Digital human generation method and device, electronic equipment and storage medium
By annotating the default texture set and user reference parts key point information to generate target parts, replacing preset parts to form a custom texture set, solving the problem of high resource consumption in the process of generating digital people, and realizing personalized client generation and interactive experience improvement.
Patent Information
- Application Number
- CN202510583517.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-05-07
- Publication Date
- 2025-08-01
AI Technical Summary
In the prior art, the process of generating digital humans requires powerful computing power in the cloud, and it is difficult to achieve personalized adjustments on the client, resulting in high resource consumption and poor interactive experience.
By annotating preset components in the default texture set, obtaining key point information of the user's reference components, generating target components, and replacing them with preset components, forming a custom texture set, loading them into a two-dimensional image dynamic rendering model to generate digital people, and using ControlNet and artificial intelligence algorithms for integration and adjustment.
It realizes the generation of personalized digital people on the client side, reduces the computing power demand, improves user interaction experience, and meets user personalized needs.
Smart Images
Figure CN120411318A_ABST
Abstract
Description
Technical Field
[0001] This disclosure belongs to the technical field of digital humans, and particularly relates to a method and device for generating digital humans, an electronic device, and a storage medium. Background Art
[0002] Digital Humans, also known as virtual humans or synthetic characters, refer to virtual characters created through computer technology. These digital humans can be completely fictional or digital reproductions of real people. They can have appearances, movements, and behavior patterns similar to real humans and can interact and perform tasks in various digital environments. These digital humans are not only used in film production and video game development but also have extensive applications in fields such as education, healthcare, and social platforms. Summary of the Invention
[0003] This disclosure aims to solve at least one of the technical problems existing in the prior art and provides a method and device for generating digital humans, an electronic device, and a storage medium.
[0004] In a first aspect, an embodiment of this disclosure provides a method for generating a digital human, and the method for generating the digital human includes:
[0005] Label the preset components in the default texture set and record the parameters of the preset components;
[0006] Obtain an image of a reference component uploaded by a user and extract key point information of the reference component; [[ID=2…]]
[0007] Generate a target component according to the parameters of the preset component and the key point information of the reference component;
[0008] Replace the preset component with the target component to generate a custom texture set;
[0009] Load the custom texture set into a two-dimensional image dynamic rendering model and run the two-dimensional image dynamic rendering model to generate a digital human.
[0010] In some embodiments, the generating a target component according to the parameters of the preset component and the key point information of the reference component includes:
[0011] Input the key point information of the reference component into a control neural network and generate a control signal;
[0012] Input the control signal and the parameters of the preset component into an image generation model to fuse the control signal with the key point information of the reference component and generate a target component.
[0013] In some embodiments, generating a target component according to the parameters of the preset component and the key point information of the reference component includes:
[0014] Using an artificial intelligence algorithm to fuse the parameters of the preset component and the key point information of the reference component to generate a target component.
[0015] In some embodiments, replacing the preset component with the target component to generate a custom texture set includes:
[0016] Analyzing the differences between the key point information of the target component and the preset component according to the key point information of the target component and the preset component;
[0017] Adjusting the target component according to the differences between the key point information of the target component and the preset component so that the target component is aligned with the preset component and covers the preset component.
[0018] In some embodiments, before loading the custom texture set into a two-dimensional image dynamic rendering model and running the two-dimensional image dynamic rendering model to generate a digital human, it further includes:
[0019] Judging whether the custom texture set is specified according to the operation instruction;
[0020] If the custom texture set is not specified, loading the default texture set into the two-dimensional image dynamic rendering model and running the two-dimensional image dynamic rendering model to generate a digital human.
[0021] In some embodiments, the preset component includes at least one of a face, hair, eyes, ears, nose, eyebrows, lips, clothes, arms or decorations.
[0022] In a second aspect, an embodiment of the present disclosure provides a digital human generation device, and the digital human generation device includes:
[0023] An annotation module configured to annotate the preset components in the default texture set and record the parameters of the preset components;
[0024] An extraction module configured to obtain an image of a reference component uploaded by a user and extract the key point information of the reference component;
[0025] A first generation module configured to generate a target component according to the parameters of the preset component and the key point information of the reference component;
[0026] A second generation module configured to replace the preset component with the target component to generate a custom texture set;
[0027] A loading module, configured to load the custom texture set into a two-dimensional image dynamic rendering model and run the two-dimensional image dynamic rendering model to generate a digital human.
[0028] In some embodiments, the first generation module is specifically configured to input the key point information of the reference component into a control neural network and generate a control signal;
[0029] Input the control signal and the parameters of the preset component into an image generation model to fuse the control signal with the key point information of the reference component and generate a target component.
[0030] In some embodiments, the first generation module is specifically configured to use an artificial intelligence algorithm to fuse the parameters of the preset component and the key point information of the reference component to generate a target component.
[0031] In a third aspect, an embodiment of the present disclosure provides an electronic device, which includes:
[0032] At least one processor; and
[0033] A memory communicatively connected to the at least one processor; wherein,
[0034] The memory stores one or more computer programs executable by the at least one processor, and the one or more computer programs are executed by the at least one processor so that the at least one processor can execute the method for generating a digital human provided in the first aspect.
[0035] In a fourth aspect, an embodiment of the present disclosure provides a computer-readable storage medium, on which a computer program is stored, and the computer program realizes the method for generating a digital human provided in the first aspect when executed by a processor. BRIEF DESCRIPTION OF THE DRAWINGS
[0036] Figure 1 It is a schematic flowchart of a method for generating a digital human provided by an embodiment of the present disclosure.
[0037] Figure 2 It is a schematic structural diagram of a device for generating a digital human provided by an embodiment of the present disclosure.
[0038] Figure 3 It is a schematic structural diagram of an electronic device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION
[0039] To make the objectives, technical solutions, and advantages of the embodiments of the present disclosure clearer, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only a part of the embodiments of the present disclosure, rather than all the embodiments. The components of the embodiments of the present disclosure described and illustrated herein can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present disclosure provided in the drawings is not intended to limit the scope of the claimed present disclosure, but merely represents selected embodiments of the present disclosure. All other embodiments obtained by those skilled in the art based on the embodiments of the present disclosure without creative efforts fall within the scope of protection of the present disclosure. Without conflict, the various embodiments of the present disclosure and the features in the embodiments can be combined with each other.
[0040] Unless otherwise defined, the technical terms or scientific terms used in the present disclosure shall have the ordinary meanings understood by those of ordinary skill in the art to which the present disclosure pertains. The terms "first", "second", and similar terms used in the present disclosure do not denote any order, quantity, or importance, but are only used to distinguish different components. Similarly, terms such as "a", "an", or "the" do not denote a limitation of quantity, but indicate the presence of at least one. Terms such as "comprising" or "including" mean that the elements or items appearing before the term cover the elements or items listed after the term and their equivalents, without excluding other elements or items.
[0041] As used in the present disclosure, "a plurality or several" means two or more. "And / or" describes the association relationship of associated objects and indicates that three relationships can exist. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. The character " / " generally indicates that the associated objects before and after are in an "or" relationship.
[0042] For the convenience of understanding, the special terms involved in the embodiments of the present disclosure will be described in detail first.
[0043] Live2D: A 2D digital human engine that can run on platforms such as Android, Windows, and the Web, and realizes 3D effects through the distortion and deformation of objects.
[0044] Artificial Intelligence Generated Content: Refers to various types of content automatically generated using artificial intelligence technology, including text, images, audio, and video, etc.
[0045] Live2D Texture Set: After packaging, the Live2D digital human combines all the textures used into one texture, which is called a texture set. Simply put, it is a picture that contains various components of the digital human's face, hair, body, clothes, etc.
[0046] ControlNet: A neural network technology for enhancing image generation, especially suitable for the Stable Diffusion Model. Its purpose is to increase control over the generated content without changing the core structure of the generation model. The main idea of ControlNet is to guide the generation process by adding additional control signals. These control signals can be the edges of an image, sketches, depth maps, or other forms of information. By introducing these signals, ControlNet can better meet the specific requirements of users for the generated images.
[0047] Traditional 3D digital humans collect data on the shape, posture, and expression of real humans through devices such as 3D scanners and virtual reality glasses. Then, using computer image processing technology and machine learning algorithms, these data are processed and analyzed to generate highly realistic 3D digital human models. During the operation of 3D digital humans, they require powerful computing power from the cloud and stream to the client. It is still a difficult point to be fully able to run on the client.
[0048] In order to solve at least one of the above technical problems, the embodiments of the present disclosure provide a method and device for generating a digital human, an electronic device, and a storage medium. The method and device for generating a digital human, the electronic device, and the storage medium provided by the embodiments of the present disclosure will be further described in detail below in conjunction with the accompanying drawings and specific embodiments.
[0049] In a first aspect, the embodiments of the present disclosure provide a method for generating a digital human. Figure 1 The following is a schematic flowchart of the method for generating a digital human provided by the embodiments of the present disclosure. As Figure 1 shown, the method for generating a digital human includes the following steps S101 to S105.
[0050] S101, label the preset components in the default texture set and record the parameters of the preset components.
[0051] In the above step S101, the texture set can be understood as a picture containing various components of the digital human, such as the face, hair, eyes, ears, nose, eyebrows, lips, clothes, arms, or decorations. The default texture set is a picture pre-formed using drawing techniques, where the positions of the various components are fixed, and the preset components can be at least one of the face, hair, eyes, ears, nose, eyebrows, lips, clothes, arms, or decorations. Some of the preset components can be identified and marked using manual measurement or image recognition techniques. In the embodiments of the present disclosure, the preset component will be described by taking the face as an example. For example, the position and size of the face are marked and recorded, and the position information of the human face is labeled as {x: 200, y: 100, width: 100, height: 50}. It can be understood that the preset components to be marked can also be other components, such as ears, noses, etc., and the implementation principle is similar, and will not be elaborated here.
[0052] S102, Obtain the image of the reference component uploaded by the user, and extract the key point information of the reference component.
[0053] In the above step S102, the image of the reference component uploaded by the user can be a self-taken image or an image of other people downloaded from the Internet. The key point information of the reference component can be the points in the face that need to be dynamically controlled, such as around the lips and around the eyes.
[0054] S103, Generate a target component according to the parameters of the preset component and the key point information of the reference component.
[0055] In the above step S103, the preset component and the reference component can be fused according to the parameters of the preset component and the key point information of the reference component to generate a target component. For example, the face shape in the self-taken image uploaded by the user is adjusted according to the preset face to meet the requirements of dynamic control.
[0056] S104, Replace the preset component with the target component to generate a custom texture set.
[0057] In the above step S104, the generated target component is used to replace the preset component in the default texture set. For example, after the face shape in the self-taken image uploaded by the user is adjusted, it replaces the face image in the texture set, thus modifying the default texture set and generating a custom texture set.
[0058] S105, Load the custom texture set into a two-dimensional image dynamic rendering model, and run the two-dimensional image dynamic rendering model to generate a digital human.
[0059] In the above step S105, the two-dimensional image dynamic rendering model can specifically be Live2D. The custom texture set is loaded into the Live2D engine, and Live2D is run. A new digital human can be generated according to the custom texture set, and the face of the digital human is the face image of the selfie image uploaded by the user.
[0060] In the method for generating a digital human provided by the embodiments of the present disclosure, the default texture set can be modified according to the personalized requirements of the user to form a custom texture set. When running the two-dimensional image dynamic rendering model (Live2D), the custom texture set can be loaded to generate a personalized digital human. In this way, the entire digital human generation process can be run on the client side, and there is no need to transfer the generation process to the cloud for running. Therefore, computing power can be saved, which is beneficial to the data light weight of digital human generation. Moreover, during the digital human generation process, the reference components uploaded by the user can be used to generate target components, and the target components can replace the preset components in the default texture set, so that the generated digital human can meet the personalized needs of the user. Therefore, the interactive experience of the user can be improved.
[0061] In some embodiments, in the above step S103, generating the target component according to the parameters of the preset component and the key point information of the reference component includes: inputting the key point information of the reference component into a control neural network and generating a control signal; inputting the control signal and the parameters of the preset component into an image generation model to fuse the control signal with the key point information of the reference component to generate the target component.
[0062] ControlNet is a neural network concept that controls an image generation large model (such as Stable Diffusion) through additional inputs. Some open-source frameworks support extracting face key points from existing human pictures as ControlNet. The key point information is extracted from the selfie image uploaded by the user or other human images downloaded from the network, and the extracted key point information is used as the face shape effect of the digital human controlled by ControlNet. A human picture of the same character as the user-uploaded person is generated, maintaining the consistency of the human character. At the same time, a human picture of a certain style can be generated according to the prompt words and the image generation model. The process of image generation is more finely controlled, and the face shape of the human character generated conforms to the standards of Live2D, so that the facial movements and mouth shapes can be normally driven. Among them, the image generation model can be, for example, the commonly used Stable Diffusion / Flux, etc.
[0063] In some embodiments, in the above step S103, generating the target component according to the parameters of the preset component and the key point information of the reference component includes: using an artificial intelligence algorithm to fuse the parameters of the preset component and the key point information of the reference component to generate the target component.
[0064] In practical applications, artificial intelligence algorithms can be utilized to fuse the parameters of the preset component and the key point information of the reference component. For example, AI face-swapping technology can be used to replace the face image in the self-taken photo uploaded by the user with the face image in the preset texture set, enabling the generated digital human to meet the personalized needs of the user, thereby enhancing the user's interaction experience.
[0065] In some embodiments, the above step S104 of replacing the target component with the preset component to generate a custom texture set includes: analyzing the differences between the key point information of the target component and the preset component according to the key point information of the target component and the preset component; adjusting the target component according to the differences between the key point information of the target component and the preset component so that the target component is aligned with the preset component and covers the preset component.
[0066] There are certain differences in parameters such as size between the self-taken photo uploaded by the user or the image of other people downloaded from the network and the preset component, which do not meet the standards of Live2D. The self-taken photo uploaded by the user or the image of other people downloaded from the network can be cropped and aligned, etc., so that it can meet the standards of Live2D. Then, the face image that meets the standards of Live2D is used to cover the face image in the default texture set to form a custom texture set.
[0067] In some embodiments, as Figure 1 shown, before the above step S105 of loading the custom texture set into the two-dimensional image dynamic rendering model and running the two-dimensional image dynamic rendering model to generate a digital human, the following steps S201 and S202 are also included.
[0068] Step S201: Determine whether to specify a custom texture set according to the operation instruction.
[0069] The user can input an operation instruction to control Live2D to load the default texture set or the custom texture set.
[0070] If the custom texture set is not specified, step S202 is executed, loading the default texture set into the two-dimensional image dynamic rendering model and running the two-dimensional image dynamic rendering model to generate a digital human.
[0071] If the user does not specify to load the custom texture set, the default texture set is loaded into Live2D to generate a digital human with the default image.
[0072] In a second aspect, an embodiment of the present disclosure provides a digital human generation device. Figure 2 For the structural schematic diagram of a digital human generation device provided by an embodiment of the present disclosure, as Figure 2As shown in the figure, the digital human generation device includes: an annotation module 201, an extraction module 202, a first generation module 203, a second generation module 204, and a loading module 205.
[0073] The annotation module 201 is configured to annotate the preset components in the default texture set and record the parameters of the preset components; the extraction module 202 is configured to obtain the image of the reference component uploaded by the user and extract the key point information of the reference component; the first generation module 203 is configured to generate a target component according to the parameters of the preset component and the key point information of the reference component; the second generation module 204 is configured to replace the preset component with the target component to generate a custom texture set; the loading module 205 is configured to load the custom texture set into the two-dimensional image dynamic rendering model and run the two-dimensional image dynamic rendering model to generate a digital human.
[0074] In some embodiments, the first generation module 203 is specifically configured to input the key point information of the reference component into a control neural network and generate a control signal; input the control signal and the parameters of the preset component into an image generation model to fuse the control signal with the key point information of the reference component to generate a target component.
[0075] In some embodiments, the first generation module 203 is specifically configured to use an artificial intelligence algorithm to fuse the parameters of the preset component and the key point information of the reference component to generate a target component.
[0076] It should be noted here that each module in the above digital human generation device can be implemented in whole or in part by software, hardware, and their combination. The above modules can be embedded in the processor of the computer device in hardware form or independent of it, or stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to the above modules to implement the digital human generation method provided in any of the above embodiments. The specific implementation manner is the same as that of the digital human generation method provided in any of the above embodiments, and will not be elaborated here.
[0077] In a third aspect, an embodiment of the present disclosure provides an electronic device. Figure 3 The structural schematic diagram of the electronic device provided by the embodiment of the present disclosure is shown in Figure 3 As shown in the figure, the electronic device provided by the embodiment of the present disclosure includes: at least one processor 301; at least one memory 302, and one or more I / O interfaces 303 connected between the processor 301 and the memory 302; wherein, the memory 302 stores one or more computer programs executable by at least one processor 301, and the one or more computer programs are executed by at least one processor 301 so that at least one processor 301 can execute the digital human generation method provided in any of the above embodiments.
[0078] Each module in the above electronic device can be implemented in whole or in part by software, hardware, or a combination thereof. Each of the above modules can be embedded in or independent of the processor in the computer device in the form of hardware, or stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules to implement the digital human generation method provided in any of the above embodiments.
[0079] In a fourth aspect, an embodiment of the present disclosure provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the digital human generation method provided in any of the above embodiments when executed by a processor / processing core. The computer-readable storage medium can be a volatile or non-volatile computer-readable storage medium.
[0080] Those of ordinary skill in the art can understand that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, and appropriate combinations thereof. In the hardware implementation, the division of the functional modules / units mentioned above does not necessarily correspond to the division of physical components; for example, one physical component can have multiple functions, or one function or step can be executed by several physical components in cooperation. Some or all of the physical components can be implemented as software executed by a processor, such as a central processing unit, a digital signal processor, or a microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit. Such software can be distributed on a computer-readable storage medium, which can include a computer storage medium (or non-transitory medium) and a communication medium (or transitory medium).
[0081] As is well known to those of ordinary skill in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information, such as computer-readable program instructions, data structures, program modules, or other data. Computer storage media includes, but is not limited to, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), static random access memory (SRAM), flash memory or other memory technologies, portable compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical disc storage, magnetic cassette, tape, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store the desired information and can be accessed by a computer. In addition, as is well known to those of ordinary skill in the art, communication media typically includes computer-readable program instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transmission mechanism, and can include any information delivery medium.
[0082] The computer-readable program instructions described herein can be downloaded to various computing / processing devices from a computer-readable storage medium or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network may include copper transmission cables, optical fiber transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in a computer-readable storage medium in each computing / processing device.
[0083] The computer program instructions for performing the operations of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state-setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages such as Smalltalk, C++, etc., and conventional procedural programming languages such as the "C" language or similar programming languages. The computer-readable program instructions may be executed entirely on the user's computer, partially on the user's computer, executed as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider). In some embodiments, by using the status information of the computer-readable program instructions to customize an electronic circuit, such as a programmable logic circuit, a field-programmable gate array (FPGA), or a programmable logic array (PLA), the electronic circuit can execute the computer-readable program instructions to implement various aspects of the present disclosure.
[0084] The computer program product described herein may be implemented specifically by hardware, software, or a combination thereof. In an alternative embodiment, the computer program product is specifically embodied as a computer storage medium. In another alternative embodiment, the computer program product is specifically embodied as a software product, such as a Software Development Kit (SDK), etc.
[0085] Aspects of the present disclosure are described herein with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present disclosure. It should be understood that each block of the flowcharts and / or block diagrams, and the combinations of blocks in the flowcharts and / or block diagrams, can be implemented by computer-readable program instructions.
[0086] These computer-readable program instructions may be provided to a processor of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, when executed by the processor of the computer or other programmable data processing apparatus, create means for implementing the functions / acts specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions may also be stored in a computer-readable storage medium that causes a computer, a programmable data processing apparatus, and / or other devices to function in a particular manner, such that the computer-readable medium storing the instructions comprises a manufacture, the instructions including aspects of implementing the functions / acts specified in one or more blocks of the flowchart and / or block diagram.
[0087] The computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other devices, such that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other devices to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other devices to implement the functions / acts specified in one or more blocks of the flowchart and / or block diagram.
[0088] The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram may represent a module, a segment of code, or a portion of an instruction, and the module, segment of code, or portion of an instruction may include one or more executable instructions for implementing the specified logical function. In some alternative implementations, the functions noted in the blocks may occur out of the order noted in the figures. For example, two consecutive blocks may in fact be executed substantially in parallel, or they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block of the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented by a dedicated hardware-based system for performing the specified functions or acts, or by a combination of dedicated hardware and computer instructions.
[0089] Example embodiments have been disclosed herein, and although specific terms are employed, they are used in a generic and descriptive sense only and not for purposes of limitation. In some instances, it will be apparent to those skilled in the art that, unless otherwise expressly stated, the features, characteristics, and / or elements described in connection with a particular embodiment may be used singly or in combination with those described in connection with other embodiments. Accordingly, those skilled in the art will appreciate that various forms and details may be changed without departing from the scope of the present disclosure as set forth by the appended claims.
Claims
1. A method for generating a digital human, characterized in that, The method for generating the digital human includes: Label the preset components in the default texture set and record the parameters of the preset components; Obtain the image of the reference component uploaded by the user and extract the key point information of the reference component; Generate a target component according to the parameters of the preset component and the key point information of the reference component; Replace the preset component with the target component to generate a custom texture set; Load the custom texture set into the two-dimensional image dynamic rendering model and run the two-dimensional image dynamic rendering model to generate a digital human.
2. The method for generating a digital human according to claim 1, wherein The generating the target component according to the parameters of the preset component and the key point information of the reference component includes: Input the key point information of the reference component into the control neural network and generate a control signal; Input the control signal and the parameters of the preset component into the image generation model to fuse the control signal with the key point information of the reference component and generate a target component.
3. The method for generating a digital human according to claim 1, wherein The generating the target component according to the parameters of the preset component and the key point information of the reference component includes: Use an artificial intelligence algorithm to fuse the parameters of the preset component and the key point information of the reference component to generate a target component.
4. The method for generating a digital human according to claim 1, wherein, The replacing the preset component with the target component to generate a custom texture set includes: Analyze the difference between the key point information of the target component and the key point information of the preset component according to the key point information of the target component and the preset component; Adjust the target component according to the difference between the key point information of the target component and the key point information of the preset component so that the target component is aligned with the preset component and covers the preset component.
5. The method for generating a digital human according to claim 1, wherein Before the loading the custom texture set into the two-dimensional image dynamic rendering model and running the two-dimensional image dynamic rendering model to generate a digital human, it further includes: Judge whether the custom texture set is specified according to the operation instruction; If the custom texture set is not specified, load the default texture set into the two-dimensional image dynamic rendering model and run the two-dimensional image dynamic rendering model to generate a digital human.
6. The method for generating a digital human according to claim 1, wherein, The preset components include at least one of a face, hair, eyes, ears, nose, eyebrows, lips, clothes, arms or decorations.
7. A digital human generation device, characterized in that, The device for generating the digital human includes: A labeling module configured to label the preset components in the default texture set and record the parameters of the preset components; An extraction module configured to obtain the image of the reference component uploaded by the user and extract the key point information of the reference component; A first generation module configured to generate a target component according to the parameters of the preset component and the key point information of the reference component; A second generation module configured to replace the preset component with the target component to generate a custom texture set; A loading module configured to load the custom texture set into the two-dimensional image dynamic rendering model and run the two-dimensional image dynamic rendering model to generate a digital human.
8. The digital human generation device according to claim 7, wherein The first generation module is specifically configured to input the key point information of the reference component into the control neural network and generate a control signal; Input the control signal and the parameters of the preset component into the image generation model to fuse the control signal with the key point information of the reference component and generate a target component.
9. The digital human generation device according to claim 7, characterized in that, The first generation module is specifically configured to use an artificial intelligence algorithm to fuse the parameters of the preset component and the key point information of the reference component to generate a target component.
10. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores one or more computer programs executable by the at least one processor, and the one or more computer programs are executed by the at least one processor so that the at least one processor can execute the digital human generation method according to any one of claims 1 to 6.
11. A computer-readable storage medium having a computer program stored thereon, characterized in that, The computer program, when executed by a processor, implements the digital human generation method according to any one of claims 1 to 6.