary tool information corresponding to the second makeup implementation step;

[0276] Among them, the makeup effect picture, step description information, makeup product information and auxiliary tool information are displayed in different areas respectively, and the display areas of the step description information, makeup product information and auxiliary tool information surround the display area of ​​the makeup effect picture.

[0277] In an embodiment of the present application, the makeup scheme generating device 1000 can interact with the server and provide the target user's user appearance image and makeup description information to the server to instruct the server to generate at least one user makeup image, and then receive and display the at least one user makeup image for the user to browse and select. Since the user appearance image can accurately reflect the appearance characteristics of the target user, and the at least one user makeup image is a makeup image generated by applying at least one makeup effect to the user appearance image, the makeup effect in the user makeup image has a higher degree of layer fit with the user's appearance, and does not change the original characteristics of the user's appearance, and the generated user makeup image is more realistic. Since the user makeup image can reflect the actual situation of the makeup effect applied to the target user's appearance, the target user can analyze and judge whether the makeup effect corresponding to the makeup description information is suitable for him / her based on the at least one user makeup image, and obtain a makeup scheme suitable for him / her by modifying the makeup description information.

[0278] It should be noted that: the makeup solution generation device 1000 provided in the above embodiment only uses the division of the above functional modules as an example when providing a user appearance image and makeup description information and displaying at least one user makeup image, or providing a target makeup image and displaying the makeup implementation solution corresponding to the target makeup image. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the makeup solution generation device 1000 provided in the above embodiment and the makeup solution generation method embodiment belong to the same concept. The specific implementation process is detailed in the method embodiment and will not be repeated here.

[0279] Please refer to Figure 11, which is a schematic diagram of the structure of a computing device provided in an embodiment of the present application. At least one computing device can constitute a server that implements the makeup plan generation method provided in an embodiment of the present application. The computing device 1100 includes: a bus 1102, a processor 1104, a memory 1106, and a communication interface 1108. The processor 1104, the memory 1106, and the communication interface 1108 communicate with each other via the bus 1102. The embodiment of the present application does not limit the number of processors and memories in the computing device 1100.

[0280] Bus 1102 may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, among others. Buses may be classified as address buses, data buses, control buses, and the like. For ease of illustration, FIG11 illustrates a single bus line, but this does not imply a single bus or type of bus. Bus 1102 may include a path for transmitting information between various components of computing device 1100 (e.g., memory 1106, processor 1104, and communication interface 1108).

[0281] The processor 1104 may include any one or more processors such as a central processing unit (CPU), a graphics processing unit (GPU), a microprocessor (MP), or a digital signal processor (DSP).

[0282] The memory 1106 may include volatile memory, such as random access memory (RAM). The processor 1104 may also include non-volatile memory, such as read-only memory (ROM), flash memory, hard disk drive (HDD), or solid state drive (SSD).

[0283] In the embodiment of the present application, memory 1106 stores executable program code, and processor 1104 executes this executable program code to implement the functions of the aforementioned receiving module 901, makeup image generation module 902, and sending module 903, thereby implementing the makeup plan generation method shown in Figures 1-8. In other words, memory 1106 stores computer program instructions for executing the makeup plan generation method executed by the server shown in Figures 1-8.

[0284] The communication interface 1108 uses a transceiver module such as, but not limited to, a network interface card or a transceiver to implement communication between the computing device 1100 and other devices or a communication network.

[0285] The present application also provides a computing device cluster that constitutes a server for executing the makeup scheme generation method provided in the present application. The computing device cluster includes at least one computing device. The computing device can be a server, such as a central server, an edge server, or a local server in a local data center. In some embodiments, the computing device can also be a terminal device such as a desktop computer, a laptop computer, or a smartphone.

[0286] As shown in Figure 12, the computing device cluster includes at least one computing device 1100. The memory 1106 in one or more computing devices 1100 in the computing device cluster may store the same computer program instructions for executing the makeup plan generation method executed by the server shown in Figures 1-8.

[0287] In some possible implementations, the memory 1106 of one or more computing devices 1100 in the computing device cluster may also store partial instructions for the server to execute the makeup plan generation method. In other words, the combination of one or more computing devices 1100 can collectively execute computer program instructions for executing the makeup plan generation method executed by the server as shown in Figures 1-8.

[0288] It should be noted that the memory 1106 in different computing devices 1100 in the computing device cluster can store different instructions, each for executing a portion of the functions of the makeup plan generating apparatus 900. In other words, the instructions stored in the memory 1106 in different computing devices 1100 can implement the functions of one or more of the receiving module 901, the makeup image generating module 902, and the sending module 903.

[0289] In some possible implementations, one or more computing devices in a computing device cluster may be connected via a network. The network may be a wide area network (WAN) or a local area network (LAN). FIG. 13 illustrates one possible implementation. As shown in FIG. 13 , two computing devices 1100A and 1100B are connected via a network. Specifically, each computing device is connected to the network via a communication interface within the computing device.

[0290] Taking the example of a server composed of a computing device cluster executing the makeup plan generation method shown in Figures 1-8 above, in the implementation shown in Figure 13, memory 1106 in computing device 1100A stores instructions for executing the functions of receiving module 901 and sending module 903. Simultaneously, memory 1106 in computing device 1100B stores instructions for executing the functions of makeup image generation module 902.

[0291] The connection method between the computing device clusters shown in Figure 13 can be based on the consideration that the makeup plan generation method provided in this application may require the use of a large amount of computing resources and AIGC models to generate makeup plans for users. Therefore, it is considered to hand over the functions implemented by the makeup image generation module 902 to the computing device 1100B to reduce the computing power of the computing device 1100A.

[0292] It should be understood that the functionality of the computing device 1100A shown in FIG13 may also be implemented by multiple computing devices 1100. Similarly, the functionality of the computing device 1100B may also be implemented by multiple computing devices 1100.

[0293] The present application also provides another computing device cluster. The connection relationship between the computing devices in this computing device cluster can be similar to the connection relationship between computing device clusters in Figures 12 and 13. However, the memory 1106 in one or more computing devices 1100 in this computing device cluster can store the same instructions for executing the video processing method.

[0294] In some possible implementations, the memory 1106 of one or more computing devices 1100 in the computing device cluster may also store a portion of the computer program instructions for executing the makeup plan generation method. In other words, the combination of one or more computing devices 1100 may collectively store the computer program instructions for executing the makeup plan generation method.

[0295] FIG14 is a block diagram of a terminal structure provided in an embodiment of the present application. Terminal 1400 may be the user terminal shown in FIG1-8 , such as a smartphone, tablet computer, MP3 player (moving picture experts group audio layer III), MP4 player (moving picture experts group audio layer IV), laptop computer, or desktop computer. Terminal 1400 may also be referred to as user equipment, portable terminal, laptop terminal, desktop terminal, or other similar names.

[0296] Typically, the terminal 1400 includes a processor 1401 and a memory 1402 .

[0297] The processor 1401 may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 1401 may be implemented in at least one hardware form of digital signal processing (DSP), field-programmable gate array (FPGA), and programmable logic array (PLA). The processor 1401 may also include a main processor and a coprocessor. The main processor is a processor for processing data in the awake state, also known as a central processing unit (CPU); the coprocessor is a low-power processor for processing data in the standby state. In some embodiments, the processor 1401 may be integrated with a graphics processing unit (GPU), which is responsible for rendering and drawing the content to be displayed on the display screen. In some embodiments, the processor 1401 may also include an artificial intelligence (AI) processor, which is used to process computing operations related to machine learning.

[0298] Memory 1402 may include one or more computer-readable storage media, which may be non-transitory. Memory 1402 may also include high-speed random access memory, and non-volatile memory, such as one or more disk storage devices, flash memory storage devices. In some embodiments, the non-transitory computer-readable storage medium in memory 1402 is used to store at least one computer program instruction, which is used to be executed by processor 1401 to implement the makeup plan generation method provided in the method embodiment of the present application.

[0299] In some embodiments, terminal 1400 may optionally include a peripheral device interface 1403 and at least one peripheral device. Processor 1401, memory 1402, and peripheral device interface 1403 may be connected via a bus or signal lines. Each peripheral device may be connected to peripheral device interface 1403 via a bus, signal lines, or circuit boards. Specifically, the peripheral device may include at least one of a radio frequency circuit 1404, a touchscreen display 1405, a camera 1406, an audio circuit 1407, a positioning component 1408, and a power supply 1409.

[0300] The peripheral device interface 1403 can be used to connect at least one input / output (I / O)-related peripheral device to the processor 1401 and the memory 1402. In some embodiments, the processor 1401, the memory 1402, and the peripheral device interface 1403 are integrated on the same chip or circuit board; in some other embodiments, any one or two of the processor 1401, the memory 1402, and the peripheral device interface 1403 can be implemented on separate chips or circuit boards, which is not limited in this embodiment.

[0301] The radio frequency circuit 1404 is used to receive and transmit radio frequency (RF) signals, also known as electromagnetic signals. The radio frequency circuit 1404 communicates with communication networks and other communication devices via electromagnetic signals. The radio frequency circuit 1404 converts electrical signals into electromagnetic signals for transmission, or converts received electromagnetic signals into electrical signals. Optionally, the radio frequency circuit 1404 includes: an antenna system, an RF transceiver, one or more amplifiers, a tuner, an oscillator, a digital signal processor, a codec chipset, a user identity module card, etc. The radio frequency circuit 1404 can communicate with other terminals via at least one wireless communication protocol. Such wireless communication protocols include, but are not limited to, the World Wide Web, a metropolitan area network, an intranet, various generations of mobile communication networks (2G, 3G, 4G, and 5G), a wireless local area network, and / or a WiFi network. In some embodiments, the radio frequency circuit 1404 may also include circuits related to near field communication (NFC), which is not limited in the embodiments of the present application.

[0302] Display screen 1405 is used to display a user interface (UI). This UI may include graphics, text, icons, videos, or any combination thereof. When display screen 1405 is a touchscreen display, it is also capable of collecting touch signals on or above the surface of display screen 1405. These touch signals can be input as control signals to processor 1401 for processing. Display screen 1405 can also be used to provide virtual buttons and / or a virtual keyboard, also known as soft buttons and / or a soft keyboard. In some embodiments, there can be a single display screen 1405, located on the front panel of terminal 1400. In other embodiments, there can be at least two display screens 1405, located on different surfaces of terminal 1400 or in a foldable design. In some embodiments, display screen 1405 can be a flexible display, located on a curved or foldable surface of terminal 1400. Display screen 1405 can also be configured as a non-rectangular, irregular shape, also known as a special-shaped screen. Display screen 1405 can be made of materials such as liquid crystal display (LCD) and organic light-emitting diode (OLED).

[0303] The camera assembly 1406 is used to capture images or videos. Optionally, the camera assembly 1406 includes a front camera and a rear camera. Typically, the front camera is arranged on the front panel of the terminal, and the rear camera is arranged on the back of the terminal. In some embodiments, there are at least two rear cameras, which are any one of a main camera, a depth of field camera, a wide-angle camera, and a telephoto camera, so as to realize the fusion of the main camera and the depth of field camera to realize the background blur function, the fusion of the main camera and the wide-angle camera to realize panoramic shooting and virtual reality (VR) shooting function or other fusion shooting functions. In some embodiments, the camera assembly 1406 may also include a flash. The flash can be a single-color temperature flash or a dual-color temperature flash. A dual-color temperature flash refers to a combination of a warm light flash and a cold light flash, which can be used for light compensation at different color temperatures.

[0304] The audio circuit 1407 may include a microphone and a speaker. The microphone is used to collect sound waves from the user and the environment, and convert the sound waves into electrical signals that are input into the processor 1401 for processing, or input into the radio frequency circuit 1404 to achieve voice communication. For the purpose of stereo sound collection or noise reduction, there may be multiple microphones, each located in different parts of the terminal 1400. The microphone may also be an array microphone or an omnidirectional collection microphone. The speaker is used to convert electrical signals from the processor 1401 or the radio frequency circuit 1404 into sound waves. The speaker may be a traditional thin film speaker or a piezoelectric ceramic speaker. When the speaker is a piezoelectric ceramic speaker, it can not only convert electrical signals into sound waves audible to humans, but also convert electrical signals into sound waves inaudible to humans for purposes such as ranging. In some embodiments, the audio circuit 1407 may also include a headphone jack.

[0305] Positioning component 1408 is used to locate the current geographic location of terminal 1400 to implement navigation or location-based services (LBS). Positioning component 1408 can be a positioning component based on the US Global Positioning System (GPS), China's BeiDou system, or Russia's Galileo system.

[0306] Power supply 1409 is used to power various components in terminal 1400. Power supply 1409 can be AC ​​power, DC power, a disposable battery, or a rechargeable battery. When power supply 1409 includes a rechargeable battery, the rechargeable battery can be a wired rechargeable battery or a wireless rechargeable battery. A wired rechargeable battery is charged via a wired line, while a wireless rechargeable battery is charged via a wireless coil. The rechargeable battery can also support fast charging technology.

[0307] In some embodiments, the terminal 1400 further includes one or more sensors 1410. The one or more sensors 1410 include, but are not limited to, an acceleration sensor, a gyroscope sensor, a pressure sensor, a fingerprint sensor, an optical sensor, and a proximity sensor.

[0308] Those skilled in the art will understand that the structure shown in FIG14 does not constitute a limitation on the terminal 1400 , and may include more or fewer components than shown in the figure, or combine certain components, or adopt a different component arrangement.

[0309] The present application also provides a computer program product comprising instructions. This computer program product can be executed on a server or stored in any available medium. When the computer program product is executed on a server, it causes the server to execute the makeup plan generation method shown in Figures 1-8 above.

[0310] The present application also provides a computer program product comprising instructions. This computer program product can be software or a program product that runs on a terminal or is stored in any available medium. When the computer program product runs on a terminal, it causes the terminal to execute the makeup plan generation method shown in Figures 1-8 above.

[0311] The embodiment of the present application also provides a computer-readable storage medium. The computer-readable storage medium can be any available medium that can be stored by a computing device or a data storage device such as a data center that contains one or more available media. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a DVD), or a semiconductor medium (for example, a solid-state hard disk), etc. The computer-readable storage medium includes instructions that instruct the server to execute the makeup scheme generation method shown in Figure 8 above, or instruct the terminal to execute the makeup scheme generation method shown in Figure 8 above.

[0312] It should be understood that the "plurality" mentioned herein refers to two or more. In the description of the embodiments of the present application, unless otherwise specified, " / " means or, for example, A / B can mean A or B; "and / or" in this article is merely a description of the association relationship of associated objects, indicating that there can be three relationships, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, in order to facilitate a clear description of the technical solutions of the embodiments of the present application, in the embodiments of the present application, words such as "first" and "second" are used to distinguish between identical or similar items with substantially the same functions and effects. Those skilled in the art will understand that words such as "first" and "second" do not limit the quantity and execution order, and words such as "first" and "second" do not necessarily limit them to be different.

[0313] It should be noted that the information (including but not limited to user device information, user personal information, etc.), data (including but not limited to data used for analysis, stored data, displayed data, etc.) and signals involved in the embodiments of this application are all authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data need to comply with the relevant laws, regulations and standards of relevant countries and regions.

[0314] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the protection scope of the technical solutions of the embodiments of the present application.

Claims

1. A makeup plan generation method, characterized in that: Applied to a server, the method comprises: Receiving a user appearance image and makeup description information of a target user sent by a user terminal, wherein the makeup description information indicates a makeup effect desired by the target user; Based on the user appearance image and the makeup description information, generating at least one user makeup image by using a trained makeup effect generation model, wherein the at least one user makeup image is a makeup image generated by applying at least one makeup effect to the user appearance image; The at least one user makeup image is sent to the user terminal to instruct the user terminal to display the at least one user makeup image.

2. The method according to claim 1, characterized in that The generating at least one user makeup image based on the user appearance image and the makeup description information by using a trained makeup effect generation model comprises: Acquire a first geometric grid image corresponding to the user appearance image; Based on the user appearance image, the first geometric grid image and the makeup description information, at least one user makeup image is generated by a trained makeup effect generation model.

3. The method according to claim 2, characterized in that The generating the at least one user makeup image by using a trained makeup effect generation model based on the user appearance image, the first geometric grid image and the makeup description information comprises: Based on the makeup description information, determining a target prompt template from a prompt template library, wherein the prompt template library includes a plurality of makeup prompt templates, each of which includes a plurality of makeup prompts describing a makeup effect; The target prompt template, the user appearance image and the first geometric grid image are input into the makeup effect generation model to obtain the at least one user makeup image output by the makeup effect generation model.

4. The method according to any one of claims 1 to 3, characterized in that: Before sending the at least one user makeup image to the user terminal, the method further includes: Determining a display priority of each user makeup image in the at least one user makeup image; sorting the at least one user makeup image based on the display priority of the at least one user makeup image to obtain an image display order of the at least one user makeup image; The sending the at least one user makeup image to the user terminal includes: The at least one user makeup image and the image display order are sent to the user terminal to instruct the user terminal to display the at least one user makeup image according to the image display order.

5. The method according to any one of claims 1 to 4, characterized in that: The method further comprises: receiving a target makeup image sent by the user terminal, wherein the target makeup image is a makeup image determined by the target user based on the at least one user makeup image; Determine a makeup implementation scheme corresponding to the target makeup image, wherein the makeup implementation scheme includes a plurality of makeup implementation steps associated in sequence and makeup prompt information corresponding to each makeup implementation step; The makeup implementation plan is sent to the user terminal to instruct the user terminal to display the makeup implementation plan.

6. The method according to claim 5, characterized in that The step of determining a makeup implementation scheme corresponding to the target makeup image comprises: The target makeup image is input into a trained makeup solution analysis model to obtain a makeup implementation solution corresponding to the target makeup image output by the makeup solution analysis model.

7. The method according to claim 5, characterized in that The sending the makeup implementation scheme to the user terminal to instruct the user terminal to display the makeup implementation scheme includes: Sending makeup prompt information corresponding to a first makeup implementation step to the user terminal, where the first makeup implementation step is any one of the makeup implementation steps in the makeup implementation scheme; If a step jump instruction for skipping the first makeup implementation step is received from the user terminal, in response to the step jump instruction, makeup prompt information corresponding to the second makeup implementation step is sent to the user terminal to instruct the user terminal to display the makeup prompt information corresponding to the second makeup implementation step, and the second makeup implementation step is the next makeup implementation step adjacent to the first makeup implementation step in the makeup implementation plan.

8. The method according to claim 5, characterized in that The makeup prompt information corresponding to the makeup implementation step includes one or more of step description information, makeup map data, makeup product information and auxiliary tool information required for the makeup implementation step; The makeup map data includes makeup contour information and map positioning information, wherein the makeup contour information indicates the contour of the makeup effect corresponding to the makeup implementation step, and the map positioning information indicates the position of the makeup effect corresponding to the makeup implementation step.

9. A method for generating a makeup plan, characterized in that: Applied to a user terminal, the method comprises: Acquire a user appearance image and makeup description information of a target user, wherein the makeup description information indicates a makeup effect desired by the target user; Sending the user appearance image and the makeup description information to a server to instruct the server to generate at least one user makeup image based on the user appearance image and the makeup description information through a trained makeup effect generation model, wherein the at least one user makeup image is a makeup image generated by applying at least one makeup effect to the user appearance image; Receive and display the at least one user makeup image sent by the server.

10. The method according to claim 9, characterized in that Before displaying the at least one user makeup image, the method further includes: receiving an image display order of the at least one user makeup image sent by the server; The displaying of the at least one user makeup image comprises: The at least one user makeup image is displayed in the image display order.

11. The method according to claim 9 or 10, characterized in that After displaying the at least one user makeup image, the method further includes: determining a target makeup image based on the at least one user makeup image; Sending the target makeup image to the server to instruct the server to determine a makeup implementation scheme corresponding to the target makeup image, wherein the makeup implementation scheme includes a plurality of sequentially associated makeup implementation steps and makeup prompt information corresponding to each makeup implementation step; Receive and display the makeup implementation plan sent by the server.

12. The method according to claim 11, characterized in that The receiving and displaying the makeup implementation scheme sent by the server includes: receiving and displaying makeup prompt information corresponding to a first makeup implementation step sent by the server, wherein the first makeup implementation step is any one of the makeup implementation steps in the makeup implementation scheme; In response to a step jump operation triggered by the target user for skipping the first makeup implementation step, a step jump instruction is sent to the server, wherein the step jump instruction is used to request makeup prompt information corresponding to a second makeup implementation step, where the second makeup implementation step is the next makeup implementation step adjacent to the first makeup implementation step in the makeup implementation scheme; Receive and display makeup prompt information corresponding to the second makeup implementation step sent by the server.

13. The method according to claim 12, characterized in that The makeup prompt information of the makeup implementation step includes one or more of step description information, makeup map data, makeup product information and auxiliary tool information required for the makeup implementation step; The makeup map data includes makeup contour information and map positioning information, wherein the makeup contour information indicates the contour of the makeup effect corresponding to the makeup implementation step, and the map positioning information indicates the position of the makeup effect corresponding to the makeup implementation step.

14. The method according to claim 13, characterized in that The makeup prompt information of the makeup implementation step includes the makeup map data; the display of the makeup prompt information corresponding to the second makeup implementation step includes: Acquire a real-time appearance image of the target user; Based on the makeup map data corresponding to the second makeup implementation step, rendering the real-time appearance image with makeup effects to obtain a makeup effect image corresponding to the second makeup implementation step; Display the makeup effect diagram corresponding to the second makeup implementation step.

15. The method according to claim 14, characterized in that The step of rendering the real-time appearance image with makeup effects based on the makeup map data corresponding to the second makeup implementation step to obtain a makeup effect map corresponding to the second makeup implementation step includes: generating a second geometric grid image corresponding to the real-time appearance image; Determining a makeup rendering position in the real-time appearance image based on the texture positioning information corresponding to the second makeup implementation step and the second geometric grid image; Based on the makeup rendering position, the real-time appearance image is rendered with makeup effects according to the makeup contour information corresponding to the second makeup implementation step to obtain a makeup effect image corresponding to the second makeup implementation step.

16. The method according to claim 14 or 15, characterized in that The makeup prompt information of the makeup implementation steps also includes the step description information, the makeup product information and the auxiliary tool information; the method also includes: Displaying step description information corresponding to the second makeup implementation step, makeup product information corresponding to the second makeup implementation step, and auxiliary tool information corresponding to the second makeup implementation step; Among them, the makeup effect picture, the step description information, the makeup product information and the auxiliary tool information are respectively displayed in different areas, and the display areas of the step description information, the makeup product information and the auxiliary tool information surround the display area of ​​the makeup effect picture.

17. A makeup plan generating device, characterized in that: Included in a server, the device comprises: A receiving module, configured to receive a user appearance image and makeup description information of a target user sent by a user terminal, wherein the makeup description information indicates a makeup effect desired by the target user; a makeup image generation module, configured to generate at least one user makeup image based on the user appearance image and the makeup description information by using a trained makeup effect generation model, wherein the at least one user makeup image is a makeup image generated by applying at least one makeup effect to the user appearance image; The sending module is used to send the at least one user makeup image to the user terminal to instruct the user terminal to display the at least one user makeup image.

18. A makeup plan generating device, characterized in that: Included in a user terminal, the device includes: An acquisition module, used to acquire a user appearance image and makeup description information of a target user, wherein the makeup description information indicates a makeup effect desired by the target user; a sending module, configured to send the user appearance image and the makeup description information to a server, so as to instruct the server to generate at least one user makeup image based on the user appearance image and the makeup description information through a trained makeup effect generation model, wherein the at least one user makeup image is a makeup image generated by applying at least one makeup effect to the user appearance image; The receiving module is used to receive and display the at least one user makeup image sent by the server.

19. A server, characterized in that: The server is a computing device cluster, the computing device cluster includes at least one computing device, each computing device includes a processor and a memory; The processor of the at least one computing device is used to execute computer program instructions stored in the memory of the at least one computing device, so that the computing device cluster executes the makeup plan generation method as described in any one of claims 1-8.

20. A terminal, characterized in that: The terminal includes a memory and a processor, the memory is used to store a computer program, and the processor is used to execute computer program instructions stored in the memory, so that the terminal executes the makeup plan generating method described in any one of claims 9-16.

21. A computer-readable storage medium, characterized in that: The storage medium stores computer program instructions, and when the computer program instructions are executed on the server, the server executes the makeup plan generating method as described in any one of claims 1-8.

22. A computer-readable storage medium, characterized in that: The storage medium stores computer program instructions, and when the computer program instructions are executed on the terminal, the terminal executes the makeup plan generating method as described in any one of claims 9 to 16.

Images