Decoration material generation method and device, equipment and storage medium

Abstract

The embodiment of the invention relates to a method and device for generating decoration materials, electronic equipment and a storage medium. The method comprises the following steps: acquiring input information, wherein the input information indicates a material category and a material style; a target decoration material generated on the basis of the input information is provided, and the target decoration material is generated on the basis of the following processes that mask information corresponding to the material category is determined, and the mask information indicates a target area used for generating the decoration material; providing the reference image, the mask information and a first cue word corresponding to the input information for a first target model to indicate the first target model to fill a target area in the reference image; and generating a target decoration material based on the filling result of the target area. According to the embodiment of the invention, the quality of the generated decoration material can be improved.

Description

Technical Field

[0001] The exemplary embodiments disclosed herein generally relate to the field of computers, and particularly to a method, apparatus, device, and computer-readable storage medium for generating decorative materials. Background Technology

[0002] With the development of computer technology, artificial intelligence technology has gradually entered the field of image processing, enabling image processing software to generate and provide a wide variety of decorative materials.

[0003] However, the generated decorative materials provided lack realism, thus affecting the user experience. Summary of the Invention

[0004] In a first aspect of this disclosure, a method for generating decorative materials is provided. The method includes: acquiring input information indicating a material category and a material style; and providing a target decorative material generated based on the input information, wherein the target decorative material is generated based on the following process: determining mask information corresponding to the material category, the mask information indicating a target region for generating the decorative material; providing a reference image, the mask information, and a first prompt word corresponding to the input information to a first target model to instruct the first target model to fill the target region in the reference image; and generating the target decorative material based on the filling result of the target region.

[0005] In a second aspect of this disclosure, an apparatus for generating decorative materials is provided. The apparatus includes: an acquisition module configured to acquire input information indicating a material category and a material style; and a providing module configured to provide a target decorative material generated based on the input information, wherein the target decorative material is generated based on the following process: determining mask information corresponding to the material category, the mask information indicating a target region for generating the decorative material; providing a reference image, the mask information, and a first prompt word corresponding to the input information to a first target model to instruct the first target model to fill the target region in the reference image; and generating the target decorative material based on the filling result of the target region.

[0006] In a third aspect of this disclosure, an electronic device is provided. The device includes at least one processing unit; and at least one memory coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit. When executed by the at least one processing unit, the instructions cause the device to perform the method of the first aspect.

[0007] In a fourth aspect of this disclosure, a computer-readable storage medium is provided. The computer-readable storage medium stores a computer program that can be executed by a processor to implement the method of the first aspect.

[0008] It should be understood that the content described in this content section is not intended to limit the key or essential features of the embodiments of this disclosure, nor is it intended to restrict the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0009] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. In the drawings, the same or similar reference numerals denote the same or similar elements, wherein:

[0010] Figure 1 A schematic diagram is shown of an example environment in which embodiments of the present disclosure may be implemented;

[0011] Figure 2 A flowchart illustrating an example process for providing decorative materials according to some embodiments of this disclosure is shown;

[0012] Figures 3A to 3C Example interfaces according to some embodiments of this disclosure are shown;

[0013] Figure 4 A flowchart illustrating an example process for generating decorative materials according to some embodiments of the present disclosure is shown;

[0014] Figure 5 A flowchart illustrating an example process for generating decorative materials according to some embodiments of this disclosure is shown;

[0015] Figure 6 A flowchart illustrating an example process for generating a reference image according to some embodiments of the present disclosure is shown;

[0016] Figure 7 A schematic structural block diagram of an example device for providing decorative materials according to some embodiments of the present disclosure is shown; and

[0017] Figure 8 A block diagram of an electronic device capable of implementing several embodiments of the present disclosure is shown. Detailed Implementation

[0018] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0019] It should be noted that the headings of any section / subsection provided herein are not limiting. Various embodiments are described throughout this document, and embodiments of any type may be included under any section / subsection. Furthermore, embodiments described in any section / subsection may be combined in any way with any other embodiments described in the same section / subsection and / or different sections / subsections.

[0020] In the description of embodiments of this disclosure, the term "comprising" and similar terms should be understood as open-ended inclusion, i.e., "including but not limited to". The term "based on" should be understood as "at least partially based on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The term "some embodiments" should be understood as "at least some embodiments". Other explicit and implicit definitions may also be included below. The terms "first", "second", etc., may refer to different or the same objects. Other explicit and implicit definitions may also be included below.

[0021] The embodiments of this disclosure may involve user data, data acquisition, and / or use. All of these aspects comply with applicable laws, regulations, and relevant provisions. In the embodiments of this disclosure, all data collection, acquisition, processing, manipulation, forwarding, and use are conducted with the user's knowledge and confirmation. Accordingly, in implementing the embodiments of this disclosure, the type, scope of use, and usage scenarios of any data or information that may be involved should be communicated to the user and their authorization obtained in accordance with relevant laws and regulations through appropriate means. The specific methods of notification and / or authorization may vary depending on the actual situation and application scenario, and the scope of this disclosure is not limited in this respect.

[0022] In this specification and the embodiments, any processing of personal information will be carried out only under the premise of legality (such as obtaining the consent of the personal information subject, or being necessary for the performance of a contract), and will only be carried out within the scope stipulated or agreed upon. A user's refusal to process personal information other than that necessary for basic functions will not affect the user's use of basic functions.

[0023] As mentioned above, some traditional solutions allow users to add AI-generated materials, such as stickers. However, the decorative materials generated by traditional solutions often fail to fit the image being decorated. For example, when using decorative materials, issues may arise such as the material being the wrong size or in the wrong position, thus affecting the user experience.

[0024] Embodiments of this disclosure propose a scheme for providing decorative materials. The scheme includes: acquiring input information, the input information indicating a material category and a material style; and providing a target decorative material generated based on the input information, wherein the target decorative material is generated based on the following process: determining mask information corresponding to the material category, the mask information indicating a target area for generating the decorative material; providing a reference image, the mask information, and a first prompt word corresponding to the input information to a first target model to instruct the first target model to fill the target area in the reference image; and generating the target decorative material based on the filling result of the target area.

[0025] According to embodiments of this disclosure, by providing a reference image, mask information corresponding to the material category, and a first prompt word corresponding to the input information to the first target model, embodiments of this disclosure can effectively limit the area for generating the target decorative material when generating the target decorative material, thereby limiting the size and position of the target decorative material, thereby enhancing the adaptability and realism of the target decorative material and improving the user experience.

[0026] The following section provides a detailed description of various example implementations of this scheme, with reference to the accompanying drawings.

[0027] Example Environment

[0028] Figure 1 A schematic diagram of an example environment 100 in which embodiments of the present disclosure can be implemented is shown. For example... Figure 1 As shown, example environment 100 may include terminal device 110.

[0029] In this example environment 100, terminal device 110 may run an application 120 for providing decorative elements. Application 120 may be any suitable type of application for providing decorative elements, examples of which may include, but are not limited to, image processing applications or other suitable applications. User 140 may interact with application 120 via terminal device 110 and / or its attached devices.

[0030] exist Figure 1 In environment 100, if application 120 is active, terminal device 110 can use application 120 to present interface 150 for providing decorative materials.

[0031] In some embodiments, terminal device 110 communicates with server 130 to provide services to application 120. Terminal device 110 can be any type of mobile terminal, fixed terminal, or portable terminal, including mobile phones, desktop computers, laptop computers, notebook computers, netbook computers, tablet computers, media computers, multimedia tablets, handheld computers, portable gaming terminals, VR / AR devices, personal communication system (PCS) devices, personal navigation devices, personal digital assistants (PDAs), audio / video players, digital cameras / camcorders, positioning devices, television receivers, radio receivers, e-book devices, gaming devices, or any combination thereof, including accessories and peripherals of these devices or any combination thereof. In some embodiments, terminal device 110 can also support any type of user-facing interface (such as "wearable" circuitry).

[0032] Server 130 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks, and big data and artificial intelligence platforms. Server 130 may include, for example, computing systems / servers such as mainframes, edge computing nodes, computing devices in a cloud environment, etc. Server 130 can provide backend services for application 120 in terminal device 110 that provides decorative materials.

[0033] A communication connection can be established between server 130 and terminal device 110. This communication connection can be established via wired or wireless means. The communication connection may include, but is not limited to, Bluetooth, mobile network, Universal Serial Bus (USB), and Wireless Fidelity (WiFi) connections; the embodiments of this disclosure are not limited in this respect. In the embodiments of this disclosure, server 130 and terminal device 110 can achieve signaling interaction through the communication connection between them.

[0034] It should be understood that the structure and function of the various elements in environment 100 are described for illustrative purposes only and do not imply any limitation on the scope of this disclosure.

[0035] The following description will continue with reference to the accompanying drawings, which will provide some exemplary embodiments of this disclosure.

[0036] Example process

[0037] Figure 2 A flowchart illustrating an example process 200 for providing decorative materials according to some embodiments of the present disclosure is shown. Process 200 can be implemented at terminal device 110. Reference is made below. Figure 1 To describe process 200.

[0038] like Figure 2 As shown, in box 210, terminal device 110 acquires input information. The input information indicates the material category and material style.

[0039] In some embodiments, the input information may include input content obtained by the terminal device 110 from the user 140. As an example, the user may input the material category and material style through other input methods such as text input or voice input. In some embodiments, the material category refers to the type of decorative material desired by the user, examples of which may include, but are not limited to, categories such as glasses, hats, and beards. Additionally, the material style may indicate the style of the decorative material, examples of which may include, but are not limited to, patterns, colors, and styles.

[0040] In some instances, the input information may include text content that indicates the material category and style, such as "hat with peach blossom pattern," where "hat" can indicate the material category and "with peach blossom pattern" can indicate the material style.

[0041] In some embodiments, such as Figure 3A As shown, terminal device 110 can display interface 300A configured with corresponding input boxes. For example, as... Figure 3B As shown, when the terminal device 110 receives the user's operation information in the interface 300B, the terminal device 110 displays the interface 300A.

[0042] In box 220, terminal device 110 provides target decorative materials generated based on input information. The target decorative materials conform to the material categories and styles proposed by the user.

[0043] In some embodiments, such as Figure 3C As shown, after the target decorative material is generated, the terminal device 110 can display the generated target decorative material in the interface 300C. As an example, the terminal device 110 can display a preview effect of the target decorative material being applied to the image being decorated.

[0044] It should be understood that Figures 3A to 3CThe illustrated material generation interface is merely an example; other suitable interfaces can also be used to generate and provide decorative materials. The various graphic elements in the interface can have different arrangements and different visual representations, one or more elements can be omitted or replaced, and one or more other elements may also be present. The embodiments of this disclosure are not limited in this respect.

[0045] The following will be further combined Figure 4 and Figure 5 This describes the specific generation process of decorative materials. Figure 4 A flowchart illustrating an example process for generating decorative materials according to some embodiments of the present disclosure is shown. Figure 5 A flowchart illustrating an example process 500 for generating decorative materials according to some embodiments of the present disclosure is shown. It should be understood that the decorative materials can be generated by terminal device 110 and / or server 130, and process 500 will be described below using server 130 as an example.

[0046] like Figure 5 As shown in box 510, server 130 determines mask information corresponding to the material category. The mask information indicates the target area used to generate decorative materials.

[0047] by Figure 4 As shown, server 130 can determine the mask information corresponding to the material category indicated by the input information using language model 410. In some embodiments, different categories of decorative materials can correspond to different placement areas. As an example, hats and ties can correspond to different wearing positions.

[0048] Additionally, the placement area for decorative elements can also depend on the reference object that each category of decorative element is decorating. For example, the placement area for a hat element can be determined based on the head position of a reference figure in the target image.

[0049] To ensure that the generated decorative materials can be placed in the appropriate areas, server 130 can establish a mapping relationship between each material category and the area where the decorative materials are generated. That is, server 130 can pre-set mask information for each material category. Once server 130 determines the material category indicated by the input information, it can determine the corresponding mask information from a set of candidate mask information corresponding to a set of candidate material categories (e.g., different types of decorative materials).

[0050] In frame 520, server 130 provides first target model 420 with a reference image, mask information, and a first prompt word corresponding to the input information to instruct first target model 420 to fill the target area in the reference image.

[0051] In some embodiments, the first target model 420 is a generative model with in-painting capabilities. The first target model 420 can predict and fill in the content of a specified region based on existing image information. As an example, before using the first target model 420 to fill in the target region, the server 130 can also provide a reference image to make the filling result of the first target model 420 more adaptable and realistic.

[0052] In some embodiments, the reference image may be determined based on a target image containing a reference object. In some embodiments, the reference object may be associated with a target decorative material to be generated, and the reference image may include a visual representation corresponding to the reference object. As an example, server 130 may retrieve a preset reference image from its storage device. Alternatively, server 130 may also determine the reference image by processing the received input image using a second target model 430.

[0053] In some embodiments, the input image may be, for example, an image taken or uploaded by a user. Further, the server 130 may utilize the second target model 430 to process the input image to generate a reference image that matches the material style indicated in the input information. In one manner, embodiments of this disclosure allow the first target model 420 to fill the target area based on a reference image with a matching style, thereby making the generated target decorative material more consistent in style with the reference image.

[0054] Figure 6 The specific process of generating the reference image is further illustrated. As shown in the figure, in box 610, server 130 can generate a second prompt word corresponding to the material style.

[0055] In some embodiments, the content described by the second prompt word can be more detailed than the content described by the material style indicated in the input information. For example, the server 130 can use the language model 410 to expand the material style indicated in the input information to obtain the second prompt word.

[0056] In frame 620, server 130 can provide input image and second prompt word to second target model 430 to instruct second target model 430 to adjust input image according to material style to obtain reference image.

[0057] As an example, the second target model 430 may include an appropriate style control model such as ControlNet or a diffusion model. The second target model 430 may adjust the input image based on a second cue word to output a reference image that matches the target style indicated by the second cue word. In one example, if the material style in the input information is style A, the second target model 430 may transform the input image (e.g., a portrait image) into a reference image that matches style A.

[0058] Continue to refer to Figure 4 Server 130 can provide a first prompt word to the first target model 420 to instruct the first target model 420 to fill the target area indicated by the mask information based on the first prompt word and the reference image. In some embodiments, server 130 can utilize language model 410 to process input information to generate the first prompt word. In some examples, the first prompt word can include, but is not limited to, both material category and material style information. For example, the first prompt word can be generated by filling the material category and material style into a preset prompt word template.

[0059] In some embodiments, the part of the first prompt word associated with the material style may be an expanded version of the material style, so that the first target model 420 can fill the target area more accurately.

[0060] Continue to refer to Figure 5 In box 530, server 130 can generate target decorative material based on the filling result of the target area.

[0061] Taking a hat as an example, the first target model 420 can fill the target area (the preset area of ​​the head of the portrait) indicated by the mask information based on a reference image (e.g., a portrait image) and a first prompt (e.g., the description of the hat material) to obtain the filling result of the target area.

[0062] In some embodiments, server 130 can obtain an intermediate image generated by first target model 420 by filling target regions in reference image, and can segment target decorative material from the intermediate image.

[0063] For example, the image generated by the first target model 420 may include an intermediate image filled with hat material. Further, the server 130 can segment the hat material from this intermediate image to complete the generation of the hat material. For example, the server 130 can utilize an appropriate entity segmentation model to determine the region in the intermediate image corresponding to the hat.

[0064] In some embodiments, to improve segmentation accuracy, server 130 may also segment the target decorative material from the intermediate image based on mask information. For example, server 130 may perform entity segmentation only on the sub-images in the intermediate image that correspond to the mask information, thereby improving the accuracy of image segmentation.

[0065] Based on the process described above, the embodiments of this disclosure, when generating target decorative materials using the first target model, can effectively limit the area where the target decorative materials are generated by setting a target region, thereby limiting the size and position of the target decorative materials. Therefore, the embodiments of this disclosure can enhance the realism and adaptability of the target decorative materials. Furthermore, when generating target decorative materials using the first target model, the embodiments of this disclosure can also combine a reference image containing the material style, thereby improving the adaptability between the target decorative materials and the image being decorated.

[0066] Example devices and equipment

[0067] Embodiments of this disclosure also provide corresponding apparatus for implementing the above methods or processes. Figure 5 A schematic structural block diagram of an example device 700 for providing decorative materials according to certain embodiments of the present disclosure is shown. Device 700 may be implemented as or included in terminal device 110. Various modules / components in device 700 may be implemented by hardware, software, firmware, or any combination thereof.

[0068] like Figure 7 As shown, the device 700 includes: an acquisition module 710 configured to acquire input information indicating a material category and a material style; and a providing module 720 configured to provide a target decorative material generated based on the input information, wherein the target decorative material is generated based on the following process: determining mask information corresponding to the material category, the mask information indicating a target area for generating the decorative material; providing a reference image, the mask information, and a first prompt word corresponding to the input information to a first target model to instruct the first target model to fill the target area in the reference image; and generating the target decorative material based on the filling result of the target area.

[0069] In some embodiments, the reference image includes a reference object associated with the target decorative material to be generated, and mask information is associated with the position of the reference object in the reference image.

[0070] In some embodiments, the reference image has an image style that matches the material style.

[0071] In some embodiments, the reference image is obtained based on the following process: generating a second cue word corresponding to the material style; providing the input image and the second cue word to the second target model to instruct the second target model to adjust the input image according to the material style to obtain the reference image.

[0072] In some embodiments, the first prompt word is generated based on the following process: processing input information using a language model to generate a first prompt word that matches a preset prompt word template.

[0073] In some embodiments, determining the mask information corresponding to the material category includes: determining the mask information corresponding to the material category from a set of candidate mask information corresponding to a set of candidate material categories based on the material category.

[0074] In some embodiments, generating a target decorative material based on the filling result of the target region includes: obtaining an intermediate image generated by the first target model by filling the target region in a reference image; and segmenting the target decorative material from the intermediate image.

[0075] In some embodiments, segmenting the target decorative material from the intermediate image includes: segmenting the target decorative material from the intermediate image based on mask information.

[0076] like Figure 8 As shown, electronic device 800 is in the form of a general-purpose electronic device. Components of electronic device 800 may include, but are not limited to, one or more processors or processing units 810, memory 820, storage device 830, one or more communication units 840, one or more input devices 850, and one or more output devices 860. Processing unit 810 may be a physical or virtual processor and is capable of performing various processes according to programs stored in memory 820. In a multiprocessor system, multiple processing units execute computer-executable instructions in parallel to improve the parallel processing capability of electronic device 800.

[0077] Electronic device 800 typically includes multiple computer storage media. Such media can be any accessible media that is accessible to electronic device 800, including but not limited to volatile and non-volatile media, removable and non-removable media. Memory 820 can be volatile memory (e.g., registers, cache, random access memory (RAM)), non-volatile memory (e.g., read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof. Storage device 830 can be removable or non-removable media and can include machine-readable media, such as flash drives, disks, or any other media that can be used to store information and / or data and can be accessed within electronic device 800.

[0078] Electronic device 800 may further include additional removable / non-removable, volatile / non-volatile storage media. Although not explicitly stated... Figure 8 As shown, disk drives for reading from or writing to removable, non-volatile disks (e.g., "floppy disks") and optical disk drives for reading from or writing to removable, non-volatile optical disks can be provided. In these cases, each drive can be connected to a bus (not shown) via one or more data media interfaces. Memory 820 may include computer program product 825 having one or more program modules configured to perform various methods or actions of various embodiments of this disclosure.

[0079] The communication unit 840 enables communication with other electronic devices via a communication medium. Additionally, the functionality of the components of the electronic device 800 can be implemented using a single computing cluster or multiple computing machines capable of communicating via communication connections. Therefore, the electronic device 800 can operate in a networked environment using logical connections to one or more other servers, network personal computers (PCs), or another network node.

[0080] Input device 850 can be one or more input devices, such as a mouse, keyboard, trackball, etc. Output device 860 can be one or more output devices, such as a monitor, speaker, printer, etc. Electronic device 800 can also communicate with one or more external devices (not shown) via communication unit 840 as needed. These external devices include storage devices, display devices, etc., and can communicate with one or more devices that enable user interaction with electronic device 800, or with any device that enables electronic device 800 to communicate with one or more other electronic devices (e.g., network card, modem, etc.). Such communication can be performed via input / output (I / O) interface (not shown).

[0081] According to an exemplary implementation of this disclosure, a computer-readable storage medium is provided that stores computer-executable instructions thereon, wherein the computer-executable instructions are executed by a processor to implement the methods described above. According to an exemplary implementation of this disclosure, a computer program product is also provided, which is tangibly stored on a non-transitory computer-readable medium and includes computer-executable instructions, which are executed by a processor to implement the methods described above.

[0082] Various aspects of this disclosure are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatuses, devices, and computer program products implemented according to this disclosure. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.

[0083] These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processing unit of the computer or other programmable data processing apparatus, they create means for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner. Thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0084] Computer-readable program instructions can be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions that execute on the computer, other programmable data processing apparatus, or other device to perform the functions / actions specified in one or more boxes of a flowchart and / or block diagram.

[0085] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction, which contains one or more executable instructions for implementing the specified logical function. In some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0086] Various implementations of this disclosure have been described above. These descriptions are exemplary and not exhaustive, nor are they limited to the disclosed implementations. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described implementations. The terminology used herein is chosen to best explain the principles, practical applications, or improvements to technology in the market, or to enable others skilled in the art to understand the various implementations disclosed herein.

Claims

1. A method for generating decorative materials, comprising: Obtain input information, which indicates the material category and material style; as well as, A target decorative material generated based on the input information is provided, wherein the target decorative material is generated based on the following process: determining mask information corresponding to the material category, the mask information indicating a target area for generating the decorative material; providing a reference image, the mask information, and a first prompt word corresponding to the input information to a first target model to instruct the first target model to fill the target area in the reference image; and generating the target decorative material based on the filling result of the target area.

2. The method according to claim 1, wherein, The reference image includes a reference object associated with the target decorative material to be generated, and the mask information is associated with the position of the reference object in the reference image.

3. The method according to claim 2, wherein, The reference image has an image style that matches the material style.

4. The method according to claim 3, wherein, The reference image is obtained based on the following process: generating a second prompt word corresponding to the material style; The input image and the second prompt word are provided to the second target model to instruct the second target model to adjust the input image according to the material style to obtain the reference image.

5. The method according to claim 1, wherein, The first prompt word is generated based on the following process: processing the input information using a language model to generate the first prompt word that matches a preset prompt word template.

6. The method according to claim 1, wherein, The process of determining the mask information corresponding to the material category includes: Based on the material category, the mask information corresponding to the material category is determined from a set of candidate mask information corresponding to a set of candidate material categories.

7. The method according to claim 1, wherein, The process of generating the target decorative material based on the filling result of the target region includes: Obtain an intermediate image generated by the first target model by filling the target region in the reference image; and, The target decorative material is segmented from the intermediate image.

8. The method according to claim 7, wherein, Segmenting the target decorative material from the intermediate image includes: Based on the mask information, the target decorative material is segmented from the intermediate image.

9. An apparatus for generating decorative materials, comprising: The acquisition module is configured to acquire input information, which indicates the material category and material style; as well as, A providing module is configured to provide target decorative material generated based on the input information, wherein the target decorative material is generated based on the following process: determining mask information corresponding to the material category, the mask information indicating a target area for generating the decorative material; providing a reference image, the mask information, and a first prompt word corresponding to the input information to a first target model to instruct the first target model to fill the target area in the reference image; and generating the target decorative material based on the filling result of the target area.

10. An electronic device, comprising: At least one processing unit; as well as, At least one memory, coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, which, when executed by the at least one processing unit, cause the electronic device to perform the method according to any one of claims 1 to 8.

11. A computer-readable storage medium having a computer program stored thereon, the computer program being executable by a processor to implement the method according to any one of claims 1 to 8.

Images