Picture editing method and device and electronic equipment

Abstract

The invention discloses a picture editing method and device, electronic equipment and a computer readable storage medium, and the method comprises the steps: determining a plurality of local to-be-adjusted regions of an initial picture; in response to first editing operations respectively performed on the plurality of local to-be-adjusted areas, receiving adjustment description information input by each first editing operation; and in response to the picture editing instruction, submitting adjustment information for the initial picture to enable the agent model to generate a target picture based on the adjustment information and the initial picture, the adjustment information including region information of the local to-be-adjusted region and adjustment description information. Therefore, according to the picture editing method provided by the embodiment of the invention, multiple editing operations can be carried out on multiple local areas of one picture at a time, efficient and rapid editing is realized, and the requirement of a user for rapid picture output is met.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a method, device, electronic device and computer-readable storage medium for editing pictures. Background Art

[0002] With the continuous development of computer technology, automatic image generation technology has made significant progress. Among them, text-generated image technology has received widespread attention. As an emerging AI (artificial intelligence) application, this technology allows users to input text descriptions to generate corresponding images.

[0003] However, the current text-to-image technology can only accept one text input to generate an image at a time, which means that if the user wants to modify the initially generated image multiple times, they need to repeatedly input the modified content multiple times and modify the image one by one, which cannot meet the user's needs for fast image generation. Therefore, how to efficiently and quickly edit AI-generated images has become an urgent problem to be solved. Summary of the invention

[0004] The present application provides a method, device, electronic device and computer-readable storage medium for editing pictures, which can perform multiple editing operations on multiple local areas of a picture at one time, realize efficient and fast editing, and meet the user's needs for fast picture output. The specific scheme is as follows:

[0005] In a first aspect, an embodiment of the present application provides a method for editing a picture, the method comprising:

[0006] Determine multiple local areas of the initial image to be adjusted;

[0007] In response to first editing operations respectively performed on the plurality of local areas to be adjusted, receiving adjustment description information input by each of the first editing operations;

[0008] In response to the picture editing instruction, adjustment information for the initial picture is submitted so that the intelligent model generates a target picture based on the adjustment information and the initial picture, wherein the adjustment information includes the area information of the local area to be adjusted and the adjustment description information.

[0009] In a second aspect, an embodiment of the present application provides a device for editing a picture, the device comprising:

[0010] A determination unit, used to determine a plurality of local areas to be adjusted of the initial image;

[0011] a receiving unit, configured to receive adjustment description information inputted by each of the first editing operations respectively performed on the plurality of local areas to be adjusted;

[0012] A submission unit is used to respond to the picture editing instruction and submit adjustment information for the initial picture so that the intelligent model generates a target picture based on the adjustment information and the initial picture, wherein the adjustment information includes the area information of the local area to be adjusted and the adjustment description information.

[0013] In a third aspect, the present application further provides an electronic device, including:

[0014] Processor; and

[0015] The memory is used to store a data processing program. After the electronic device is powered on and the program is run by the processor, the method described in the first aspect is executed.

[0016] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium storing a data processing program, which is executed by a processor to perform the method described in the first aspect.

[0017] Compared with the prior art, this application has the following advantages:

[0018] The method for editing a picture provided by the embodiment of the present application includes: determining multiple local areas to be adjusted of an initial picture; in response to the first editing operations respectively performed on the multiple local areas to be adjusted, receiving the adjustment description information input by each of the first editing operations; in response to the picture editing instruction, submitting the adjustment information for the initial picture, so that the intelligent agent model generates a target picture based on the adjustment information and the initial picture, wherein the adjustment information includes the area information of the local areas to be adjusted and the adjustment description information. It can be seen that in the method for editing a picture provided by the embodiment of the present application, for the initial picture, first, multiple local areas to be adjusted are determined, so as to determine the local areas to be adjusted in the initial picture, and then, by performing the first editing operation on each local area to be adjusted, respectively, the adjustment description information is input for each local area to be adjusted. Afterwards, in response to the picture editing instruction, the adjustment information containing the area information of each local area to be adjusted and the corresponding adjustment description information can be submitted to control the intelligent agent model to perform the editing operation indicated by the corresponding adjustment description information on multiple local areas to be adjusted of the initial picture at one time. Therefore, the method for editing pictures provided in the present application can perform multiple editing operations on multiple local areas of a picture at one time, achieve efficient and fast editing, and meet the user's needs for fast picture output. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 It is a schematic diagram of generating and modifying pictures in the Chinese picture generation software in the prior art;

[0020] Figure 2is a flowchart of a method for editing a picture provided by an embodiment of the present application;

[0021] Figure 3 It is a schematic diagram of an example of switching from a chat interface to an editing interface in the method for editing a picture provided in an embodiment of the present application;

[0022] Figure 4 It is a schematic diagram of an example of inputting adjustment description information for a local area to be adjusted in the method for editing a picture provided by an embodiment of the present application;

[0023] Figure 5 is a schematic diagram of an example of inputting adjustment description information for another local area to be adjusted in the method for editing a picture provided by an embodiment of the present application;

[0024] Figure 6 It is a schematic diagram of an example in which the second input area in the method for editing a picture provided by an embodiment of the present application displays content to be sent including adjustment information;

[0025] Figure 7 is a structural block diagram of an example of a device for editing a picture provided in an embodiment of the present application;

[0026] Figure 8 It is a structural block diagram of an example of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0027] Many specific details are described in the following description to facilitate a full understanding of the present application. However, the present application can be implemented in many other ways than those described herein, and those skilled in the art can make similar generalizations without violating the connotation of the present application, so the present application is not limited by the specific implementation disclosed below.

[0028] It should be noted that the terms "first", "second", "third", etc. in the claims, description and drawings of the present application are used to distinguish similar objects and are not used to describe a specific order or sequence. The data used in this way are interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "including", "having" and their variants are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0029] It should be understood that in the embodiments of the present application, "at least one" refers to one or more, and "more than one" refers to two or more. "And / or" is merely a way to describe the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the previous and subsequent associated objects are in an "or" relationship. "Including A, B and / or C" means including any one, any two, or any three of A, B, and C.

[0030] It should be understood that in the embodiments of the present application, "B corresponding to A", "B corresponding to A", "A corresponds to B", or "B corresponds to A" means that B is associated with A, and B can be determined according to A. Determining B according to A does not mean determining B only according to A, and B can also be determined according to A and / or other information.

[0031] It should be noted that the instructions or operations that appear in the subsequent detailed introduction of the method for editing pictures provided in the embodiment of the present application can all be regarded as instructions or operations triggered by the player through fingers or controlling a mouse, keyboard, stylus, or voice. The specific triggering operation can be determined according to the type of electronic device. For example, when the electronic device is a touch screen device such as a mobile phone or a tablet computer, the player can trigger instructions or operations on the touch screen through any suitable object or accessory such as a finger or stylus, or through voice. When the terminal device is a non-touch screen terminal device such as a desktop computer or a laptop computer, the player can trigger instructions or operations through external devices such as a mouse and keyboard.

[0032] Before describing the embodiments of the present application in detail, Figure 1 The prior art is further described.

[0033] like Figure 1 As shown, it is a schematic diagram of generating and modifying pictures in the prior art Chinese image generation software. First, the user inputs a description text 10 "draw a person running on the beach", and AI generates a corresponding picture 11. Then, the user inputs a modification instruction 12 "add a house", and AI can modify the picture 11 based on the modification instruction 12. When the user has other modification requirements, he can input another modification instruction again.

[0034] It can be seen that in the prior art, if the user wants to modify the initially generated image multiple times, it is necessary to repeatedly input the modification instructions multiple times, which has a high operation cost and cannot meet the user's demand for fast image output.

[0035] Based on the above reasons, in order to be able to edit AI-generated pictures efficiently and quickly, reduce operating costs, and meet users' needs for quick picture output, the first embodiment of the present application provides a method for editing pictures. The method is applied to electronic devices, which can be desktop computers, laptops, mobile phones, tablet computers, electronic watches, etc., or other electronic devices capable of picture editing, which are not specifically limited in the embodiments of the present application.

[0036] It should be noted that in the embodiment of the present application, the execution subject of the method for editing pictures can be a terminal device or a server, and the embodiment of the present application does not limit the type of the execution subject.

[0037] The technical solution of the present application is described in detail below through specific embodiments. It should be noted that the following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.

[0038] The following, combined Figure 2 to Figure 6 The following describes a method for editing pictures provided in an embodiment of the present application.

[0039] like Figure 2 As shown, the method for editing pictures provided by the present application includes the following steps S101 to S103.

[0040] Step S101: determining a plurality of local areas to be adjusted of an initial image.

[0041] The above-mentioned initial image refers to the image to be edited, which can be an image uploaded by the user or an image generated by the intelligent model.

[0042] The above-mentioned local area to be adjusted refers to the area to be edited corresponding to the above-mentioned initial image. The multiple local areas to be adjusted refer to different areas in the initial image, and the specific number can be 2, 3, 4, etc. For example, the multiple local areas to be adjusted can include the upper left corner area, the upper right corner area, the lower left corner area, and the lower right corner area of ​​the initial image.

[0043] In an optional implementation, in the embodiment of the present application, a graphical user interface is provided by a terminal device, and the terminal device may be a desktop computer, a laptop computer, a mobile phone, a tablet computer, an electronic watch, etc. The graphical user interface includes a chat interface with the agent model. That is, before the above step S101, the above method may further include the following steps:

[0044] Displaying a chat interface with the agent model through a terminal device, wherein the chat interface includes a second input area;

[0045] In response to a second input operation performed in the second input area, an initial picture is generated and displayed in the chat interface according to the description information input by the second input operation.

[0046] In an embodiment of the present application, the terminal device is a terminal device held by a user, and a client corresponding to the intelligent body model is installed on the terminal device. The user can open the client to display a chat interface with the intelligent body model on the terminal device. The chat interface may include a second input area. The user can perform a second input operation in the second input area to input the description information of the picture to be generated to the intelligent body model. In this way, the intelligent body model can generate an initial picture that matches the description information.

[0047] The above description information may be a description text, and the description information is used to describe the image content and image style of the initial image to be generated.

[0048] In a specific implementation, the above-mentioned second input operation can be an interactive operation between an external device such as a mouse or keyboard and a terminal device, or a touch operation performed on a touch-sensitive screen, or a voice command operation, wherein the touch operation can be one or a combination of click operations, slide operations, press operations, and drag operations. This application does not limit the specific implementation method of the second input operation.

[0049] It should be noted that when the intelligent agent model receives the input descriptive information, first, the descriptive information input by the second input operation can be converted into a machine language that can be understood by the machine. Specifically, natural language processing technology can be used to analyze the sentence structure, grammar, semantics and context information of the descriptive information. In this way, concepts and details in the descriptive information, such as objects, actions, locations, etc., can be extracted; secondly, a feature vector can be extracted from the above machine language, and the feature vector includes information required to generate the above initial picture; thereafter, the initial picture can be generated based on the extracted feature vector, and it can be determined whether the generated initial picture is true; if the generated initial picture is true, it is output to the user.

[0050] Exemplarily, when a user inputs the descriptive information "draw a little girl running in a forest", the descriptive information will be parsed first to identify the key elements "little girl", "forest" and "running", and then feature extraction will be performed to obtain a feature vector that characterizes the meanings of the key elements "little girl", "forest" and "running" and the relationship between them. Finally, an image is generated based on the feature vector, which shows a little girl running in a forest.

[0051] In step S101, multiple area selection instructions may be generated for the initial image, and the area selection instructions may be generated by a voice instruction operation, a touch operation on a specified control, or a trigger operation on the initial image. In response to the multiple area selection instructions, the local area to be adjusted corresponding to each area selection instruction may be determined, thereby obtaining multiple local areas to be adjusted of the initial image.

[0052] Optionally, when the initial image is generated by the agent model in the chat interface based on the description information input by the user, the step S101 specifically refers to:

[0053] In response to a first trigger operation on the initial picture displayed in the chat interface, switching the chat interface to an editing interface for the initial picture;

[0054] In response to a plurality of area selection instructions for the initial image displayed in the editing interface, a local area to be adjusted corresponding to each area selection instruction is determined to obtain a plurality of local areas to be adjusted of the initial image.

[0055] In the embodiment of the present application, the user can perform a first trigger operation on the initial image generated by the intelligent model, and the first trigger operation includes but is not limited to a touch operation, a voice command operation, an air gesture operation, or a shortcut key operation on the initial image, or a trigger control can be provided in the chat interface, and the first trigger operation can be a touch operation on the trigger control. Among them, the touch operation can be a click operation, a slide operation, a press operation, or a drag operation, etc. This embodiment does not specifically limit the triggering method of the first trigger operation on the initial image.

[0056] After receiving the first trigger operation for the initial picture, the chat interface currently displayed by the graphical user interface can be switched to an editing interface for the initial picture, and the initial picture is displayed in the editing interface.

[0057] It should be noted that the size of the initial picture displayed in the editing interface is larger than the size of the initial picture displayed in the chat interface. By providing an editing interface, on the one hand, the user can more conveniently and quickly determine multiple local areas to be adjusted for the initial picture. On the other hand, when adjusting the initial picture in the editing interface, misoperation of the chat interface can be effectively avoided.

[0058] Step S102: In response to first editing operations respectively performed on the plurality of local areas to be adjusted, receiving content adjustment description information to be edited input by each of the first editing operations.

[0059] In an embodiment of the present application, a user can perform a first editing operation on each of the multiple local areas to be adjusted of the above-mentioned initial image. The first editing operation can be an interactive operation between an external device such as a mouse and a keyboard and a terminal device, or a touch operation performed on a touch-sensitive screen, or a voice command operation, wherein the touch operation can be one or a combination of a click operation, a slide operation, a press operation, and a drag operation. The above-mentioned first editing operation is used to input adjustment description information for the above-mentioned initial image, and the adjustment description information can be description information in text form or description information in voice form. Different adjustment description information respectively represent different editing requirements for different local areas to be adjusted corresponding to the initial image, and the adjustment description information is used to describe the adjustment operation to be performed on the corresponding local area to be adjusted.

[0060] It should be noted that, when multiple local areas to be adjusted are determined by multiple area selection instructions for the initial image displayed in the editing interface, the user can perform the above-mentioned first editing operation on the multiple local areas to be adjusted of the initial image displayed in the editing interface respectively, so as to input adjustment description information for each local area to be adjusted of the initial image.

[0061] Through step S102, adjustment description information representing different editing requirements for different local areas to be adjusted corresponding to the initial image can be received, providing a basis for the intelligent agent model to perform multiple editing operations on the initial image at one time.

[0062] Step S103: In response to the picture editing instruction, submit adjustment information for the initial picture so that the intelligent model generates a target picture based on the adjustment information and the initial picture, wherein the adjustment information includes the area information of the local area to be adjusted and the adjustment description information.

[0063] In an embodiment of the present application, after receiving the above-mentioned adjustment description information, the above-mentioned picture editing instructions can be automatically generated, or the picture editing quality can be generated when receiving the user's specified operation.

[0064] In response to the picture editing instruction, adjustment information for the initial picture can be submitted. It should be noted that the above adjustment information includes the area information and adjustment description information of the local area to be adjusted, and the area information is used to determine the local area to be adjusted from the initial picture. In this way, the intelligent body model can clearly identify the local areas to be adjusted on the initial picture and the adjustment operations that need to be performed on each local area to be adjusted, so that the intelligent body model can perform the editing operations corresponding to the adjustment description information on the initial picture based on the adjustment information, thereby adjusting the initial picture to the target picture. Afterwards, the target picture can be displayed in the graphical user interface corresponding to the intelligent body model.

[0065] Optionally, the region information of the local area to be adjusted may be a region identifier corresponding to the local area to be adjusted. Each local area to be adjusted of the initial image may have a corresponding region identifier. The region identifier may be understood as an ID number of the local area to be adjusted, which is used to enable the computer to identify the corresponding local area to be adjusted. The region identifier may be preset or generated in real time. The region identifier corresponds to the local area to be adjusted one by one, that is, one local area to be adjusted has one and only one region identifier, and a unique local area to be adjusted can be determined based on one region identifier.

[0066] In the related art, the adjustment of a certain picture is achieved by the user inputting a modification instruction in the interface. Figure 1 To introduce, the user enters the content to be modified 12 "Add a house" in the dialog box in the chat interface, so as to modify the entire picture. It is impossible to perform fine control on the local area on the picture. For example, the related technology cannot add a house in a specified area on the upper left of the person in the picture 11.

[0067] In the embodiment of the present application, the user can select multiple specific areas (local areas to be adjusted) to perform the first editing operation respectively, thereby providing a basis for performing refined detail correction on multiple local areas of the initial image at one time.

[0068] As shown in Table 1, it is an example table of area information and adjustment description information of a local area to be adjusted included in the adjustment information in the method for editing a picture provided in an embodiment of the present application.

[0069] Table 1.

[0070]

[0071] In the above Table 1, the determined local areas to be adjusted are area 01 and area 02, respectively. The adjustment description information input for area 01 is to add some flying birds, and the adjustment description information input for area 02 is to add light entering from the upper left. In response to the image editing instruction, the adjustment information of adding some flying birds to area 01 of the initial image and adding light entering from the upper left to area 02 of the initial image can be submitted, thereby adding some flying birds to area 01 of the initial image and adding light entering from the upper left to area 02 of the initial image through the intelligent body model.

[0072] It can be seen that in the method for editing pictures provided in the embodiment of the present application, the user can input corresponding adjustment description information for different local areas to be adjusted in the initial picture according to actual needs, and submit the adjustment information for the initial picture through picture editing instructions, and then control the intelligent model to perform the editing operation indicated by the corresponding adjustment description information on each local area to be adjusted at one time, thereby realizing refined control of the picture and making the target picture more in line with the user's expectations.

[0073] The method for editing a picture provided by the embodiment of the present application includes: determining multiple local areas to be adjusted of an initial picture; in response to the first editing operations respectively performed on the multiple local areas to be adjusted, receiving the adjustment description information input by each of the first editing operations; in response to the picture editing instruction, submitting the adjustment information for the initial picture, so that the intelligent agent model generates a target picture based on the adjustment information and the initial picture, wherein the adjustment information includes the area information of the local areas to be adjusted and the adjustment description information. It can be seen that in the method for editing a picture provided by the embodiment of the present application, for the initial picture, first, multiple local areas to be adjusted are determined, so as to determine the local areas to be adjusted in the initial picture, and then, by performing the first editing operation on each local area to be adjusted, respectively, the adjustment description information is input for each local area to be adjusted. Afterwards, in response to the picture editing instruction, the adjustment information containing the area information of each local area to be adjusted and the corresponding adjustment description information can be submitted to control the intelligent agent model to perform the editing operation indicated by the corresponding adjustment description information on multiple local areas to be adjusted of the initial picture at one time. Therefore, the method for editing pictures provided in the present application can perform multiple editing operations on multiple local areas of a picture at one time, achieve efficient and fast editing, and meet the user's needs for fast picture output.

[0074] In an optional embodiment, when multiple local areas to be adjusted are generated by multiple area selection instructions for an initial image displayed in an editing interface, a first control for indicating the shape of the area is provided in the editing interface, and the first control includes at least one of box selection, circle selection, and area selection.

[0075] Each region selection instruction can be generated by the following steps:

[0076] In response to a selection operation on the first control, configuring the initial image displayed in the editing interface to be in a to-be-triggered state;

[0077] In response to a second trigger operation on the initial image in the to-be-triggered state, the area selection instruction is generated.

[0078] In the embodiment of the present application, a first control may be provided in the editing interface, and the first control includes but is not limited to at least one of frame selection, circle selection, and area selection, etc. Frame selection refers to selecting a part of a picture by drawing a rectangle, which may be a rectangle of a preset size or a rectangle of any size; circle selection refers to selecting a part of a picture by drawing a circle or an ellipse; area selection refers to the user freely outlining the boundary of the area to be selected, and the selected area may be of any shape, such as selecting the face of a person in a picture containing a person, or selecting the person's clothes, etc.

[0079] By selecting a first target control in the first control, the initial image displayed in the editing interface can be configured from a non-triggerable state to a to-be-triggered state. It should be noted that the initial image is configured from a non-triggerable state to a to-be-triggered state means that the initial image is changed from a state without interactive functions to a state with specific interactive functions or response capabilities.

[0080] The selection operation may be one of a click operation, a press operation, a slide operation or a drag operation. Afterwards, the user may perform a second trigger operation, such as a slide operation, a click operation, etc., on the initial image configured as a to-be-triggered state in the editing interface. In this way, the above-mentioned area selection instruction may be generated.

[0081] It should be noted that after the second trigger operation is completed, the initial image can be changed from the to-be-triggered state to the non-triggerable state. After the first control is selected again, the initial image will be changed to the to-be-triggered state again.

[0082] Optionally, the shapes of the local areas to be adjusted determined by different first controls are different. The above step of "determining the local area to be adjusted corresponding to each area selection instruction" may specifically include the following steps:

[0083] According to the second trigger operation, determining a local area to be adjusted that matches the area shape indicated by the first target control;

[0084] The local area to be adjusted of the first shape is highlighted.

[0085] In this embodiment, the above-mentioned local area to be adjusted that matches the shape of the area indicated by the first target control specifically refers to: if the selected first control is a frame selection control, the determined local area to be adjusted is a rectangle; if the selected first control is a circle selection control, the determined local area to be adjusted is a circle; if the selected first control is an area selection control, the determined local area to be adjusted is a shape formed by connecting the contact positions in sequence in the touch operation to be performed.

[0086] After determining the local area to be adjusted that matches the area shape indicated by the first target control, the local area to be adjusted can be highlighted on the initial image displayed in the editing interface. For example, a layer is added to the local area to be adjusted of the initial image displayed in the editing interface, or the local area to be adjusted is highlighted, or the local area to be adjusted is displayed in different colors to intuitively present the currently selected local area to be adjusted to the user.

[0087] It should be noted that the user can perform area adjustment operations on the highlighted local area to be adjusted, such as enlarging the local area to be adjusted, reducing the local area to be adjusted, moving the local area to be adjusted, or rotating the local area to be adjusted.

[0088] In the embodiment of the present application, by providing a first control for indicating the shape of the area, the user can select the corresponding first control according to actual needs. If you want to edit a circular area, you can select the circle selection control. If you want to edit a rectangular area, you can select the box selection control. If you want to freely delimit the selected area for editing, you can select the area selection control. On the one hand, the first control facilitates the user to more accurately delimit the desired local area to be adjusted. For some simple shapes, such as circles and rectangles, the area of ​​the desired shape can be quickly obtained through the circle selection control and the box selection control, without the user manually drawing the selected area in detail; on the other hand, providing the first control in the editing interface reduces the learning cost for novice users and reduces the cognitive burden of users.

[0089] In addition, after the local area to be adjusted is determined, the local area to be adjusted is highlighted in the editing interface to intuitively present the currently selected local area to be adjusted to the user, so that the user can quickly determine whether the currently selected local area to be adjusted is the expected area.

[0090] In an optional implementation manner, the method for editing a picture provided in the embodiment of the present application may further include the following steps:

[0091] When each of the local areas to be adjusted is determined, the area identifier of the local area to be adjusted and the corresponding first input area are displayed through the terminal device, wherein the area identifier represents the area information of the local area to be adjusted.

[0092] In a specific implementation, when each local area to be adjusted is determined, the area identifier of the local area to be adjusted and the corresponding first input area can be displayed through the terminal device. The area identifier represents the area information of the corresponding local area to be adjusted, and the first input area is used to input the corresponding adjustment description information for the corresponding local area to be adjusted.

[0093] Optionally, the first editing operation in step S102 is a first input operation performed in the first input area. The "receiving the adjustment description information input by each of the first editing operations" in step S102 may specifically be: for each of the local areas to be adjusted, determining the information input by the first input operation as the adjustment description information of the local area to be adjusted.

[0094] In the case where multiple local areas to be adjusted are generated by multiple area selection instructions for the initial image displayed in the editing interface, when a selection operation is performed on the first target control in the first control and a second trigger operation is performed on the initial image displayed in the editing interface and in a triggered state, after the local area to be adjusted is determined, the area identifier of the above-mentioned local area to be adjusted and the corresponding first input area are displayed in the editing interface. In this way, the above-mentioned first editing operation is the first input operation performed in the first input area displayed in the editing interface. When the first input operation is received, the information input by the first input operation is determined as the adjustment description information of the local area to be adjusted.

[0095] Exemplarily, the area identifier of a local area to be adjusted is 01, and the information input in the corresponding first input area is adding flying birds, then the adjustment description information for the 01 area is adding flying birds.

[0096] In an optional implementation, the above picture editing instruction may be generated in the following manner:

[0097] In response to a page return operation performed when the first editing operation is completed, switching the editing interface to the chat interface;

[0098] Displaying the content to be sent including the adjustment information in the second input area;

[0099] In response to a sending operation on the content to be sent, the picture editing instruction is generated.

[0100] In an optional specific implementation, a corresponding functional control may be provided in the editing interface to support a page return operation. For example, a return control may be provided in the upper left corner of the editing interface. After the user completes the adjustment description information through the first editing operation input, the user may click the return control to cause the editing interface to jump to the chat interface and display the content to be sent containing the above adjustment information in the second input area of ​​the chat interface.

[0101] In another optional specific implementation, the page return operation can be a voice command operation. After the user completes the adjustment description information through the first editing operation input, the voice command "Please return to the main interface" can be issued, so that the editing interface jumps to the chat interface and displays the content to be sent containing the above-mentioned adjustment information in the second input area of ​​the chat interface.

[0102] By displaying the chat interface with the content to be sent containing the above adjustment information, the user can confirm whether the currently displayed content to be sent covers the required multiple editing requirements. If so, the content to be sent can be sent. The sending operation includes but is not limited to the touch operation, voice command operation, air gesture operation or shortcut key operation of the sending control provided in the interface. Among them, the touch operation can be a click operation, a slide operation, a press operation or a drag operation.

[0103] After receiving the sending operation for the content to be sent, the above-mentioned picture editing instruction can be generated, thereby submitting the adjustment information for the initial picture, so that the intelligent agent model generates the target picture based on the adjustment information and the initial picture.

[0104] In an optional implementation, after the first input operation is completed, the first input area may continue to be displayed in the graphical user interface, that is, the first input area is visible to the user regardless of whether the first input operation is completed or not.

[0105] In another optional implementation, after the first input operation is completed, the first input area is changed from a visible state to an invisible state. In this case, the method for editing a picture provided in the embodiment of the present application may further include the following steps:

[0106] When the adjustment description information is received, generating a second control in the corresponding highlighted local area to be adjusted;

[0107] In response to a third trigger operation on the second control, displaying a first input area containing the adjustment description information;

[0108] In response to an update operation on the adjustment description information displayed in the first input area, updated adjustment description information is acquired, and the updated adjustment description information is determined as the adjustment description information of the corresponding local area to be adjusted.

[0109] In this embodiment, when the adjustment description information for a certain local area to be adjusted is received, a second control can be generated in the local area to be adjusted that is corresponding to and highlighted in the initial image displayed in the editing interface, and each local area to be adjusted can contain a corresponding second control. The second control is used to support the user to update the adjustment description information corresponding to the local area to be adjusted. The second control can be located at any position in the local area to be adjusted, such as the upper left corner, the lower left corner, the upper right corner, and the lower right corner. This application does not limit the display position of the second control.

[0110] In a specific implementation, the user can perform a third trigger operation on the second control, and the third trigger operation can be one of a click operation, a press operation, a slide operation, a drag operation, a voice command operation, etc. on the second control.

[0111] In response to the third trigger operation, a first input area containing adjustment description information may be displayed in the graphical user interface. In this way, the user may perform an update operation on the adjustment description information displayed in the first input area, thereby obtaining the updated adjustment description information corresponding to the update operation, and determining the updated adjustment description information as the adjustment description information of the local area to be adjusted where the second control is located, thereby implementing the update of the adjustment description information.

[0112] The above-mentioned update operation can be to delete the currently displayed adjustment description information and re-enter the updated adjustment description information through an external device such as a mouse or keyboard, or to delete the currently displayed adjustment description information and re-enter the updated adjustment description information through a touch screen, or to delete the currently displayed adjustment description information and re-enter the updated adjustment description information through voice commands.

[0113] For example, a second control is generated in a local area to be adjusted 01. After the user clicks the second control, a first input area is generated that contains the adjustment description information "Add some flying birds" currently corresponding to the local area to be adjusted 01. The user updates "Add some flying birds" displayed in the first input area to "Add some butterflies", thereby updating the adjustment description information of the local area to be adjusted 01 to "Add some butterflies".

[0114] This setting method, after inputting the adjustment description information for the local area to be adjusted, can provide visual guidance for the user by generating and displaying the second control in the local area to be adjusted, so that the user can quickly update the adjustment description information for the local area to be adjusted through the second control, thereby improving the flexibility and freedom when editing pictures.

[0115] The following is a detailed introduction to the method for editing pictures provided by the embodiment of the present application through a specific application scenario:

[0116] In the chat interface with the intelligent agent model, the user enters the description information "Please generate a picture of a little girl running in the forest", and then the intelligent agent model outputs the initial picture a; first, the user can perform a first trigger operation (such as a click operation) on the initial picture a displayed in the chat interface to switch the chat interface to an editing interface for the initial picture a.

[0117] At this time, the editing interface displays multiple first controls, including a box selection control, a circle selection control, and an area selection control. The user can select the box selection control, and then the initial image a displayed in the editing interface changes to a to-be-triggered state; the user can perform a sliding operation (i.e., a second trigger operation) on the initial image a in the to-be-triggered state, thereby using the sliding path of the sliding operation as a diagonal line to generate a rectangular local area to be adjusted 01. At this time, the editing interface displays the area identifier 01 of the local area to be adjusted 01 and the corresponding first input area, in which the user enters the adjustment description information of "add some flying birds".

[0118] Afterwards, the user selects the circle control from the first control again, and then the initial image a displayed in the editing interface changes to the to-be-triggered state again; the user can perform a sliding operation (i.e., the second trigger operation) on the initial image a in the to-be-triggered state, thereby using the sliding path of the sliding operation as the diameter to generate a circular local area to be adjusted 02. At this time, the editing interface displays the area identifier 02 of the local area to be adjusted 02 and the corresponding first input area, in which the user enters the adjustment description information of "brightness dimming".

[0119] Moreover, in the initial picture 01 displayed in the editing interface, the local area to be adjusted 01 and the local area to be adjusted 02 are highlighted, and second controls are generated in the local area to be adjusted 01 and the local area to be adjusted 02, respectively. When the corresponding second control in the local area to be adjusted 01 is clicked, the first input area containing the adjustment description information "Add some flying birds" is displayed, and the player updates the adjustment description information "Add some flying birds" to the adjustment description information "Add some butterflies", thereby updating the adjustment description information of the local area to be adjusted 01 to "Add some butterflies".

[0120] Afterwards, the user can perform a page return operation in the editing interface to switch the editing interface displayed by the current graphical user interface to a chat interface with the intelligent body model. In the chat interface, the second input area displays the content to be sent, including the area information of the local area to be adjusted 01 and its adjustment description information "add some butterflies", as well as the area information of the local area to be adjusted 02 and its adjustment description information "dim the brightness".

[0121] Finally, the user can perform a sending operation to generate a picture editing instruction, and submit adjustment information including the area information of the local area to be adjusted 01 and its adjustment description information "add some butterflies", as well as the area information of the local area to be adjusted 02 and its adjustment description information "dim the brightness", so that the intelligent model can add butterfly elements to the local area to be adjusted 01 of the initial picture a at one time, and dim the brightness of the local area to be adjusted 02 of the initial picture a, thereby realizing multiple editing operations on multiple local areas of a picture at one time.

[0122] It should be noted that in the embodiment of the present application, when the content to be sent containing adjustment information is displayed in the chat interface, the user can preview the content to be sent to confirm whether the content to be sent is complete or incorrect, so as to decide whether to enter the editing interface again to add or modify the local area to be adjusted or the adjustment description information. Therefore, the method for editing pictures provided in the embodiment of the present application improves the flexibility, rationality and strategy of picture editing, and can efficiently and quickly obtain the target picture expected by the user.

[0123] The following Figure 3 to Figure 6 The interface interaction in the method for editing a picture provided in the embodiment of the present application is introduced:

[0124] like Figure 3 The figure is a schematic diagram of an example of switching from a chat interface to an editing interface in the method for editing pictures provided in an embodiment of the present application, including interface (3-a) and interface (3-b).

[0125] As shown in interface (3-a), it is a chat interface with the agent model, and the chat interface includes a second input area. In response to the description information 10 "draw a person running on a poster" input by the user in the second input area, an initial picture 11 consistent with the description information 10 is generated. When the user clicks or presses the initial picture, the graphical user interface will switch from interface (3-a) to interface (3-b).

[0126] As shown in interface (3-b), it is an editing interface for the initial image 11. In the editing interface, an initial image 13 whose size is larger than that of the initial image 11 in interface (3-a) is displayed, as well as a first control for indicating the shape of the area, which are a frame selection control, a circle control (also called a circle selection control), a zone selection control, and a cropping control. Among them, the frame selection control is used to determine a rectangular local area to be adjusted in the initial image 13, the circle control is used to determine a circular local area to be adjusted in the initial image 13, the zone selection control is used to freely outline a local area to be adjusted in any shape in the initial image 13, and the cropping control is used to crop the initial image 13 into a rectangular local area to be adjusted. After the user clicks or presses the frame selection control, it will be displayed Figure 4 The graphical user interface shown.

[0127] like Figure 4 The figure is a schematic diagram of an example of inputting adjustment description information for a local area to be adjusted in the method for editing a picture provided in an embodiment of the present application, including interface (4-a) and interface (4-b).

[0128] As shown in interface (4-a), after the user performs a selection operation on the box selection control, a second trigger operation is performed on the initial image 13. The determined local area to be adjusted 14 is highlighted on the initial image 13, and a first input area 16 is displayed. The first input area 16 includes area information "box selection" of the local area to be adjusted 14. The user enters adjustment description information "add some flying birds" in the first input area 16 and clicks the completion control 17. Then, the corresponding adjustment description information "add some seagulls" can be entered for the boxed local area to be adjusted 14, and the graphical user interface will switch from interface (4-a) to interface (4-b).

[0129] As shown in interface (4-b), a second control 15 is generated in the local area to be adjusted 14 highlighted in the initial image 13 displayed in the editing interface. When the user performs a third trigger operation on the second control 15, the graphical user interface will switch from interface (4-b) to interface (4-c).

[0130] As shown in interface (4-c), the editing interface displays a first input area 16 containing adjustment description information "Add some flying birds". The user can update the adjustment description information displayed in the first input area 16. As shown in interface (4-d), the adjustment description information "Add some flying birds" will be updated to "Add some seagulls".

[0131] like Figure 5 The figure is a schematic diagram of an example of inputting adjustment description information for another local area to be adjusted in the method for editing a picture provided in an embodiment of the present application, including interface (5-a) and interface (5-b).

[0132] As shown in interface (5-a), after the user performs a selection operation on the circled control, the graphical user interface will switch from interface (5-a) to interface (5-b).

[0133] As shown in interface (5-b), the user performs the second trigger operation on the initial image 13, the determined circular local area to be adjusted 19 is highlighted on the initial image 13, and the first input area 16 is displayed, the first input area 16 includes the area information "circle" of the local area to be adjusted 19, the user enters the adjustment description information "add some shells" in the first input area 16, and clicks the completion control 17, then the corresponding adjustment description information "add some shells" can be entered for the circled local area to be adjusted 19. In addition, the second control will also be generated in the local area to be adjusted 19.

[0134] After that, you can click the return button in the editing interface (such as 20 shown in interface (5-b)) to control Figure 5 The editing interface shown switches to Figure 6 The chat interface shown is as follows: Figure 6 FIG. 1 is a schematic diagram of an example in which the second input area displays the content to be sent including the adjustment information in the method for editing a picture provided by an embodiment of the present application. Figure 3 , 4 , 5, the second input area 21 in the chat interface will display the content to be sent, which includes the adjustment description information of "add some seagulls" for the framed area and the adjustment description information of "add some shells" for the circled area. The user can click the send control 22 in the chat interface to send the content to be sent. In this way, the intelligent model can add some seagulls to the local area to be adjusted 14 in the initial picture and some shells to the local area to be adjusted 19 at one time.

[0135] Optionally, a restore control may be provided in the editing interface. The method for editing a picture provided in the embodiment of the present application may further include the following steps:

[0136] In response to a fourth trigger operation on the restoration control after the first editing operation is completed, the adjustment description information input for the local area to be adjusted corresponding to the first editing operation is cleared.

[0137] It should be noted that, in response to the above-mentioned first editing operation, the adjustment description information is input for the local area to be adjusted. In this case, a fourth trigger operation can be performed for the restoration control, and the fourth trigger operation can be a click operation, a slide operation, a press operation, a voice command operation, or a shortcut key operation, etc. In response to the fourth trigger operation, the adjustment description information input for the local area to be adjusted corresponding to the first editing operation can be cleared, and in addition, the determined local area to be adjusted can also be cleared.

[0138] Combined with Figure 5 The interface (5-b) in the figure introduces the above steps. A restore control 18 is provided in the interface (5-b). When the restore control 18 is clicked, the determined local area to be adjusted 19 will be cleared, and the adjustment description information "add some shells" corresponding to the local area to be adjusted 19 will be cleared.

[0139] By setting the restore control, the user can undo the determined local area to be adjusted and its corresponding adjustment description information, so that the user can freely control the local area to be adjusted and the adjustment description information.

[0140] Suppose that five modifications need to be made to an initial image. In the prior art, it takes 5 seconds for the player to input each modification opinion, and 30 seconds for the system to generate the corresponding image. Then, it takes 175 seconds to make five modifications. In contrast, in the method for editing images provided in the embodiment of the present application, it takes 1 second for the player to select the first control, 1 second to determine the local area to be adjusted, and 3 seconds to input the adjustment description information for each local area to be adjusted. In this way, it takes 25 seconds to input the five modification opinions, 3 seconds to issue the image editing instruction, and 30 seconds for the system to generate the corresponding image at one time. Then, it takes a total of 58 seconds to generate the target image. It can be seen that in this example, a total of 117 seconds are saved, and the efficiency is improved by 66.9%, meeting the user's demand for fast image output.

[0141] Corresponding to the method for editing pictures provided in the first embodiment of the present application, the second embodiment of the present application further provides a device for editing pictures, such as Figure 7 As shown, the apparatus 700 for editing a picture includes:

[0142] A determination unit 701 is used to determine a plurality of local areas to be adjusted of an initial image;

[0143] A receiving unit 702 is configured to receive adjustment description information input by each of the first editing operations respectively performed on the plurality of local areas to be adjusted;

[0144] The submission unit 703 is used to respond to the picture editing instruction and submit adjustment information for the initial picture so that the intelligent model generates a target picture based on the adjustment information and the initial picture, wherein the adjustment information includes the area information of the local area to be adjusted and the adjustment description information.

[0145] Optionally, the apparatus 700 for editing a picture further includes a display unit, and the display unit is used to:

[0146] When each of the local areas to be adjusted is determined, the area identifier of the local area to be adjusted and the corresponding first input area are displayed through the terminal device, wherein the area identifier represents the area information of the local area to be adjusted.

[0147] Optionally, the first editing operation is a first input operation performed in the first input area; and the receiving unit 702 is specifically configured to:

[0148] For each of the local areas to be adjusted, the information input by the first input operation is determined as the adjustment description information of the local area to be adjusted.

[0149] Optionally, the display unit is further used for:

[0150] Displaying a chat interface with the agent model through a terminal device, wherein the chat interface includes a second input area;

[0151] In response to a second input operation performed in the second input area, an initial picture is generated and displayed in the chat interface according to the description information input by the second input operation.

[0152] Optionally, the determining unit 701 is specifically configured to:

[0153] In response to a first trigger operation on the initial picture displayed in the chat interface, switching the chat interface to an editing interface for the initial picture;

[0154] In response to a plurality of area selection instructions for the initial image displayed in the editing interface, a local area to be adjusted corresponding to each area selection instruction is determined to obtain a plurality of local areas to be adjusted of the initial image.

[0155] Optionally, a first control for indicating a region shape is provided in the editing interface, and the first control includes at least one of a box selection, a circle selection, and a region selection; the determining unit 701 specifically generates each region selection instruction in the following manner:

[0156] In response to a selection operation on a first target control in the first controls, configuring the initial image displayed in the editing interface to be in a to-be-triggered state;

[0157] In response to a second trigger operation on the initial image in the to-be-triggered state, the area selection instruction is generated.

[0158] Optionally, the determining unit 701 is specifically configured to:

[0159] According to the second trigger operation, determining a local area to be adjusted that matches the area shape indicated by the first target control;

[0160] The local area to be adjusted is highlighted.

[0161] Optionally, the submitting unit 703 generates the picture editing instruction in the following manner:

[0162] In response to a page return operation performed when the first editing operation is completed, switching the editing interface to the chat interface;

[0163] Displaying the content to be sent including the adjustment information in the second input area;

[0164] In response to a sending operation on the content to be sent, the picture editing instruction is generated.

[0165] Optionally, the display unit is further used for:

[0166] When the adjustment description information is received, generating a second control in the corresponding highlighted local area to be adjusted;

[0167] In response to a third trigger operation on the second control, displaying a first input area containing the adjustment description information;

[0168] In response to an update operation on the adjustment description information displayed in the first input area, updated adjustment description information is acquired, and the updated adjustment description information is determined as the adjustment description information of the corresponding local area to be adjusted.

[0169] Optionally, a restore control is provided in the editing interface, and the apparatus 700 for editing a picture further includes a restore unit, and the restore unit is specifically used to:

[0170] In response to a fourth trigger operation on the restoration control after the first editing operation is completed, the adjustment description information input for the local area to be adjusted corresponding to the first editing operation is cleared.

[0171] The apparatus for editing a picture provided in an embodiment of the present application determines, for an initial picture, a plurality of local areas to be adjusted of the initial picture; in response to first editing operations respectively performed on the plurality of local areas to be adjusted, receives adjustment description information input by each first editing operation; in response to a picture editing instruction, submits adjustment information for the initial picture, so that the intelligent agent model generates a target picture based on the adjustment information and the initial picture, wherein the adjustment information includes area information and adjustment description information of the local areas to be adjusted. Therefore, the apparatus for editing a picture provided in the present application can perform a variety of editing operations on a plurality of local areas of a picture at one time, realize efficient and fast editing, and meet the user's demand for fast picture generation.

[0172] Corresponding to the method for editing pictures provided in the first embodiment of the present application, the third embodiment of the present application further provides an electronic device for editing pictures. Figure 8 As shown, the electronic device 800 includes: a processor 801; and a memory 802, which is used to store a program of a method for editing a picture. After the device is powered on and the program of the method for editing a picture is run by the processor, the following steps are performed:

[0173] Determine multiple local areas of the initial image to be adjusted;

[0174] In response to first editing operations respectively performed on the plurality of local areas to be adjusted, receiving adjustment description information input by each of the first editing operations;

[0175] In response to the picture editing instruction, adjustment information for the initial picture is submitted so that the intelligent model generates a target picture based on the adjustment information and the initial picture, wherein the adjustment information includes the area information of the local area to be adjusted and the adjustment description information.

[0176] The electronic device for editing pictures provided by the embodiment of the present application determines, for an initial picture, multiple local areas to be adjusted of the initial picture; in response to first editing operations respectively performed on multiple local areas to be adjusted, receives adjustment description information input by each first editing operation; in response to a picture editing instruction, submits adjustment information for the initial picture, so that the intelligent agent model generates a target picture based on the adjustment information and the initial picture, wherein the adjustment information includes area information and adjustment description information of the local areas to be adjusted. Therefore, the electronic device for editing pictures provided by the present application can perform multiple editing operations on multiple local areas of a picture at one time, realize efficient and fast editing, and meet the user's demand for fast picture output.

[0177] Corresponding to the method for editing a picture provided in the first embodiment of the present application, the fourth embodiment of the present application provides a computer-readable storage medium storing a program for the method for editing a picture, the program being executed by a processor to perform the following steps:

[0178] In response to a first input operation of description information, generating an initial image according to the description information;

[0179] In response to at least two second input operations respectively performed on the initial picture, respectively recording the content to be edited input by each second input operation, wherein each content to be edited respectively represents a different editing requirement for the initial picture;

[0180] In response to the editing instructions including the contents to be edited, the editing operations indicated by the contents to be edited are respectively performed on the initial image.

[0181] The computer-readable storage medium provided in the embodiment of the present application determines, for an initial image, multiple local areas to be adjusted of the initial image; in response to first editing operations respectively performed on multiple local areas to be adjusted, receives adjustment description information input by each first editing operation; in response to an image editing instruction, submits adjustment information for the initial image, so that the intelligent agent model generates a target image based on the adjustment information and the initial image, wherein the adjustment information includes area information and adjustment description information of the local areas to be adjusted. Therefore, the computer-readable storage medium provided in the present application can perform multiple editing operations on multiple local areas of a picture at one time, realize efficient and fast editing, and meet the user's demand for fast image output.

[0182] It should be noted that for the detailed description of the devices, electronic devices and computer-readable storage media provided in the second, third and fourth embodiments of the present application, reference can be made to the relevant description of the first embodiment of the present application, and no further details will be given here.

[0183] Although the present application is disclosed as above in the form of a preferred embodiment, it is not intended to limit the present application. Any technical personnel in this field may make possible changes and modifications without departing from the spirit and scope of the present application. Therefore, the scope of protection of the present application shall be based on the scope defined by the claims of the present application.

[0184] In a typical configuration, a node device in a blockchain includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0185] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0186] 1. Computer-readable media includes permanent and non-permanent, removable and non-removable media that can be used to store information by any method or technology. Information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), random access memory (RAM) of other attributes, read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage media or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined in this article, computer-readable media does not include non-transitory media such as modulated data signals and carrier waves.

[0187] 2. Those skilled in the art should understand that the embodiments of the present application can be provided as methods, systems or computer program products. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0188] Although the present application is disclosed as above in the form of a preferred embodiment, it is not intended to limit the present application. Any technical personnel in this field may make possible changes and modifications without departing from the spirit and scope of the present application. Therefore, the scope of protection of the present application shall be based on the scope defined by the claims of the present application.

Claims

1. A method for editing a picture, characterized in that: The method comprises: Determine multiple local areas of the initial image to be adjusted; In response to first editing operations respectively performed on the plurality of local areas to be adjusted, receiving adjustment description information input by each of the first editing operations; In response to the picture editing instruction, adjustment information for the initial picture is submitted so that the intelligent model generates a target picture based on the adjustment information and the initial picture, wherein the adjustment information includes the area information of the local area to be adjusted and the adjustment description information.

2. The method according to claim 1, characterized in that The method further comprises: When each of the local areas to be adjusted is determined, the area identifier of the local area to be adjusted and the corresponding first input area are displayed through the terminal device, wherein the area identifier represents the area information of the local area to be adjusted.

3. The method according to claim 2, characterized in that The first editing operation is a first input operation performed in the first input area; The receiving the adjustment description information input by each of the first editing operations includes: For each of the local areas to be adjusted, the information input by the first input operation is determined as the adjustment description information of the local area to be adjusted.

4. The method according to claim 1, characterized in that Before determining the multiple local areas to be adjusted of the initial image, the method further includes: Displaying a chat interface with the agent model through a terminal device, wherein the chat interface includes a second input area; In response to a second input operation performed in the second input area, an initial picture is generated and displayed in the chat interface according to the description information input by the second input operation.

5. The method according to claim 1, characterized in that The determining of a plurality of local areas to be adjusted of the initial image includes: In response to a first trigger operation on the initial picture displayed in the chat interface, switching the chat interface to an editing interface for the initial picture; In response to a plurality of area selection instructions for the initial image displayed in the editing interface, a local area to be adjusted corresponding to each area selection instruction is determined to obtain a plurality of local areas to be adjusted of the initial image.

6. The method according to claim 5, characterized in that The editing interface provides a first control for indicating the shape of the region, wherein the first control includes at least one of box selection, circle selection, and area selection; each of the region selection instructions is generated in the following manner: In response to a selection operation on a first target control in the first controls, configuring the initial image displayed in the editing interface to be in a to-be-triggered state; In response to a second trigger operation on the initial image in the to-be-triggered state, the area selection instruction is generated.

7. The method according to claim 6, characterized in that The determining of the local area to be adjusted corresponding to each area selection instruction includes: According to the second trigger operation, determining a local area to be adjusted that matches the area shape indicated by the first target control; The local area to be adjusted is highlighted.

8. The method according to claim 5, characterized in that The picture editing instruction is generated in the following way: In response to a page return operation performed when the first editing operation is completed, switching the editing interface to the chat interface; Displaying the content to be sent including the adjustment information in the second input area; In response to a sending operation on the content to be sent, the picture editing instruction is generated.

9. The method according to claim 7, characterized in that: The method further comprises: When the adjustment description information is received, generating a second control in the corresponding highlighted local area to be adjusted; In response to a third trigger operation on the second control, displaying a first input area containing the adjustment description information; In response to an update operation on the adjustment description information displayed in the first input area, updated adjustment description information is acquired, and the updated adjustment description information is determined as the adjustment description information of the corresponding local area to be adjusted.

10. The method according to claim 7, characterized in that A restore control is provided in the editing interface, and the method further comprises: In response to a fourth trigger operation on the restoration control after the first editing operation is completed, the adjustment description information input for the local area to be adjusted corresponding to the first editing operation is cleared.

11. A device for editing a picture, characterized in that: The device comprises: A determination unit, used to determine a plurality of local areas to be adjusted of the initial image; a receiving unit, configured to receive adjustment description information inputted by each of the first editing operations respectively performed on the plurality of local areas to be adjusted; A submission unit is used to respond to the picture editing instruction and submit adjustment information for the initial picture so that the intelligent model generates a target picture based on the adjustment information and the initial picture, wherein the adjustment information includes the area information of the local area to be adjusted and the adjustment description information.

12. An electronic device, characterized in that: include: processor; as well as The memory is used to store a data processing program. After the electronic device is powered on and the program is run by the processor, the method according to any one of claims 1 to 10 is executed.

13. A computer-readable storage medium, characterized in that: A data processing program is stored, and the program is run by a processor to execute the method according to any one of claims 1 to 10.

Images