Virtual object processing method and device, electronic equipment and readable storage medium

Abstract

The invention provides a virtual object processing method and device, electronic equipment and a readable storage medium, and the method comprises the steps: responding to a first adjustment instruction for a first image of a virtual object, and adjusting the first image to obtain a second image; wherein the first adjustment instruction is an instruction generated according to an input text and / or input voice; in response to a second adjustment instruction for a second image of the virtual object, adjusting the second image to obtain a third image; wherein the second adjustment instruction is an instruction generated according to the input text and / or the input voice. Thus, different first adjustment instructions and second adjustment instructions can be input for multiple times, the image of the virtual object is interactively updated and adjusted through the first adjustment instructions and the second adjustment instructions, and the accuracy of image adjustment of the virtual object and the man-machine interaction efficiency can be improved.

Description

Technical Field

[0001] This disclosure relates to the field of human-computer interaction technology, and in particular to methods, apparatuses, electronic devices and readable storage media for processing virtual objects. Background Technology

[0002] With the development of mobile terminals and computer technology, more and more human-computer interaction games have emerged. In order to meet the personalized customization needs of different players, some object image functions are usually added for players. Based on the basic virtual objects, players can modify and adjust the virtual objects, so that players can create corresponding virtual objects according to their own preferences.

[0003] In related technologies, when players modify the appearance of virtual objects, they usually set up multiple different appearance materials. Players adjust the appearance of virtual objects by selecting the appearance materials. However, the above operation is relatively cumbersome and the efficiency of adjusting the appearance of virtual objects is low.

[0004] With the development of artificial intelligence, AI methods have also been introduced into the modification of virtual objects. By inputting specific descriptive information, the appearance of virtual objects can be changed, greatly reducing the steps involved in modifying the appearance of virtual objects and improving the efficiency of adjusting the appearance of virtual objects. However, due to input limitations, the descriptive information must be entered completely and accurately at once. If the input information is ambiguous, it will affect the process of adjusting the appearance of virtual objects, resulting in a low accuracy rate of the adjustment and thus affecting the efficiency of human-computer interaction. Summary of the Invention

[0005] In view of this, the present disclosure provides a method, apparatus, electronic device and readable storage medium for processing virtual objects, which can input different first adjustment instructions and second adjustment instructions multiple times, and interactively update and adjust the image of the virtual object through the first adjustment instructions and second adjustment instructions, which helps to improve the accuracy of adjusting the image of the virtual object and the efficiency of human-computer interaction.

[0006] In a first aspect, an optional embodiment provides a method for processing virtual objects, the method comprising:

[0007] In response to a first adjustment instruction for a first image of a virtual object, the first image is adjusted to obtain a second image; wherein the first adjustment instruction is an instruction generated based on input text and / or input voice.

[0008] In response to a second adjustment instruction for a second image of a virtual object, the second image is adjusted to obtain a third image; wherein the second adjustment instruction is an instruction generated based on input text and / or input speech.

[0009] Secondly, an optional embodiment also provides a processing apparatus for virtual objects, the processing apparatus comprising:

[0010] The first image adjustment module is used to respond to a first adjustment instruction for a first image of a virtual object and adjust the first image to obtain a second image; wherein the first adjustment instruction is an instruction generated based on input text and / or input voice.

[0011] The second image adjustment module is used to respond to a second adjustment instruction for a second image of a virtual object and adjust the second image to obtain a third image; wherein the second adjustment instruction is an instruction generated based on input text and / or input voice.

[0012] Thirdly, optional embodiments also provide an electronic device, including: a processor, a storage medium, and a bus, wherein the storage medium stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor communicates with the storage medium via the bus, and the processor executes the machine-readable instructions to perform a virtual object processing method as described in any of the first aspects.

[0013] Fourthly, optional embodiments also provide a computer-readable storage medium storing a computer program that, when executed by a processor, performs the virtual object processing method as described in any of the first aspects.

[0014] The optional embodiments provide a virtual object processing method, apparatus, electronic device, and readable storage medium that, in response to a first adjustment instruction for a first image of a virtual object, adjusts the first image to obtain a second image; wherein the first adjustment instruction is an instruction generated based on input text and / or input voice; in response to a second adjustment instruction for the second image of the virtual object, adjusts the second image to obtain a third image; wherein the second adjustment instruction is an instruction generated based on input text and / or input voice. In this way, different first and second adjustment instructions can be input multiple times, and the image of the virtual object can be interactively updated and adjusted through the first and second adjustment instructions, which helps to improve the accuracy of image adjustment for virtual objects and the efficiency of human-computer interaction.

[0015] To make the above-mentioned objects, features and advantages of this disclosure more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0016] To more clearly illustrate the technical solutions of the optional embodiments, the accompanying drawings used in the embodiments will be briefly described below. It should be understood that the following drawings only show some embodiments of this disclosure and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 A flowchart of a method for processing virtual objects provided as an optional embodiment;

[0018] Figure 2 A flowchart for generating the object image provided in an optional embodiment;

[0019] Figure 3 A schematic diagram of the object adjustment interface provided for an optional embodiment;

[0020] Figure 4 One of the schematic diagrams of the intelligent adjustment interface provided for an optional embodiment;

[0021] Figure 5 A second schematic diagram of the intelligent adjustment interface provided for an optional embodiment;

[0022] Figure 6 The third schematic diagram of the intelligent adjustment interface provided for an optional embodiment;

[0023] Figure 7 Fourth schematic diagram of the intelligent adjustment interface provided for an optional embodiment;

[0024] Figure 8 A schematic diagram of the exit prompt information provided for an optional embodiment;

[0025] Figure 9 A schematic diagram illustrating the save prompt information provided for an optional embodiment;

[0026] Figure 10 A schematic diagram of the structure of a virtual object processing device provided for an optional embodiment;

[0027] Figure 11 This is a schematic diagram of the structure of an electronic device provided as an optional embodiment. Detailed Implementation

[0028] To make the objectives, technical solutions, and advantages of the optional embodiments clearer, the technical solutions in the optional embodiments will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this disclosure, and not all of them. The components of the optional embodiments described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this disclosure provided in the accompanying drawings is not intended to limit the scope of the claimed disclosure, but merely represents selected embodiments of this disclosure. Every other embodiment obtained by those skilled in the art based on the embodiments of this disclosure without inventive effort falls within the scope of protection of this disclosure.

[0029] In an optional implementation, various cloud applications, such as cloud gaming, can run under the cloud interaction system. Taking cloud gaming as an example, cloud gaming refers to a gaming method based on cloud computing. In the cloud gaming operating mode, the game program's execution and the game screen presentation are separated. The storage and execution of virtual object processing methods are completed on the cloud gaming server. The client device is used for data reception, transmission, and game screen presentation. For example, the client device can be a display device with data transmission capabilities located close to the user, such as a mobile terminal, television, computer, or PDA; however, the information processing is performed by the cloud gaming server in the cloud. When playing the game, the player operates the client device to send operation commands to the cloud gaming server. The cloud gaming server runs the game according to the operation commands, encodes and compresses game screen data, returns it to the client device via the network, and finally, the client device decodes and outputs the game screen.

[0030] In an optional implementation, taking a game as an example, the local terminal device stores the game program and is used to display the game screen. The local terminal device is used to interact with the player through a graphical user interface (GUI), i.e., conventionally by downloading, installing, and running the game program via an electronic device. The local terminal device can provide the GUI to the player in various ways, such as rendering it on the terminal's display screen or providing it to the player via holographic projection. For example, the local terminal device can include a display screen for displaying the GUI, which includes game screens, and a processor for running the game, generating the GUI, and controlling the display of the GUI on the display screen.

[0031] In one optional implementation, this invention provides a method for processing virtual objects, which provides a graphical user interface through a terminal device. The terminal device can be a local terminal device (such as a local touch terminal) as mentioned above, or a client device in the aforementioned cloud interaction system. The following description uses the example of the virtual object processing method running on a local terminal device (hereinafter referred to as the terminal device).

[0032] Please see Figure 1 , Figure 1 A flowchart illustrating a method for processing virtual objects, provided as an optional embodiment. (e.g.) Figure 1 As shown, the optional embodiment provides a method for processing virtual objects, including:

[0033] S101. Responding to a first adjustment instruction for a first image of a virtual object, adjust the first image to obtain a second image; wherein the first adjustment instruction is an instruction generated based on input text and / or input voice.

[0034] S102, responding to a second adjustment instruction for a second image of a virtual object, adjusting the second image to obtain a third image; wherein the second adjustment instruction is an instruction generated based on input text and / or input speech.

[0035] The optional embodiment of the virtual object processing method allows for multiple inputs of different first adjustment instructions and second adjustment instructions. Through these first and second adjustment instructions, the image of the virtual object can be interactively updated and adjusted, which helps to improve the accuracy of the image adjustment of the virtual object and the efficiency of human-computer interaction.

[0036] The steps of the optional embodiments are described below:

[0037] S101. Responding to a first adjustment instruction for a first image of a virtual object, adjust the first image to obtain a second image; wherein the first adjustment instruction is an instruction generated based on input text and / or input voice.

[0038] In an optional embodiment, for virtual objects controlled by the player in the game, the player can adjust the appearance of the virtual objects to better suit the player's needs for the appearance of the objects.

[0039] In one alternative implementation, the virtual object can be a virtual prop, a virtual character, etc.; when the virtual object is a virtual prop, the appearance of the virtual prop can be adjusted, and when the virtual object is a virtual character, the appearance of the virtual character, such as its face, can be adjusted.

[0040] In one alternative implementation, the virtual object's appearance can be adjusted by entering an object adjustment interface. The object adjustment interface displays different functional controls, which can be used to access different object adjustment functions. The adjustment methods of the first and second adjustment commands for the virtual object in this disclosure are also a function under the object adjustment interface. The solution of adjusting the virtual object by adjusting commands can be selected through the function selection on the object adjustment interface.

[0041] Specifically, before the step of "responding to the first adjustment instruction for the first image of the virtual object and adjusting the first image to obtain the second image", the processing method also includes:

[0042] a1: Responds to the trigger operation of the smart adjustment control in the object adjustment interface, enters smart adjustment mode, and displays the smart adjustment interface.

[0043] In an optional embodiment, if the player has not used the smart adjustment function during the historical object processing, a prompt icon can be displayed at a preset position of the smart adjustment control to prompt the player to click the smart adjustment control, experience the smart adjustment function, enhance the diversity of the player's adjustment methods for virtual objects, and further improve the efficiency of human-computer interaction.

[0044] In one alternative implementation, during the process of switching from the object adjustment interface to the intelligent adjustment interface after determining to enter the intelligent interaction function, if it is determined that the player is using the intelligent interaction function for the first time, the function setting rules for the intelligent interaction function can be displayed in the graphical user interface. After the display of the function setting rules for the intelligent interaction function ends, the player enters the intelligent adjustment interface. At the same time, a confirmation control is displayed while the function setting rules are displayed. The player can close the display of the function setting rules in advance by touching the confirmation control and directly enter the intelligent adjustment interface to use the intelligent interaction function to adjust the virtual object, thereby further improving the efficiency of interface switching and human-computer interaction.

[0045] In one alternative implementation, the intelligent adjustment interface displays the virtual object to be adjusted, and simultaneously displays a command input area. The command input area is compatible with both text and voice input. Players can input text and / or voice through different input areas to generate image adjustment commands for the virtual object.

[0046] Specifically, the text input area may have corresponding input boxes and input controls. When the player clicks on the input box or input control, an input software disk will be displayed in the intelligent adjustment interface. The player can input text and issue the first adjustment command and / or the second adjustment command by inputting on the input software disk. The voice input area may display a voice input control. The player can input voice by triggering the voice input control, and end the voice input process after ending the triggering operation of the voice input control.

[0047] In one alternative implementation, since the input voice method requires the cooperation of the terminal device's voice acquisition device (such as a microphone) for acquisition, if the current system does not support the activation of the voice acquisition device or the current voice acquisition device is not activated, it is necessary to respond to the trigger operation of the voice input control, display a voice acquisition device activation prompt message, and complete the acquisition process of the player's input voice after confirming that the voice acquisition device is activated.

[0048] In one alternative implementation, the first adjustment instruction for the first image of the virtual object can be an adjustment to the overall style of the virtual object or an adjustment to a local part of the virtual object. The different adjustment methods for the virtual object will be described below.

[0049] In one alternative implementation, the step "in response to a first adjustment instruction for a first image of a virtual object, adjusting the first image to obtain a second image" includes:

[0050] b1: Respond to the first adjustment instruction for the first image of the virtual object, and parse the first local adjustment information contained in the first adjustment instruction.

[0051] b2: Adjust the first image based on the first partial adjustment information to obtain the second image.

[0052] In an optional embodiment, after determining that the first adjustment instruction has been received, regardless of whether the first adjustment instruction is determined by input text or by voice, the first adjustment instruction can be converted into adjustment text during the analysis of the first adjustment instruction. The first local adjustment information for the virtual object can be determined by voice analysis of the adjustment text. The first image of the virtual object can be adjusted according to the first local adjustment information to obtain the second image.

[0053] Specifically, the analysis of the first adjustment instruction can be to analyze the part to be adjusted and the specific adjustment instruction from the first adjustment instruction, and then adjust the first image of the virtual object to obtain the second image.

[0054] For example, if the player determines the first adjustment instruction by inputting text as "make the eyes bigger", then through analysis, it can be seen that the first adjustment instruction issued by the player is to adjust the local part of the virtual object as "eyes", and the specific adjustment instruction is "make them bigger". Therefore, when adjusting the virtual object according to the first image to obtain the second image, the eyes of the virtual object in the second image are larger than the eyes of the virtual object in the first image.

[0055] In another alternative implementation, the first adjustment instruction can be used to adjust local information of the virtual object, or it can be used to adjust the overall style of the virtual object, thereby regenerating a virtual object with a completely new style. In this case, the style of the second virtual object is inconsistent with that of the first virtual object.

[0056] Specifically, the step "responding to the first adjustment instruction for the first image of the virtual object and adjusting the first image to obtain the second image" further includes: responding to the first adjustment instruction for the first image of the virtual object, parsing the first overall style adjustment information contained in the first adjustment instruction; and adjusting the first image according to the first local adjustment information to obtain the second image.

[0057] In one optional implementation, when entering the intelligent interaction mode, the overall style of the first image of the virtual object is "cute style". If you want to adjust the overall style of the virtual object, you can directly issue a first adjustment command containing the overall style information by inputting text and / or voice. By analyzing the first adjustment command, the current style adjustment direction and specific adjustment method of the virtual object can be determined. For example, after analysis, it can be seen that the input first adjustment command is "mature style". At this time, it is necessary to adjust the overall "cute style" of the first image to the "mature style" of the second image, and thus obtain the virtual object after adjustment to the second image.

[0058] In another alternative implementation, after receiving the first adjustment instruction, a second image of the virtual object can be generated using artificial intelligence technology.

[0059] Specifically, the step "responding to a first adjustment instruction for a first image of a virtual object, adjusting the first image to obtain a second image" includes:

[0060] c1: In response to the first adjustment instruction for the first image of the virtual object, the second image is obtained by adjusting the first image according to the first adjustment instruction through artificial intelligence.

[0061] In an optional embodiment, artificial intelligence (AI) can autonomously analyze the first adjustment command input by the player to determine the player's intention to adjust the virtual object, and then directly generate a second virtual object that matches the player's intention, adjusting the virtual object from the first image to the second image.

[0062] In one alternative implementation, when adjusting the overall style of a virtual object, in order to better match the player's expectations for the adjustment of the virtual object, the artificial intelligence can generate multiple different second images according to the first adjustment instruction. At this time, the second image that best matches the player's expectations can be selected based on the player's historical object adjustment information.

[0063] For example, the player's first adjustment command is to generate a "mature style" virtual object. The artificial intelligence generates multiple mature style second images. At this time, according to the player's historical object adjustment information, it can be seen that the player prefers virtual objects with fair skin. Therefore, the virtual image with the fairest skin can be determined as the second image from the multiple mature style virtual images generated by the artificial intelligence.

[0064] In one alternative implementation, artificial intelligence can adjust a local part of a virtual object using a first adjustment instruction.

[0065] Specifically, the step "adjusting the first image according to the first adjustment instruction using artificial intelligence to obtain the second image" includes:

[0066] d1: The second image is obtained by making partial adjustments to the first image according to the first adjustment instruction using artificial intelligence.

[0067] In an optional embodiment, similarly, when making local adjustments to a virtual object, in order to better match the player's expectations for the virtual object, the artificial intelligence can generate multiple different second images based on the first adjustment instruction. At this time, the second image that best matches the player's expectations can be selected based on the player's historical object adjustment information.

[0068] For example, after receiving the first adjustment instruction, it is determined that the current player's adjustment goal is to enlarge the eyes of the virtual object. At this time, the artificial intelligence can generate multiple candidate images with enlarged local eyes. Then, combined with the player's historical object adjustment information, it is determined that the player prefers round and large eyes. Therefore, it is necessary to select the candidate image with larger and rounder eyes from the multiple generated candidate images with enlarged eyes as the second image, and adjust the virtual object from the first image to the second image.

[0069] Optionally, in one implementation, prompt text can be displayed in the command input area. Currently, the prompt text is in a non-interactive state, only providing feedback to the player's input. Alternatively, it can be in an interactive state, allowing the player to click on it for quick input. The prompt text displayed in the command input area can be personalized based on the player's input habits, or it can be based on the historical adjustment frequency of multiple players for the virtual avatar that the player needs to adjust, displaying the text with the highest adjustment frequency for that virtual avatar in the command input area.

[0070] In one alternative implementation, players can issue a first adjustment command to adjust the virtual object by entering text commands in the command input area. However, considering the computational load of the server background processing and to ensure the processing efficiency of the background server, an input limit can be set in the command input area. When the preset limit is exceeded, the player will be prompted that no more commands can be entered.

[0071] Specifically, the processing methods also include:

[0072] e1: Determine the number of input information in the first adjustment instruction or the second adjustment instruction.

[0073] e2: In response to the number of input messages reaching a preset threshold, display a message indicating the maximum input limit.

[0074] In an optional embodiment, the number of input messages can be set by the number of characters, with a corresponding preset information quantity threshold. Upon determining that the number of input messages in either the first or second adjustment command exceeds the preset threshold, an input limit prompt is displayed to remind the player to re-enter the adjustment command. This ensures accurate prompts for the player, reduces the steps of repeatedly entering useless text, improves human-computer interaction efficiency, reduces the data processing load on the backend server, and improves server processing efficiency. Optionally, the number of input messages can also be the number of times the adjustment command is entered.

[0075] In one alternative implementation, the information input limit prompt message may be a message stating "The maximum amount of text that can be entered has been reached".

[0076] For example, if we consider one Chinese character as one character, and the preset information quantity threshold is set to 10 characters (this is just a theoretical example; in actual applications, the preset information quantity threshold is usually set to be relatively large, which can basically meet the input needs of players), then the adjustment command entered by the player, "mature style big eyes red hair girl", exceeds the preset information quantity threshold of 10 characters. In this case, only "mature style big eyes red head" can be displayed in the command input area, and the prompt message "Input text has reached the limit" will be displayed.

[0077] In one alternative implementation, the second image generated according to the first adjustment instruction may not fully meet the player's adjustment needs. In order to ensure that the image adjustment is more in line with the player's adjustment needs and further improve human-computer interaction efficiency, a scheme for regenerating the second image is also provided in the embodiments of this disclosure.

[0078] Specifically, the processing methods also include:

[0079] f1: In response to the regeneration instruction for the second image of the virtual object, the first image is adjusted based on the first adjustment instruction to obtain the sixth image; wherein, the virtual object of the sixth image has the same style as the virtual object of the second image, but the local details of the object are different.

[0080] In an optional embodiment, in addition to displaying the virtual object to be adjusted and the command input area in the intelligent adjustment interface, a command display area is also displayed. In the command display area, multiple first adjustment commands entered by the player in this round are displayed in text form, and the multiple first adjustment commands are displayed in the order of their input time.

[0081] Specifically, the processing methods also include:

[0082] g1: Display the input text and / or input speech included in the first or second adjustment instruction in text form according to the input order.

[0083] In an optional embodiment of this disclosure, after a player inputs a first adjustment command or a second adjustment command in the command input area, whether it is text input or voice input, it can be converted into text format. A send control is set in the command input area. The first or second adjustment command is only displayed in the command display area after the first or second adjustment command is input and a trigger command is issued for the send control. Furthermore, the commands are displayed in the order they were input. Optionally, voice input may not be converted into text format for display.

[0084] In one alternative implementation, if the player does not input the first adjustment command or the second adjustment command, but instead issues a touch operation on the send control, a prompt message indicating that input cannot be sent will be displayed in the graphical user interface to prompt the player to input the first adjustment command or the second adjustment command before sending it again.

[0085] For example, the specific content displayed when input cannot be sent could be "No text has been entered."

[0086] In one alternative implementation, a "Regenerate" prompt message will also be displayed in the instruction display area to remind players that if they are not satisfied with the current second image generation result, they can regenerate the second image by regenerating it.

[0087] Optionally, the player's regeneration command is for the first adjustment command generated in each round. Other first adjustment commands that are not generated in the first round can be readjusted through a rollback operation.

[0088] In one alternative implementation, a regeneration control can be set in the instruction display area. In response to a touch operation on the regeneration control, a regeneration instruction is issued. After receiving the regeneration instruction, the corresponding sixth image is regenerated according to the first adjustment instruction, and the virtual object is adjusted according to the sixth image, changing the virtual object from the first image to the second image.

[0089] Among them, the virtual object of the sixth image has the same style as the virtual object of the second image, but the local details of the objects are different.

[0090] For example, if the first adjustment command input in this adjustment is "adjust style to mature style", then a second image with black eyes and a mature style can be generated according to the first adjustment command, and the virtual object can be adjusted from the first image to the second image. If the player is not satisfied and issues a regeneration command, then a sixth image with green eyes and a mature style can be generated according to the regeneration command. Optionally, the second image and the sixth image have the same style, both being mature style, but there are differences in the details between the two; one has black eyes and the other has green eyes.

[0091] In one alternative implementation, after the player issues a regenerate command, if the sixth image is not generated again, in order to reduce the probability that the player is still dissatisfied, the player needs to issue a regenerate command again and regenerate a new image. This would be a tedious process and would further improve the efficiency of human-computer interaction. Instead, when generating the sixth image again, the player's historical adjustment information can be referenced to directly generate a sixth image that better meets the player's settings requirements, reducing the player's repeated operations on image generation.

[0092] In one alternative implementation, a rollback operation can be performed on the adjustment command given by the player, withdrawing the adjustment command and reversing the adjustment to the virtual character's appearance.

[0093] Specifically, the processing methods also include:

[0094] h1: In response to the rollback operation for the second adjustment command, adjust the virtual object's second appearance back to its first appearance. This achieves a rollback to the appearance before the adjustment via the second adjustment command.

[0095] h2: In response to the rollback operation for the second adjustment instruction, the virtual object's appearance is rolled back to the appearance corresponding to the second adjustment instruction.

[0096] In an optional embodiment, similarly, in addition to displaying the virtual object to be adjusted and the command input area in the intelligent adjustment interface, a command display area is also displayed. In the command display area, multiple first adjustment commands entered by the player in this round are displayed in text form, and the multiple first adjustment commands are displayed in the order of their input time.

[0097] Optionally, the back action can be triggered via touch, keyboard, or mouse. Alternatively, the back action can be triggered via a control or a shortcut.

[0098] Optionally, in response to a rollback operation for the second adjustment command, the virtual object's appearance is rolled back to the appearance corresponding to the second adjustment command. Optionally, the appearance corresponding to the second adjustment command refers to the appearance adjusted according to the second adjustment command. For example, during the process of adjusting the virtual object's appearance, the player can input adjustment commands multiple times and make multiple adjustments accordingly. Taking four adjustment commands as an example, they are denoted as command 1, command 2, command 3, and command 4. Command 4 is the latest adjustment command, and the currently displayed appearance is the appearance adjusted according to command 4. The player can choose to roll back to the appearance corresponding to command 1, command 2, or command 3. For example, the player can choose to roll back to the appearance corresponding to command 3, which is the appearance adjusted according to command 3 during the above adjustment process, but has not yet been adjusted by command 4.

[0099] Optionally, in response to a rollback operation for the third adjustment command, the virtual object's appearance is rolled back to the appearance corresponding to the third adjustment command. Similarly, rollback can also be performed for other adjustment commands.

[0100] In one optional implementation, a back button can be set at a preset position for each first adjustment instruction displayed in the instruction display area (optionally, except for the first or last adjustment instruction issued). By touching the back button at the corresponding position, the corresponding first adjustment instruction can be undone, and the image of the virtual object can be adjusted to the image before the first adjustment instruction was undone.

[0101] For example, if a player enters two adjustment commands consecutively: "girl" and "enlarge eyes", the virtual object's image will be changed to a girl with big eyes after the two adjustment commands. If the player chooses to undo the "enlarge eyes" adjustment command, the virtual object's image after "enlarge eyes" will be canceled, and the virtual object with the girl image will be obtained.

[0102] Optionally, when performing a rollback operation, other first adjustment instructions following the first adjustment instruction to be rolled back will also be revoked, and the image of the virtual object will be adjusted to the image before the first adjustment instruction to be rolled back.

[0103] For example, if a player enters three adjustment commands in succession: "girl", "enlarge eyes", and "pink hair", the virtual object's image will be changed to a girl with big eyes and pink hair after the three adjustment commands. If the player chooses to undo the "enlarge eyes" adjustment command, the virtual object's image will be undone according to the adjustment commands "enlarge eyes" and "pink hair", and the virtual object with the girl image will be obtained.

[0104] In one alternative implementation, if a player simultaneously inputs multiple first adjustment commands, it is necessary to set the number of undo commands, that is, to set the number of times the first adjustment commands can be undoed. Only the first adjustment commands that exceed the preset number of undo commands can be undoed. For first adjustment commands that exceed the number of undo commands, the undo control displayed before the first adjustment command that exceeds the number of undo commands is canceled to prompt the player that the current first adjustment command cannot be undoed again.

[0105] Specifically, the rollback count can be set to 3, indicating that the first adjustment command of the last three adjustment inputs can be rolled back; historical first adjustment commands beyond 3 times cannot be rolled back; rollback data will be recorded in the client's local cache.

[0106] For example, if six adjustment commands are entered during the process of adjusting the appearance of a virtual object, and the number of undo operations is set to three, then the adjustment commands from the fourth to the sixth can be undoed. The adjustment commands from the second to the third cannot be undoed. If you want to undo the adjustment commands from the second to the third, you need to undo all the appearance adjustment schemes by restoring to the initial scheme and start readjusting the appearance of the virtual object again.

[0107] In one alternative implementation, to further save players' time in inputting adjustment commands, or to provide players with some adjustment command references and improve human-computer interaction efficiency, multiple adjustment example labels can be displayed in the command input area. Players can directly select the corresponding adjustment example label to adjust the appearance of the virtual object.

[0108] Specifically, the processing methods also include:

[0109] i1: Display at least one adjustment example label.

[0110] i2: In response to a selection operation on a target example label in at least one adjustment example label, adjust the first image of the virtual object to obtain the seventh image.

[0111] In an optional embodiment, at least one adjustment example label may be determined based on the player's input habits, the attribute information of the virtual object, and the current adjustment progress of the virtual object.

[0112] Specifically, in one optional implementation, the adjustment commands of players in the process of making historical adjustments to virtual objects can be analyzed. Based on the adjustment information contained in the adjustment commands, adjustment information with a probability greater than a preset probability threshold can be determined, and the above adjustment information can be used as the basis for setting adjustment example labels.

[0113] In one alternative implementation, corresponding adjustment example tags can be set for the attribute information of the virtual object, and adjustment example tags that match the gender and personality of the virtual object can be set according to the gender and personality of the virtual object.

[0114] For example, if the gender of the virtual object is set to male, then the example label can be set to "male god" instead of labels such as "girl" which are obviously inconsistent with the virtual object.

[0115] In one alternative implementation, the determination can be based on the current progress of the virtual object adjustment. If the overall style of the virtual object has not yet been adjusted, the adjustment example label can be set to the overall style label ("mature style", "cute style", etc.). If the virtual object image adjustment has been completed and the overall style adjustment has been completed, the adjustment example label representing the details ("hair longer", "eyes bigger", etc.) can be selected to allow players to select the detail adjustment label to make detailed adjustments to the virtual object.

[0116] In one alternative implementation, the adjustment example tag may include descriptive tags and adjustment tags. The descriptive tags may be tags that describe the overall style of the virtual object, and the adjustment tags may be tags that make local detail adjustments to the virtual object.

[0117] In one alternative implementation, a preset number of adjustment example tags can be set, with the preset number of adjustment example tags displayed each time for players to choose from.

[0118] For example, the preset display quantity can be set to three, that is, three adjustment example labels are displayed at the same time.

[0119] In one alternative implementation, in order to ensure that each adjustment example label can concisely express the meaning of the label adjustment, and at the same time, to ensure that the adjustment example label does not excessively obscure the entire instruction input area, the number of characters in each adjustment example label can be limited. For example, the number of characters in each adjustment example label generally does not exceed four characters.

[0120] Furthermore, after setting and displaying at least one adjustment example label, players can issue adjustment commands by selecting the adjustment example label to adjust the first image of the virtual object and obtain the seventh image.

[0121] Specifically, the step "in response to a selection operation on at least one target example label in the adjustment example label, adjusting the first image of the virtual object to obtain the seventh image" includes:

[0122] j1: In response to a selection operation on a target example label in at least one adjustment example label, parse the second local adjustment information contained in the target example label.

[0123] j2: Adjust the first image according to the second local adjustment information to obtain the seventh image.

[0124] In an optional embodiment, players can select a target example tag from at least one adjustment example tag via touch operation. After selecting the target example tag, the player can directly issue an adjustment command to adjust the appearance of the virtual object without having to send the command again, further saving the player's adjustment time and steps, and improving the efficiency of object appearance adjustment and human-computer interaction.

[0125] In one alternative implementation, if the selected target example label is determined, the target example label is converted into adjustment text, and the second local adjustment information for the virtual object is determined by speech analysis of the adjustment text. The first image of the virtual object is then adjusted according to the second local adjustment information to obtain the seventh image.

[0126] Specifically, similarly, the analysis of the target example label can be to analyze the parts to be adjusted and the specific adjustment instructions from the target example label, and then adjust the first image of the virtual object to obtain the seventh image.

[0127] In another alternative implementation, similarly, after selecting the target example tag, semantic analysis can be omitted, and instead, the seventh image of the virtual object can be directly generated through artificial intelligence technology.

[0128] Specifically, the step "in response to a selection operation on at least one target example label in the adjustment example label, adjusting the first image of the virtual object to obtain the seventh image" includes:

[0129] k1: In response to the selection operation of the target example label in at least one adjustment example label, the first image is adjusted according to the target example label by artificial intelligence to obtain the seventh image.

[0130] In an optional embodiment, similarly, the AI ​​can autonomously analyze the selected target example tags to determine the adjustment intention for the virtual object, and then directly generate a virtual object of the seventh image that conforms to the adjustment intention, adjusting the virtual object from the first image to the seventh image.

[0131] In one alternative implementation, when adjusting the overall style of a virtual object, in order to better match the player's expectations for the adjustment of the virtual object, artificial intelligence can generate multiple different seventh images based on the selected target example tags. At this time, the seventh image that best matches the player's expectations can be selected based on the player's historical object adjustment information.

[0132] In another alternative implementation, the virtual object can be partially adjusted using artificial intelligence based on the selected target example tag. Similarly, in order to better match the player's expectations for the adjustment of the virtual object, the artificial intelligence can generate multiple different seventh images based on the selected target example tag. At this time, the seventh image that best matches the player's expectations can be selected based on the player's historical object adjustment information.

[0133] Furthermore, to ensure that players have access to a variety of selectable adjustment example tags, thereby enhancing the diversity of player choices and the efficiency of human-computer interaction, the displayed adjustment example tags can be updated so that players can filter out the target example tags that better suit their preferences.

[0134] Specifically, the processing methods also include:

[0135] l1: In response to a selection operation or an update operation for at least one adjustment example label, display the updated at least one adjustment example label.

[0136] In an optional embodiment, the timing of updating the example tag adjustment can include two scenarios: either after the player selects the target example tag, or the player actively initiates the update operation for adjusting the example tag.

[0137] In one alternative implementation, for cases where the tag is updated after the player selects a target example tag, the adjustment example tags displayed in the command input area each time generally contain similar or identical adjustment content. After the player selects the target example tag, it indicates that the player will not select other adjustment example tags in the same group as the target example tag. Therefore, the adjustment example tags can be adjusted.

[0138] For example, the command input area currently displays three adjustment example labels: "mature", "girl", and "cute". After the player selects the "mature" adjustment example label as the target example label, "girl" and "cute" will also be automatically updated.

[0139] In one optional implementation, when updating the tag after the player selects a target example tag, the updated example tag will generally have a different style from the previously displayed example tag. For example, if the previous example tag represented adjustment information for the overall style of the virtual object, then the updated example tag will generally represent adjustment information for a local feature of the virtual object; if the previous example tag represented adjustment information for a certain local feature of the virtual object, then the updated example tag will generally represent adjustment information for another local feature of the virtual object.

[0140] For example, the command input area currently displays three adjustment example labels: "mature", "girl", and "cute". After the player selects the "mature" adjustment example label as the target example label, "girl" and "cute" will also be automatically updated to the adjustment example labels of "enlarge eyes", "lengthen hair", and "small mouth".

[0141] In another alternative implementation, for cases where a player actively issues an update operation for the adjusted example label, a refresh control can be displayed in the command input area. By triggering the refresh control, an update operation for the adjusted example label can be issued, thereby updating at least one adjusted example label.

[0142] In one alternative implementation, when a player actively requests an update to the adjustment example label, the updated adjustment example label will generally have the same label style as the previously displayed adjustment example label. For example, if the adjustment example label before the update represented adjustment information for the overall style of the virtual object, then the updated adjustment example label can generally also represent adjustment information for the overall style of the virtual object, but with different style description labels.

[0143] In one alternative implementation, an update limit can be set for updating the example tag. When the update limit is reached, an update error message will be displayed to inform the player that the example tag can no longer be updated.

[0144] For example, the updated error message could be "Please do not click frequently".

[0145] In one alternative implementation, if a player is not satisfied with all the adjustments made to a virtual object after it has been adjusted to a second appearance, they can directly restore the virtual object to its original state by using the restore adjustment command. This reduces the steps required for the player to undo each adjustment command and further improves the efficiency of human-computer interaction.

[0146] Specifically, the processing methods also include:

[0147] m1: In response to the restore and adjust command for the virtual object, adjust the image of the virtual object to obtain the eighth image; wherein, the eighth image is the image of the virtual object before adjustment; the restore and adjust command is a command generated based on the input text and / or input voice.

[0148] In an optional embodiment, a recovery adjustment command can be generated by inputting text and / or voice. Upon receiving the recovery adjustment command, the entire image of the virtual object during the adjustment process is undone, and the image of the virtual object before the adjustment is directly restored.

[0149] In one alternative implementation, the restoration and adjustment command may include keywords for regeneration, including but not limited to "regenerate virtual object" and "restore virtual object". After identifying the keywords in the adjustment command, it is determined that the player has issued the restoration and adjustment command, and the image of the virtual object is directly adjusted and restored to obtain the eighth image.

[0150] In one alternative implementation, if it is confirmed that the player has issued a restore / adjust command, a confirmation screen needs to be displayed, asking the player whether they really want the virtual object's appearance restored, and restoring the virtual object's appearance after receiving the player's confirmation command.

[0151] In one optional implementation, after adjusting the image of the virtual object using the first adjustment instruction, the virtual object can be further adjusted based on the second image obtained from the adjustment, and the third image of the virtual object can be obtained by adjusting the second image of the virtual object using the second adjustment instruction.

[0152] S102, responding to a second adjustment instruction for a second image of a virtual object, adjusting the second image to obtain a third image; wherein the second adjustment instruction is an instruction generated based on input text and / or input speech.

[0153] In optional embodiments, the second adjustment instruction may be an adjustment instruction of the same type as the first adjustment instruction, for example, both being instructions that adjust local information of a virtual object, but the two adjustment instructions may not be for the same part; or it may be an adjustment instruction of a different type from the first adjustment instruction. For example, the first adjustment instruction is an instruction to adjust the overall style of the virtual object, and the second adjustment instruction is an instruction to adjust a part of the virtual object.

[0154] The method of adjusting the virtual object through the second adjustment instruction is the same as the method of adjusting the virtual object through the first adjustment instruction, and will not be described again here.

[0155] In one alternative implementation, if a player exits during the process of generating a second or third image through a first or second adjustment instruction, the system needs to confirm with the player before re-exiting and stopping the generation process of the virtual object's image. This prevents accidental player actions and improves the efficiency of human-computer interaction.

[0156] Specifically, the processing methods also include:

[0157] n1: During the process of adjusting and generating the second or third image, respond to the adjustment exit operation and display an exit prompt message.

[0158] n2: In response to the exit selection option in the exit prompt message, stop generating the second or third image.

[0159] In an optional embodiment, an exit control may be displayed in the smart adjustment interface (e.g., displayed in the upper right or upper left corner of the smart adjustment interface), and an exit operation may be initiated by touch operation on the exit control.

[0160] In one alternative implementation, during the virtual object image generation process, if an adjustment exit operation is received, to prevent accidental operation by the player, a confirmation control can be displayed in the exit prompt message. If a touch operation on the confirmation control is received again, it is determined that the player has issued an exit selection operation. At this time, it is determined that the current virtual object image generation process needs to be exited, and the smart adjustment interface is exited.

[0161] In one alternative implementation, if the player does not exit during the virtual object generation process, the adjustment process for the virtual object can be completed, and the effect of the adjustment can be displayed.

[0162] Specifically, the processing methods also include:

[0163] o1: In response to the effect display command, display the adjustment effect for the first adjustment command or the second adjustment command.

[0164] In optional embodiments, the adjustment effect of the first adjustment instruction or the second adjustment instruction includes the effect of the second or third image of the adjusted virtual object, as well as additional display effects to enhance the richness of the screen display and further improve the efficiency of human-computer interaction.

[0165] In one alternative implementation, after the player issues a first adjustment command or a second adjustment command, some special effects may be displayed and a second or third image of the virtual object may be shown.

[0166] For example, special effects may include highlighting parts of a virtual object that have been adjusted.

[0167] In one alternative implementation, players can issue a first adjustment command or a second adjustment command through the completion control in the smart adjustment interface. During the process of generating a second or third image through the first and second adjustment commands, the completion control is adjusted to a non-interactive state. At this time, the text prompt on the completion control is also changed from "Completed" to "Generating" to indicate to the player that the second or third image of the virtual object is currently being generated and the image generation process can no longer proceed.

[0168] In one alternative implementation, when adjusting the image of a virtual object using a first adjustment command or a second adjustment command, if a generation failure occurs, the player should be notified of the current generation failure by displaying a generation failure message and given the reason for the failure.

[0169] Specifically, the processing methods also include:

[0170] In response to the failure to generate a second or third image of a virtual object, display a generation failure message.

[0171] Optionally, in one implementation, after determining that a failure to generate a second or third image has occurred, image generation failure information is displayed, and the reason for the image display failure is shown in the image generation failure information.

[0172] For example, the image generation failure message could be "The current image generation failed due to network instability".

[0173] In one alternative implementation, if the generation fails due to network instability, the input first adjustment instruction or second adjustment instruction needs to be stored. After the network is stabilized, the corresponding second or third image of the virtual object is generated again according to the input first adjustment instruction or second adjustment instruction.

[0174] In one optional implementation, an upper limit is set for the number of adjustment commands that can be entered in each round. When the preset upper limit is exceeded, the player will be prompted that no more commands can be entered to ensure the processing efficiency of the backend server.

[0175] In one alternative implementation, the instruction input limit prompt message may be displayed as "The maximum number of input instructions has been reached. Please restart the editing process for the virtual object."

[0176] In one alternative implementation, after determining that the image of the virtual object has been adjusted by the first adjustment instruction and the second adjustment instruction, the virtual object can be further adjusted based on the third image of the virtual object according to the third adjustment instruction.

[0177] Specifically, the processing methods also include:

[0178] p1: In response to the third adjustment instruction for the third image of the virtual object, adjust the third image to obtain the fourth image; wherein the third adjustment instruction is an instruction generated based on the input text and / or input voice.

[0179] In optional embodiments, similarly, the third adjustment instruction can be an adjustment instruction of the same type as the first and second adjustment instructions. For example, both may be instructions for adjusting local information of a virtual object, but the two adjustment instructions may not be for the same part. Alternatively, it can be an adjustment instruction of a different type from the first and second adjustment instructions. For example, the first and second adjustment instructions are instructions for adjusting the overall style of a virtual object, while the third adjustment instruction is an adjustment instruction for a local part of the virtual object.

[0180] In one alternative implementation, to enhance the diversity of intelligent interaction, in addition to generating adjustment instructions through input text and input voice, adjustment instructions can also be generated based on input images.

[0181] Specifically, the first adjustment instruction, the second adjustment instruction, and the third adjustment instruction also include instructions generated based on the input image.

[0182] In an optional embodiment, an image input control may also be displayed in the instruction input area. Players can input images by triggering the image input control, and end the current image input process after stopping the triggering operation of the image input control.

[0183] In one alternative implementation, since voice input requires the cooperation of the terminal device's image acquisition device (such as a camera), if the current system does not support the activation of the image acquisition device or the current image acquisition device is not activated, it is necessary to respond to the trigger operation of the image input control and display an image acquisition device activation prompt. After confirming that the image acquisition device is activated, the process of acquiring the player's input image is completed, for example, by capturing the player's face as the input image through the camera on the image acquisition device.

[0184] The method of adjusting the virtual object through the third adjustment instruction is the same as the method of adjusting the virtual object through the first adjustment instruction and the second adjustment instruction, and will not be described again here.

[0185] In one alternative implementation, to enhance the diversity and richness of player adjustments to the virtual object's appearance, the virtual object's appearance can be manually adjusted according to the player's ideas before adjusting it via the first adjustment command, and then the virtual object can be further adjusted based on the manually adjusted virtual appearance.

[0186] Specifically, before the step of "responding to the first adjustment instruction for the first image of the virtual object and adjusting the first image to obtain the second image", the processing method also includes:

[0187] q1: In response to the fourth adjustment instruction for the fifth image of the virtual object, adjust the fifth image to obtain the first image; wherein, the fourth adjustment instruction is a manual selection adjustment instruction for the virtual object.

[0188] In an optional embodiment, manually adjusting a virtual object can be a process of adjusting the virtual object by modifying the parts and styles displayed in the object adjustment interface.

[0189] Specifically, the step "responding to the fourth adjustment instruction for the fifth image of the virtual object, adjusting the fifth image to obtain the first image" includes:

[0190] r1: Responds to the fourth adjustment command for the fifth image of the virtual object, and determines the target adjustment part of the selected virtual object and the corresponding target adjustment style.

[0191] r2: Based on the target adjustment part and target adjustment style, adjust the fifth image to obtain the first image.

[0192] In one alternative implementation, the object adjustment interface displays different object part selection controls. In response to the selection operation of the target part control, the part style corresponding to the target part control is displayed. By selecting different part styles, the part of the selected virtual object is determined, and the virtual object is adjusted.

[0193] For example, the object adjustment interface displays controls for the eye area, mouth area, and eyebrows. In response to a touch operation on the eye area control (the target adjustment area), the object adjustment interface displays eye areas of different styles and colors. In response to a selection operation on the green phoenix eye style (the target adjustment style), the virtual object's eye area is adjusted to green phoenix eyes, thereby obtaining the corresponding first image. The process of adjusting the first image is then performed again based on the adjustment instructions.

[0194] For example, please refer to Figure 2 , Figure 2 A flowchart for generating the object image provided for an optional embodiment, such as Figure 2 As shown, the process for generating a virtual object's image can be as follows: Entering the interactive image adjustment process, first determine whether to continue editing with the current image. If yes, directly output the adjustment-type text and modify the current image; if no, output the initial text description and generate a new image. During input, check if the number of adjustment rounds (i.e., the number of times the adjustment command is input) exceeds the upper limit. If no, continue outputting the adjustment-type text and modifying the current image; if yes, output a text prompt indicating that further adjustment is not possible. After adjustment, click "Use"; return to the object image editing interface; if confirmed, click the return control, call the original system interaction logic, and save the virtual object image; check if the "Complete" control is clicked. If yes, save the virtual object image; if no, continue editing parameters on the current virtual object image until the "Complete" control is clicked and the virtual object image is saved.

[0195] Furthermore, once the adjustment of the virtual object's appearance is complete, the player's adjusted virtual object can be saved through a save operation to store the saved virtual object.

[0196] In one alternative implementation, after determining that the image adjustment for the virtual object is complete, a save operation for the adjusted virtual object can be triggered by a touch operation on the control.

[0197] Specifically, after determining and issuing the save operation for the adjusted virtual object, a save prompt message is displayed in the intelligent adjustment interface, and different save prompt messages are displayed, including prompt labels such as "Continue editing", "Save and use" and "Save as new data".

[0198] If the player selects the "Continue Editing" prompt, they will return to the smart adjustment interface to continue editing the virtual object's appearance; if the player selects the "Save and Use" prompt, the new appearance of the adjusted virtual object will be used to overwrite the existing appearance of the virtual object and applied; if the player selects the "Save as New Data" prompt, the new appearance of the adjusted virtual object will be saved as new appearance data, and the existing appearance of the virtual object will not be overwritten and will still exist.

[0199] Optionally, if players edit the virtual object based on the system's default virtual object appearance, they can only choose "Save as new data" and cannot overwrite the existing virtual object appearance. The newly added appearance will be automatically installed and applied. If players edit and save the virtual object based on the virtual object appearance generated by manually selecting adjustment commands, they can choose "Save and use" or "Save as new data" and can choose whether to overwrite the existing virtual object appearance.

[0200] The following will illustrate the processing of virtual objects in the optional embodiments through specific examples, using virtual objects as virtual roles:

[0201] Please see Figure 3 , Figure 3 The schematic diagram of the object adjustment interface provided in the optional embodiment includes a virtual object 310 and a facial feature adjustment control 320. Players can adjust and edit the facial features of the virtual object 310 by touching the facial feature adjustment control 320. At the same time, the object adjustment interface 300 also includes a smart adjustment control 330, and players can enter the smart adjustment interface by touching the smart adjustment control 330.

[0202] For further details, please refer to Figure 4 , Figure 4 One of the schematic diagrams of the intelligent adjustment interface provided for an optional embodiment, such as Figure 4As shown, the intelligent adjustment interface 400 includes a virtual object 310, an instruction input area 410, and an instruction display area 420. The instruction input area 410 includes a text input sub-area 411 and a voice input control 412. Text can be input through the text input sub-area 411, and voice can be input through the voice input control 412. After inputting voice and / or text, the input adjustment instruction can be displayed in the instruction display area 420 through the send control 430.

[0203] For further details, please refer to Figure 5 , Figure 5 The second schematic diagram of the intelligent adjustment interface provided for an optional embodiment, as shown below. Figure 5 As shown, the instruction input area 410 also includes at least one adjustment example label 414. By selecting any adjustment example label 414, an adjustment instruction for the virtual object can be directly issued. At the same time, the instruction input area 410 also includes a refresh control 415. By touching the refresh control 415, at least one adjustment example label 414 can be updated.

[0204] For further details, please refer to Figure 6 , Figure 6 The third schematic diagram of the intelligent adjustment interface provided for an optional embodiment, as shown below. Figure 6 As shown, after the input adjustment command is displayed in the command display area 420 via the send control, multiple adjustment commands are displayed in the command display area 420. A regeneration control 421 is displayed before the first adjustment command, allowing the player to regenerate the virtual object's image by touching the regeneration control 421. A rollback control 422 is displayed before all other adjustment commands except the first one, allowing the player to undo the current adjustment command's changes to the virtual object's image by touching the rollback control 422. Simultaneously, the command display area 420 also includes an effect display control (view effect) 423, which displays the effect on the virtual object's image by triggering the effect display control (view effect) 423.

[0205] For further details, please refer to Figure 7 , Figure 7 The fourth schematic diagram of the intelligent adjustment interface provided for an optional embodiment, as shown below. Figure 7 As shown, the intelligent adjustment interface 400 also includes a completion control 440. After a touch operation is performed on the completion control 440, the text display of the completion control 440 changes to "Generating", to prompt the player that a new image of a virtual object is being generated.

[0206] For further details, please refer to Figure 8 , Figure 8 An illustration of an exit prompt message provided for an optional embodiment, such as... Figure 8 As shown, during the virtual object's image generation process, upon receiving an adjustment / exit operation, an exit prompt message is displayed, along with the text "Current image is being generated; exiting will not save the changes. Do you wish to continue generating?" Simultaneously, "Abandon" and "Continue Generating" selection controls are displayed. If the player selects the "Abandon" control, the current image editing is abandoned; if the player selects the "Continue Generating" control, the current image editing continues.

[0207] For further details, please refer to Figure 9 , Figure 9 The illustration shows a save prompt message provided for an optional embodiment, such as... Figure 9 As shown, after the save operation for the adjusted virtual object is initiated, a save prompt message is displayed in the intelligent adjustment interface, and the exit prompt message displays the text "Save current image?" and different save prompt selection controls including "Continue editing", "Save and use" and "Save as new data" to allow players to choose different save methods.

[0208] An optional embodiment provides a method for processing virtual objects, which, in response to a first adjustment instruction for a first image of the virtual object, adjusts the first image to obtain a second image; wherein the first adjustment instruction is an instruction generated based on input text and / or input voice; and, in response to a second adjustment instruction for the second image of the virtual object, adjusts the second image to obtain a third image; wherein the second adjustment instruction is an instruction generated based on input text and / or input voice. In this way, different first and second adjustment instructions can be input multiple times, and the image of the virtual object can be interactively updated and adjusted through the first and second adjustment instructions, which helps to improve the accuracy of image adjustment for virtual objects and the efficiency of human-computer interaction.

[0209] Based on the same inventive concept, optional embodiments also provide a virtual object processing device corresponding to the virtual object processing method. Since the principle of the device in the optional embodiments for solving the problem is similar to the virtual object processing method described above in the optional embodiments, the implementation of the device can refer to the implementation of the method, and repeated parts will not be described again.

[0210] Please see Figure 10 , Figure 10 This is a schematic diagram of the structure of a virtual object processing apparatus provided for an optional embodiment. For example... Figure 10 As shown, the processing device 1000 includes:

[0211] The first image adjustment module 1010 is used to respond to a first adjustment instruction for a first image of a virtual object and adjust the first image to obtain a second image; wherein, the first adjustment instruction is an instruction generated based on input text and / or input voice.

[0212] The second image adjustment module 1020 is used to respond to a second adjustment instruction for a second image of a virtual object and adjust the second image to obtain a third image; wherein the second adjustment instruction is an instruction generated based on input text and / or input voice.

[0213] In an optional implementation, when the first image adjustment module 1010 adjusts the first image to obtain a second image in response to a first adjustment instruction for a first image of a virtual object, the first image adjustment module 1010 is used to:

[0214] In response to a first adjustment instruction for a first image of a virtual object, parse the first local adjustment information contained in the first adjustment instruction;

[0215] The second image is obtained by adjusting the first image based on the first partial adjustment information.

[0216] In an optional implementation, when the first image adjustment module 1010 adjusts the first image to obtain a second image in response to a first adjustment instruction for a first image of a virtual object, the first image adjustment module 1010 is used to:

[0217] In response to a first adjustment instruction for a first image of a virtual object, a second image is obtained by adjusting the first image according to the first adjustment instruction using artificial intelligence.

[0218] In one optional implementation, when the first image adjustment module 1010 is used to adjust the first image according to the first adjustment instruction using artificial intelligence to obtain the second image, the first image adjustment module 1010 is used to:

[0219] The second image is obtained by making partial adjustments to the first image based on the first adjustment instruction using artificial intelligence.

[0220] In an optional embodiment, the processing device 1000 further includes a third image adjustment module (not shown in the figure), the third image adjustment module being used for:

[0221] In response to a third adjustment instruction for a third image of a virtual object, the third image is adjusted to obtain a fourth image; wherein the third adjustment instruction is an instruction generated based on input text and / or input voice.

[0222] In an optional embodiment, the processing device 1000 further includes a fourth image adjustment module (not shown in the figure), the fourth image adjustment module being used for:

[0223] In response to the fourth adjustment instruction for the fifth image of the virtual object, the fifth image is adjusted to obtain the first image; wherein, the fourth adjustment instruction is a manual selection adjustment instruction for the virtual object.

[0224] In one optional implementation, when the fourth image adjustment module adjusts the fifth image to obtain the first image in response to a fourth adjustment instruction for the fifth image of the virtual object, the fourth image adjustment module is used to:

[0225] In response to the fourth adjustment command for the fifth image of the virtual object, determine the target adjustment part of the selected virtual object and the corresponding target adjustment style;

[0226] Based on the target adjustment parts and the target adjustment style, the fifth image is adjusted to obtain the first image.

[0227] In one alternative implementation, the first adjustment instruction, the second adjustment instruction, and the third adjustment instruction further include instructions generated based on the input image.

[0228] In an optional embodiment, the processing device 1000 further includes an image readjustment module (not shown in the figure), the image readjustment module being used for:

[0229] In response to the regeneration instruction for the second image of the virtual object, the first image is adjusted based on the first adjustment instruction to obtain the sixth image; wherein the virtual object of the sixth image has the same style as the virtual object of the second image, but the local details of the object are different.

[0230] In an optional embodiment, the processing device 1000 further includes a rollback adjustment module (not shown in the figure), the rollback adjustment module being used for:

[0231] In response to the rollback operation for the second adjustment command, the second image of the virtual object is adjusted back to the first image;

[0232] In response to the rollback operation for the second adjustment instruction, the image of the virtual object is rolled back to the image corresponding to the second adjustment instruction.

[0233] In an optional embodiment, the processing device 1000 further includes a label image adjustment module (not shown in the figure), which is used for:

[0234] Show at least one example of an adjustment label;

[0235] In response to a selection operation of a target example label in at least one adjustment example label, the first image of the virtual object is adjusted to obtain the seventh image.

[0236] In an optional implementation, when the label image adjustment module adjusts the first image of a virtual object to obtain a seventh image in response to a selection operation for a target example label in at least one adjustment example label, the label image adjustment module is configured to:

[0237] In response to a selection operation on a target example label in at least one adjustment example label, the second local adjustment information contained in the target example label is parsed.

[0238] The seventh image is obtained by adjusting the first image based on the second part of the adjustment information.

[0239] In an optional implementation, when the label image adjustment module adjusts the first image of a virtual object to obtain a seventh image in response to a selection operation for a target example label in at least one adjustment example label, the label image adjustment module is configured to:

[0240] In response to a selection operation of a target example label in at least one adjustment example label, the first image is adjusted using artificial intelligence based on the target example label to obtain the seventh image.

[0241] In an optional embodiment, the processing device 1000 further includes a tag updating module (not shown in the figure), the tag updating module being used for:

[0242] In response to a selection operation or an update operation for at least one adjustment example label, display the updated at least one adjustment example label.

[0243] In an optional embodiment, the processing device 1000 further includes an adjustment effect display module (not shown in the figure), which is used for:

[0244] In response to the effect display command, display the adjustment effect for the first adjustment command or the second adjustment command.

[0245] In an optional embodiment, the processing device 1000 further includes an input upper limit prompting module (not shown in the figure), the input upper limit prompting module being used for:

[0246] Determine the number of input information in the first adjustment instruction or the second adjustment instruction;

[0247] When the number of input messages reaches a preset threshold, a message indicating the maximum input limit is displayed.

[0248] In an optional embodiment, the processing device 1000 further includes an exit prompt module (not shown in the figure), the exit prompt module being used for:

[0249] During the process of adjusting and generating a second or third image, respond to the adjustment exit operation and display an exit prompt message;

[0250] In response to the exit option in the exit prompt message, stop generating a second or third image.

[0251] In an optional embodiment, the processing device 1000 further includes a recovery adjustment module (not shown in the figure), which is used for:

[0252] In response to the restore and adjustment command for the virtual object, the image of the virtual object is adjusted to obtain the eighth image; wherein, the eighth image is the image of the virtual object before the adjustment; the restore and adjustment command is a command generated based on the input text and / or input voice.

[0253] In an optional embodiment, the processing device 1000 further includes an instruction display module (not shown in the figure), which is used for:

[0254] The input text and / or input speech included in the first or second adjustment instruction will be displayed in text form in the order of input.

[0255] The optional embodiment provides a virtual object processing device that, in response to a first adjustment instruction for a first image of a virtual object, adjusts the first image to obtain a second image; wherein the first adjustment instruction is an instruction generated based on input text and / or input voice; and in response to a second adjustment instruction for the second image of the virtual object, adjusts the second image to obtain a third image; wherein the second adjustment instruction is an instruction generated based on input text and / or input voice. In this way, different first and second adjustment instructions can be input multiple times, and the image of the virtual object can be interactively updated and adjusted through the first and second adjustment instructions, which helps to improve the accuracy of image adjustment for virtual objects and the efficiency of human-computer interaction.

[0256] Please see Figure 11 , Figure 11 This is a schematic diagram of the structure of an electronic device provided as an optional embodiment. (See diagram below.) Figure 11 As shown, the electronic device 1100 includes a processor 1110, a memory 1120, and a bus 1130.

[0257] Memory 1120 stores machine-readable instructions executable by processor 1110. When electronic device 1100 is running, processor 1110 communicates with memory 1120 via bus 1130, causing processor 1110 to execute the following instructions during operation:

[0258] In response to a first adjustment instruction for a first image of a virtual object, the first image is adjusted to obtain a second image; wherein the first adjustment instruction is an instruction generated based on input text and / or input voice.

[0259] In response to a second adjustment instruction for a second image of a virtual object, the second image is adjusted to obtain a third image; wherein the second adjustment instruction is an instruction generated based on input text and / or input speech.

[0260] In one optional implementation, the instructions executed by the processor 1110, in response to a first adjustment instruction for a first image of a virtual object, adjust the first image to obtain a second image, including:

[0261] In response to a first adjustment instruction for a first image of a virtual object, parse the first local adjustment information contained in the first adjustment instruction;

[0262] The second image is obtained by adjusting the first image based on the first partial adjustment information.

[0263] In one optional implementation, the instructions executed by the processor 1110, in response to a first adjustment instruction for a first image of a virtual object, adjust the first image to obtain a second image, including:

[0264] In response to a first adjustment instruction for a first image of a virtual object, a second image is obtained by adjusting the first image according to the first adjustment instruction using artificial intelligence.

[0265] In one optional implementation, the instructions executed by the processor 1110 include adjusting the first image according to the first adjustment instruction using artificial intelligence to obtain the second image, including:

[0266] The second image is obtained by making partial adjustments to the first image based on the first adjustment instruction using artificial intelligence.

[0267] In an optional implementation, the instructions executed by the processor 1110 further include:

[0268] In response to a third adjustment instruction for a third image of a virtual object, the third image is adjusted to obtain a fourth image; wherein the third adjustment instruction is an instruction generated based on input text and / or input voice.

[0269] In an optional implementation, the instructions executed by the processor 1110 further include:

[0270] In response to the fourth adjustment instruction for the fifth image of the virtual object, the fifth image is adjusted to obtain the first image; wherein, the fourth adjustment instruction is a manual selection adjustment instruction for the simulated object.

[0271] In one optional implementation, the instructions executed by the processor 1110, in response to a fourth adjustment instruction for a fifth image of a virtual object, adjust the fifth image to obtain a first image, including:

[0272] In response to the fourth adjustment command for the fifth image of the virtual object, determine the target adjustment part of the selected virtual object and the corresponding target adjustment style;

[0273] Based on the target adjustment parts and the target adjustment style, the fifth image is adjusted to obtain the first image.

[0274] In one alternative implementation, the first adjustment instruction, the second adjustment instruction, and the third adjustment instruction further include instructions generated based on the input image.

[0275] In an optional implementation, the instructions executed by the processor 1110 further include:

[0276] In response to the regeneration instruction for the second image of the virtual object, the first image is adjusted based on the first adjustment instruction to obtain the sixth image; wherein the virtual object of the sixth image has the same style as the virtual object of the second image, but the local details of the object are different.

[0277] In an optional implementation, the instructions executed by the processor 1110 further include:

[0278] In response to the rollback operation for the second adjustment command, the second image of the virtual object is adjusted back to the first image;

[0279] In response to the rollback operation for the second adjustment instruction, the image of the virtual object is rolled back to the image corresponding to the second adjustment instruction.

[0280] In an optional implementation, the instructions executed by the processor 1110 further include:

[0281] Show at least one example of an adjustment label;

[0282] In response to a selection operation of a target example label in at least one adjustment example label, the first image of the virtual object is adjusted to obtain the seventh image.

[0283] In one optional implementation, the instructions executed by the processor 1110, in response to a selection operation for at least one target example label in the adjustment example label, adjust the first image of the virtual object to obtain a seventh image, including:

[0284] In response to a selection operation on a target example label in at least one adjustment example label, the second local adjustment information contained in the target example label is parsed.

[0285] The seventh image is obtained by adjusting the first image based on the second part of the adjustment information.

[0286] In one optional implementation, the instructions executed by the processor 1110, in response to a selection operation for at least one target example label in the adjustment example label, adjust the first image of the virtual object to obtain a seventh image, including:

[0287] In response to a selection operation of a target example label in at least one adjustment example label, the first image is adjusted using artificial intelligence based on the target example label to obtain the seventh image.

[0288] In an optional implementation, the instructions executed by the processor 1110 further include:

[0289] In response to a selection operation or an update operation for at least one adjustment example label, display the updated at least one adjustment example label.

[0290] In an optional implementation, the instructions executed by the processor 1110 further include:

[0291] In response to the effect display command, display the adjustment effect for the first adjustment command or the second adjustment command.

[0292] In an optional implementation, the instructions executed by the processor 1110 further include:

[0293] Determine the number of input information in the first adjustment instruction or the second adjustment instruction;

[0294] When the number of input messages reaches a preset threshold, a message indicating the maximum input limit is displayed.

[0295] In an optional implementation, the instructions executed by the processor 1110 further include:

[0296] During the process of adjusting and generating a second or third image, respond to the adjustment exit operation and display an exit prompt message;

[0297] In response to the exit option in the exit prompt message, stop generating a second or third image.

[0298] In an optional implementation, the instructions executed by the processor 1110 further include:

[0299] In response to the restore and adjustment command for the virtual object, the image of the virtual object is adjusted to obtain the eighth image; wherein, the eighth image is the image of the virtual object before the adjustment; the restore and adjustment command is a command generated based on the input text and / or input voice.

[0300] In an optional implementation, the instructions executed by the processor 1110 further include:

[0301] The input text and / or input speech included in the first or second adjustment instruction will be displayed in text form in the order of input.

[0302] By using the above method, different first and second adjustment commands can be entered multiple times. Through the first and second adjustment commands, the image of the virtual object can be updated and adjusted interactively, which helps to improve the accuracy of the image adjustment of the virtual object and the efficiency of human-computer interaction.

[0303] An optional embodiment also provides a computer-readable storage medium storing a computer program, such that the computer program, when executed by a processor, performs the following instructions:

[0304] In response to a first adjustment instruction for a first image of a virtual object, the first image is adjusted to obtain a second image; wherein the first adjustment instruction is an instruction generated based on input text and / or input voice.

[0305] In response to a second adjustment instruction for a second image of a virtual object, the second image is adjusted to obtain a third image; wherein the second adjustment instruction is an instruction generated based on input text and / or input speech.

[0306] In one optional implementation, the instructions executed by the computer-readable storage medium, in response to a first adjustment instruction for a first image of a virtual object, adjust the first image to obtain a second image, including:

[0307] In response to a first adjustment instruction for a first image of a virtual object, parse the first local adjustment information contained in the first adjustment instruction;

[0308] The second image is obtained by adjusting the first image based on the first partial adjustment information.

[0309] In one optional implementation, the instructions executed by the computer-readable storage medium, in response to a first adjustment instruction for a first image of a virtual object, adjust the first image to obtain a second image, including:

[0310] In response to a first adjustment instruction for a first image of a virtual object, a second image is obtained by adjusting the first image according to the first adjustment instruction using artificial intelligence.

[0311] In one optional implementation, the instructions executed by the computer-readable storage medium include adjusting the first image to obtain the second image using artificial intelligence according to a first adjustment instruction, comprising:

[0312] The second image is obtained by making partial adjustments to the first image based on the first adjustment instruction using artificial intelligence.

[0313] In one optional implementation, the instructions executed by the computer-readable storage medium further include:

[0314] In response to a third adjustment instruction for a third image of a virtual object, the third image is adjusted to obtain a fourth image; wherein the third adjustment instruction is an instruction generated based on input text and / or input voice.

[0315] In one optional implementation, the instructions executed by the computer-readable storage medium further include:

[0316] In response to the fourth adjustment instruction for the fifth image of the virtual object, the fifth image is adjusted to obtain the first image; wherein, the fourth adjustment instruction is a manual selection adjustment instruction for the simulated object.

[0317] In one optional implementation, the instructions executed by the computer-readable storage medium, in response to a fourth adjustment instruction for a fifth image of a virtual object, adjust the fifth image to obtain a first image, including:

[0318] In response to the fourth adjustment command for the fifth image of the virtual object, determine the target adjustment part of the selected virtual object and the corresponding target adjustment style;

[0319] Based on the target adjustment parts and the target adjustment style, the fifth image is adjusted to obtain the first image.

[0320] In one alternative implementation, the first adjustment instruction, the second adjustment instruction, and the third adjustment instruction further include instructions generated based on the input image.

[0321] In one optional implementation, the instructions executed by the computer-readable storage medium further include:

[0322] In response to the regeneration instruction for the second image of the virtual object, the first image is adjusted based on the first adjustment instruction to obtain the sixth image; wherein the virtual object of the sixth image has the same style as the virtual object of the second image, but the local details of the object are different.

[0323] In one optional implementation, the instructions executed by the computer-readable storage medium further include:

[0324] In response to the rollback operation for the second adjustment command, the second image of the virtual object is adjusted back to the first image;

[0325] In response to the rollback operation for the second adjustment instruction, the image of the virtual object is rolled back to the image corresponding to the second adjustment instruction.

[0326] In one optional implementation, the instructions executed by the computer-readable storage medium further include:

[0327] Show at least one example of an adjustment label;

[0328] In response to a selection operation of a target example label in at least one adjustment example label, the first image of the virtual object is adjusted to obtain the seventh image.

[0329] In one alternative implementation, the instructions executed by the computer-readable storage medium, in response to a selection operation for at least one target example label in the adjustment example label, adjust a first image of a virtual object to obtain a seventh image, including:

[0330] In response to a selection operation on a target example label in at least one adjustment example label, the second local adjustment information contained in the target example label is parsed.

[0331] The seventh image is obtained by adjusting the first image based on the second part of the adjustment information.

[0332] In one alternative implementation, the instructions executed by the computer-readable storage medium, in response to a selection operation for at least one target example label in the adjustment example label, adjust a first image of a virtual object to obtain a seventh image, including:

[0333] In response to a selection operation of a target example label in at least one adjustment example label, the first image is adjusted using artificial intelligence based on the target example label to obtain the seventh image.

[0334] In one optional implementation, the instructions executed by the computer-readable storage medium further include:

[0335] In response to a selection operation or an update operation for at least one adjustment example label, display the updated at least one adjustment example label.

[0336] In one optional implementation, the instructions executed by the computer-readable storage medium further include:

[0337] In response to the effect display command, display the adjustment effect for the first adjustment command or the second adjustment command.

[0338] In one optional implementation, the instructions executed by the computer-readable storage medium further include:

[0339] Determine the number of input information in the first adjustment instruction or the second adjustment instruction;

[0340] When the number of input messages reaches a preset threshold, a message indicating the maximum input limit is displayed.

[0341] In one optional implementation, the instructions executed by the computer-readable storage medium further include:

[0342] During the process of adjusting and generating a second or third image, respond to the adjustment exit operation and display an exit prompt message;

[0343] In response to the exit option in the exit prompt message, stop generating a second or third image.

[0344] In one optional implementation, the instructions executed by the computer-readable storage medium further include:

[0345] In response to the restore and adjustment command for the virtual object, the image of the virtual object is adjusted to obtain the eighth image; wherein, the eighth image is the image of the virtual object before the adjustment; the restore and adjustment command is a command generated based on the input text and / or input voice.

[0346] In one optional implementation, the instructions executed by the computer-readable storage medium further include:

[0347] The input text and / or input speech included in the first or second adjustment instruction will be displayed in text form in the order of input.

[0348] By using the above method, different first and second adjustment commands can be entered multiple times. Through the first and second adjustment commands, the image of the virtual object can be updated and adjusted interactively, which helps to improve the accuracy of the image adjustment of the virtual object and the efficiency of human-computer interaction.

[0349] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0350] In the several embodiments provided in this disclosure, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. The apparatus embodiments described above are merely illustrative; for example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. Furthermore, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Additionally, the coupling or direct coupling or communication connection shown or discussed may be through some communication interface; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0351] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0352] In addition, the functional units in the various embodiments of this disclosure can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0353] If the functionality is implemented as a software functional unit and sold or used as an independent product, it can be stored in a processor-executable, non-volatile, computer-readable storage medium. Based on this understanding, the technical solution of this disclosure, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this disclosure. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0354] Finally, it should be noted that the above embodiments are merely specific implementations of this disclosure, used to illustrate the technical solutions of this disclosure, and not to limit it. The protection scope of this disclosure is not limited thereto. Although this disclosure has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments, or make equivalent substitutions for some of the technical features, within the scope of the technology disclosed in this disclosure. Such modifications, changes, or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the optional embodiment technical solutions, and should all be covered within the protection scope of this disclosure. Therefore, the protection scope of this disclosure should be determined by the protection scope of the claims.

Claims

1. A method for processing virtual objects, characterized in that, The processing method includes: In response to a first adjustment instruction for a first image of a virtual object, the first image is adjusted to obtain a second image; wherein the first adjustment instruction is an instruction generated based on input text and / or input voice. In response to a second adjustment instruction for a second image of a virtual object, the second image is adjusted to obtain a third image; wherein the second adjustment instruction is an instruction generated based on input text and / or input speech.

2. The processing method according to claim 1, characterized in that, The response to a first adjustment instruction for a first image of a virtual object, adjusting the first image to obtain a second image, includes: In response to a first adjustment instruction for a first image of a virtual object, the first partial adjustment information contained in the first adjustment instruction is parsed. The first image is adjusted based on the first local adjustment information to obtain the second image.

3. The processing method according to claim 1, characterized in that, The response to a first adjustment instruction for a first image of a virtual object, adjusting the first image to obtain a second image, includes: In response to a first adjustment instruction for a first image of a virtual object, a second image is obtained by adjusting the first image according to the first adjustment instruction using artificial intelligence.

4. The processing method according to claim 3, characterized in that, The process of adjusting the first image using artificial intelligence according to the first adjustment instruction to obtain the second image includes: The second image is obtained by making partial adjustments to the first image based on the first adjustment instruction using artificial intelligence.

5. The processing method according to claim 1, characterized in that, The processing method further includes: In response to a third adjustment instruction for a third image of a virtual object, the third image is adjusted to obtain a fourth image; wherein the third adjustment instruction is an instruction generated based on input text and / or input speech.

6. The processing method according to claim 1, characterized in that, Before adjusting the first image to obtain the second image in response to a first adjustment instruction for a first image of a virtual object, the processing method further includes: In response to a fourth adjustment instruction for a fifth image of the virtual object, the fifth image is adjusted to obtain a first image; wherein the fourth adjustment instruction is a manual selection adjustment instruction for the virtual object.

7. The processing method according to claim 6, characterized in that, The response to the fourth adjustment instruction for the fifth image of the virtual object, adjusting the fifth image to obtain the first image, includes: In response to the fourth adjustment command for the fifth image of the virtual object, the target adjustment part of the selected virtual object and the corresponding target adjustment style are determined; Based on the target adjustment area and the target adjustment style, the fifth image is adjusted to obtain the first image.

8. The processing method according to claim 5, characterized in that, The first adjustment instruction, the second adjustment instruction, and the third adjustment instruction also include instructions generated based on the input image.

9. The processing method according to claim 1, characterized in that, The processing method further includes: In response to a regeneration instruction for the second image of the virtual object, the first image is adjusted based on the first adjustment instruction to obtain a sixth image; wherein the virtual object of the sixth image has the same style as the virtual object of the second image, but the local details of the object are different.

10. The processing method according to claim 1, characterized in that, The processing method further includes: In response to the rollback operation for the second adjustment command, the second image of the virtual object is adjusted back to the first image; or, In response to the rollback operation for the second adjustment instruction, the image of the virtual object is rolled back to the image corresponding to the second adjustment instruction.

11. The processing method according to claim 1, characterized in that, The processing method further includes: Show at least one example of an adjustment label; In response to a selection operation for at least one of the target example tags in the adjustment example tags, the first image of the virtual object is adjusted to obtain a seventh image.

12. The processing method according to claim 11, characterized in that, The response is in response to at least one of the selected target example tags in the adjusted example tags, adjusting the first image of the virtual object to obtain the seventh image, including: In response to a selection operation for a target example label in at least one of the adjusted example labels, the second local adjustment information contained in the target example label is parsed. The first image is adjusted according to the second partial adjustment information to obtain the seventh image.

13. The processing method according to claim 11, characterized in that, The response is in response to at least one of the selected target example tags in the adjusted example tags, adjusting the first image of the virtual object to obtain the seventh image, including: In response to a selection operation of a target example tag in at least one of the adjusted example tags, the first image is adjusted using artificial intelligence based on the target example tag to obtain a seventh image.

14. The processing method according to claim 11, characterized in that, The processing method further includes: In response to a selection operation or an update operation for the at least one adjustment example label, the updated at least one adjustment example label is displayed.

15. The processing method according to claim 1, characterized in that, The processing method further includes: In response to the effect display command, display the adjustment effect for the first adjustment command or the second adjustment command.

16. The processing method according to claim 1, characterized in that, The processing method further includes: Determine the number of input information in the first adjustment instruction or the second adjustment instruction; When the number of input messages reaches a preset threshold, a message indicating the upper limit of input messages is displayed.

17. The processing method according to claim 1, characterized in that, The processing method further includes: During the process of adjusting and generating the second or third image, respond to the adjustment exit operation and display an exit prompt message; In response to the exit selection operation in the exit prompt message, the generation of the second image or the third image is stopped.

18. The processing method according to claim 1, characterized in that, The processing method further includes: In response to a restore / adjust command for the virtual object, the image of the virtual object is adjusted to obtain an eighth image; wherein, the eighth image is the image of the virtual object before the adjustment; the restore / adjust command is a command generated based on input text and / or input voice.

19. The processing method according to claim 1, characterized in that, The processing method further includes: The input text and / or input speech included in the first adjustment instruction or the second adjustment instruction are displayed in text form in the order of input.

20. A processing apparatus for virtual objects, characterized in that, The processing device includes: The first image adjustment module is used to respond to a first adjustment instruction for a first image of a virtual object and adjust the first image to obtain a second image; wherein the first adjustment instruction is an instruction generated based on input text and / or input voice. The second image adjustment module is used to respond to a second adjustment instruction for a second image of a virtual object and adjust the second image to obtain a third image; wherein the second adjustment instruction is an instruction generated based on input text and / or input voice.

21. An electronic device, characterized in that, include: The device includes a processor, a storage medium, and a bus, wherein the storage medium stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor communicates with the storage medium via the bus, and the processor executes the machine-readable instructions to perform the steps of the virtual object processing method as described in any one of claims 1 to 19.

22. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, performs the steps of the virtual object processing method as described in any one of claims 1 to 19.

Images