Image generation method and apparatus, electronic device, and readable storage medium
By obtaining the facial information and pose information of the target object model and the first image, and using the AIGC model to generate the second image, the problem of poor matching of facial and pose information in image editing is solved, and higher quality image generation and user-friendly creative editing are achieved.
Patent Information
- Application Number
- PCT/CN2024/141813
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2023-12-29
- Filing Date
- 2024-12-24
- Publication Date
- 2025-07-03
AI Technical Summary
The prior art is difficult to effectively match and edit the user's facial information and posture information during the image editing process, resulting in the generated image not matching the original image or the effect is poor.
By acquiring facial information and pose information in the target object model and the first image, a second image is generated using the AIGC model to match it with the features in the first image, and allowing the user to adjust the image style, background, pose, etc. through triggering operations to achieve the generation of creative images.
It improves the degree of matching between the generated image and the original image and the imaging effect, and enhances the user's control and flexible configuration capabilities of image content.
Smart Images

Figure CN2024141813_03072025_PF_FP_ABST
Abstract
Description
Image generation method, device, electronic device, and readable storage medium
[0001] This application claims priority to Chinese patent application No. 202311864088.7 filed on December 29, 2023, and the contents of the above-mentioned Chinese patent application disclosure are hereby cited in their entirety as part of this application. Technical Field
[0002] The present disclosure relates to an image generation method, an apparatus, an electronic device, and a readable storage medium. Background Art
[0003] With the advancement of technology, more and more users choose to use applications to edit the images they capture in order to obtain media content for publishing and sharing. Summary of the Invention
[0004] The purpose of the embodiments of the present disclosure is to provide an image generation method, device, electronic device and readable storage medium.
[0005] In a first aspect, an embodiment of the present disclosure provides an image generation method, including: obtaining a target object model, the target object model being generated based on the image of the target object; obtaining a first image on a content generation page, the first image including a first object feature of the target object, the first object feature including first facial information and first posture information; in response to a first trigger operation, generating and displaying a second image based on the target object model and the first image, the second object feature of the target object in the second image matching the first object feature.
[0006] In a second aspect, an embodiment of the present disclosure provides an image generating device, comprising: an acquisition module for acquiring a target object model, wherein the target object model is generated based on the image of the target object; a display module for acquiring a first image on a content generation page, wherein the first image includes a first object feature of the target object, wherein the first object feature includes facial information and first posture information; a generation module for generating a second image based on the target object model and the first image in response to a first trigger operation; and a display module for displaying the second image, wherein the second object feature in the second image matches the first object feature.
[0007] In a third aspect, an embodiment of the present disclosure provides an electronic device comprising a processor, a memory, and a program or instruction stored in the memory and executable on the processor, wherein the program or instruction, when executed by the processor, implements the steps of the method of the first aspect.
[0008] In a fourth aspect, an embodiment of the present disclosure provides a readable storage medium storing a program or instruction, which, when executed by a processor, implements the steps of the image generation method of the first aspect.
[0009] In a fifth aspect, an embodiment of the present disclosure provides a chip, which includes a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the steps of the image generation method of the first aspect.
[0010] In a sixth aspect, an embodiment of the present disclosure provides a computer program product, which is stored in a storage medium and is executed by at least one processor to implement the image generation method of the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS
[0011] FIG1 is a schematic diagram showing a flow chart of an image generation method provided by an embodiment of the present disclosure;
[0012] FIG2 shows one of the schematic diagrams of a content generation page provided in some embodiments of the present disclosure;
[0013] FIG3 shows a second schematic diagram of a content generation page provided in some embodiments of the present disclosure;
[0014] FIG4 shows a third schematic diagram of a content generation page provided in some embodiments of the present disclosure;
[0015] FIG5 shows a fourth schematic diagram of a content generation page provided in some embodiments of the present disclosure;
[0016] FIG6 shows a fifth schematic diagram of a content generation page provided in some embodiments of the present disclosure;
[0017] FIG7 shows a sixth schematic diagram of a content generation page provided in some embodiments of the present disclosure;
[0018] FIG8 shows a seventh schematic diagram of a content generation page provided in some embodiments of the present disclosure;
[0019] FIG9 shows a structural block diagram of an image generating apparatus provided by an embodiment of the present disclosure;
[0020] FIG10 shows a structural block diagram of an electronic device according to some embodiments of the present disclosure; and
[0021] FIG11 shows a schematic diagram of the hardware structure of an electronic device provided to implement some embodiments of the present disclosure. DETAILED DESCRIPTION
[0022] The following will be combined with the accompanying drawings in the embodiments of the present disclosure to clearly describe the technical solutions in the embodiments of the present disclosure. Obviously, the embodiments described are part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments of the present disclosure, all other embodiments obtained by ordinary technicians in this field are within the scope of protection of the present disclosure.
[0023] The terms "first", "second", etc. in the specification and claims of the present disclosure are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the terms used in this way are interchangeable where appropriate, so that the embodiments of the present disclosure can be implemented in an order other than those illustrated or described herein, and the objects distinguished by "first", "second", etc. are generally of the same type, and do not limit the number of objects. For example, the first object can be one or more. In addition, "and / or" in the specification and claims represents at least one of the connected objects, and the character " / " generally indicates that the objects associated with each other are in an "or" relationship.
[0024] The image generation method, image generation device, electronic device, and readable storage medium provided by the embodiments of the present disclosure are described in detail below with reference to Figures 1 to 11 through specific embodiments and their application scenarios.
[0025] An image generation method is provided in an embodiment of the present disclosure. FIG1 shows a flow chart of the image generation method provided in an embodiment of the present disclosure. As shown in FIG1 , the image generation method includes:
[0026] Step 102, obtaining a target object model, where the target object model is generated based on the image of the target object;
[0027] In this embodiment, the target object model is a Lora model obtained by pre-training, and the Lora model can be obtained by training based on media resources including the image of the target object. It should be noted that the target object can be a portrait.
[0028] Exemplarily, the target object is photographed at multiple angles to obtain multiple target object images, and the target object model is trained using the multiple photographed target object images.
[0029] Exemplarily, video frames including the target object are extracted from the video resources of the target object, and the target object model is trained using multiple video frames including the target object.
[0030] Step 104: acquiring a first image on the content generation page, where the first image includes first object features of the target object, and the first object features include first facial information and first posture information;
[0031] In this embodiment, the first image may be a first image of the target object, or may be a first image uploaded by a user and including the target object. The first object features are features of the target object, including first facial information and first posture information of the target object. The first facial information is information obtained by recognizing the facial features of the target object in the first image, and the first posture information is information obtained by recognizing the torso posture of the target object in the first image.
[0032] Exemplarily, hierarchical recognition is performed on the first image to identify first facial information and first posture information of a target object in a foreground area of the first image, and background information of a background area of the first image.
[0033] Step 106 : In response to the first trigger operation, generate and display a second image based on the target object model and the first image, wherein the second object feature of the target object in the second image matches the first object feature.
[0034] In this embodiment, a first trigger operation is used to trigger the update of the first image to a second image, where the second image is a creative image generated based on the first image and a target object model. The second object feature includes portrait feature information in the generated second image. Exemplarily, the second object feature includes at least one of the following: second facial information and second posture information in the second image. The second object feature matches the first object feature in the first image, i.e., the second facial information in the second object feature matches the first facial information, and the second posture information in the second object feature matches the first posture information. The background area in the second image is generated based on the association between the first and second facial information.
[0035] It should be noted that the first trigger operation can be a user's trigger operation on a virtual operation control, a user's trigger operation on a physical button, or an operation such as voice input or gesture input, which is not limited here.
[0036] Figure 2 shows one of the schematic diagrams of the content generation page provided in some embodiments of the present disclosure. As shown in Figure 2, a first image 202 is displayed in the content generation page. The user clicks the "Creative" button 204 in the content generation page, and a second image 206 is displayed in the content generation page. The second object feature in the second image 206 matches the posture information and facial information of the first object feature in the first image 202.
[0037] In the embodiment of the present disclosure, after the user takes or uploads a first image, the first image is displayed on the content page. The first trigger operation can trigger the generation and display of a second image through the target object model and the first image, so that the second object features and the face and posture of the first object features are matched with the first object features, and the first image can be creatively superimposed based on the first facial information and the second posture information, so that the generated second image can retain the relevant information of the target object in the first image, thereby improving the imaging effect of the second image and the user's control over the second image.
[0038] In some embodiments of the present disclosure, optionally, in response to the first trigger operation, generating and displaying the second image based on the target object model and the first image includes:
[0039] generating and displaying a second image based on the first facial information, the first posture information, and the target object model, the second image including image configuration information;
[0040] The image configuration information includes at least one of the following: second posture information, expression information, facial orientation information, clothing information, and background information of the second image.
[0041] In this embodiment, the image configuration information is the configuration information in the second image generated based on the first image, that is, the creative content superimposed on the first image to generate the second image matches the image configuration information, and the image configuration information is the configuration information generated based on the first facial information and the second facial information.
[0042] For example, by inputting the first and second facial information into an AIGC (AI-Generated Content) model, corresponding image configuration information can be generated. Specifically, for example, the first posture information can be used to generate the second posture information in the second image, and the first facial information and the first posture information can be used to generate facial orientation information, clothing information, and background information of the second image.
[0043] In this embodiment, the target object model includes image information of the target object. The second image is generated by using the target object model, the first facial information and the first posture information, so that the target object in the second image can be closer to the image information in the target object model.
[0044] In the embodiment of the present disclosure, a second image is generated by combining a target object model acquired in advance and the first facial information and first posture information in the first image, so that the image configuration information in the second image is information generated based on the first facial information and the first posture information, thereby further improving the degree of matching between the second image and the first image.
[0045] In some embodiments of the present disclosure, the second facial information of the target object in the second image is associated with the first facial information and the target object model; and / or the background information in the second image is associated with the first facial information and the first posture information; and / or the second posture information in the second image is associated with the first posture information.
[0046] In this embodiment, the second facial information of the target object in the second image is facial information generated based on the first facial information in the first image and the target object model, thereby improving the matching degree between the second facial information and the first facial information.
[0047] In this embodiment, the background information in the second image includes image information of the background area of the second image, which is background image information generated based on the first facial information and first posture information in the first image, so that the background area in the second image matches the first facial information and / or second posture information.
[0048] In this embodiment, the second posture information in the second image is posture information generated based on the first posture information in the first image, so that the posture of the target object in the second image matches that of the target object in the first image.
[0049] Exemplarily, the AIGC model generates second facial information in the second image based on the extracted first facial information and the target object model, generates background information of the background area in the second image based on the first facial information and the first posture information, and determines second posture information of the target object in the second image based on the first posture information.
[0050] In the embodiment of the present disclosure, second facial information, second posture information and background information in the second image can be generated based on the first facial information, first posture information and target object model, further improving the matching degree between the second image and the first image, as well as the imaging effect of the second image.
[0051] In some embodiments of the present disclosure, before receiving the first trigger operation, the method further includes:
[0052] Displaying at least two first controls on the content generation page, where the at least two first controls are respectively used to determine at least two pieces of first style information;
[0053] receiving a second trigger operation on a target control among the at least two first controls;
[0054] In response to a second trigger operation, determining second style information from the at least two first style information;
[0055] In response to a first trigger operation, generating and displaying a second image based on the target object model and the first image, including:
[0056] A second image is generated and displayed based on the second style information, the first facial information, the first posture information, and the target object model.
[0057] In this embodiment, a first control is displayed on a content generation page. The first control is used to determine the first style information required to generate a second image. The number of first controls is at least two. The user performs a second trigger operation on a target control among the at least two first controls, thereby selecting the second style information corresponding to the target control as the style information for generating the second image.
[0058] FIG3 shows a second schematic diagram of a content generation page provided in some embodiments of the present disclosure. As shown in FIG3 , a first image 302 and three first controls 304 are displayed on the content generation page. Preview images corresponding to the first style information are displayed in the first controls 304. The user clicks and selects a target control among the three first controls 304 to determine the second style information required to generate the second image. The content generation page also includes a capture control 306 and an album control 308. The user clicks the capture control 306 to capture the first image 302, and the first image 302 is displayed on the content generation page. The user clicks the album control 308 to select an album image from the album as the first image 302, and the first image 302 is displayed on the content generation page.
[0059] In this embodiment, before the user generates the second image by performing the first trigger operation, the user can select the second style information required for generating the second image by performing the second trigger operation on a target control among the at least two first controls. During the process of generating the second image based on the first image and the target object model, image configuration information for the second image is generated based on the second style information, thereby facilitating the user to adjust the overall image style of the second image.
[0060] It should be noted that the second trigger operation is the operation input performed by the user on the target control of at least two first controls. The operation input can be a gesture input such as long press input, short press input, sliding input, etc., which is not limited here.
[0061] Exemplarily, different first style information corresponds to different AIGC style templates. After determining the second style information to be called from the plurality of first style information, the second image is generated using the corresponding style template, the first facial information, and the first posture information.
[0062] In an embodiment of the present disclosure, before triggering the generation of the second image, the user can perform a second trigger operation on the second control of at least two first controls to select the second style information required to generate the second image, so that the generated and displayed second image matches the second style information selected by the user, allowing the user to flexibly configure the second image to be generated.
[0063] In some embodiments of the present disclosure, in response to a first trigger operation, before generating and displaying a second image based on a target object model and a first image, an image generation method includes:
[0064] In response to the third trigger operation, a first marker is displayed in the first image, wherein the first marker is used to display the first posture information.
[0065] In the disclosed embodiment, a first identifier is displayed in a first image, and the first identifier can display first posture information extracted from the first image. Before the user generates and displays the second image through a first trigger operation, the content generation page displays the first image. The user then displays the first identifier on the content display page by performing a third trigger operation. It should be noted that the third trigger operation can be a user triggering a virtual control, a user triggering a physical button, or an operation such as voice input or gesture input, without limitation herein.
[0066] Exemplarily, the first mark may be a line mark displayed in a floating manner on the first image.
[0067] Figure 4 shows a third schematic diagram of a content generation page provided in some embodiments of the present disclosure. As shown in Figure 4, a first image 402 is displayed in the content generation page. By double-clicking the first image 402, the user displays a line segment marker 404 in the first image 402. The line segment marker 404 can be displayed in a floating manner on the target object in the first image 402 to display the first posture information of the target object.
[0068] In an embodiment of the present disclosure, before generating a second image through a first image and a target object model, a user can trigger the display of a first identifier in the first image through a third trigger operation. The first identifier can display the recognized first posture information to the user, allowing the user to view the first posture information before triggering the generation and display of the second image.
[0069] In some embodiments of the present disclosure, in response to the first trigger operation, before generating and displaying the second image based on the target object model and the first image, the image generation method further includes:
[0070] receiving a fourth triggering operation on the first image;
[0071] In response to a fourth trigger operation, a target selection area is displayed in the first image, where the target selection area is used to select an area of the first image;
[0072] In response to a first trigger operation, generating and displaying a second image based on the target object model and the first image, including:
[0073] determining first image content in a first image region;
[0074] generating third image content based on the target object model and second image content in the second image region, where the second image region is an image region in the first image excluding the first image region;
[0075] A second image is generated and displayed based on the first image content and the third image content.
[0076] In this embodiment, the fourth triggering operation is used to trigger the display of a target selection in the first image. The target selection is an image area identified through image recognition, and the image content within the target selection is mutually related image content. It should be noted that the fourth triggering operation is an operation input performed by the user on the first image. This operation input can be a gesture input such as a long press input, a short press input, a sliding input, etc., and is not limited here.
[0077] For example, the image content displayed in the target selection area may be the foreground area in the first image, including the target object, or the image content displayed in the target selection area may be the background area in the first image.
[0078] In this embodiment, the first image area is the image area selected within the target selection area in the first image, and the second image area is the image area outside the target selection area in the first image. The first image content is the image content within the first image area, and this first image content is retained in the generated second image. The second image content is the image content within the second image area, and the third image content in the second image is generated based on this second image content.
[0079] Specifically, after the user generates the target selection through the fourth trigger operation, the user triggers the generation and display of the second image through the first trigger operation, then the first image content in the target selection in the first image is retained in the second image, and the third image content is generated based on the target object model and the second image content in the second image area in the first image, and the third image content is other image content in the second image except the first image content.
[0080] FIG5 illustrates a fourth schematic diagram of a content generation page provided in some embodiments of the present disclosure. As shown in FIG5 , a first image 502 is displayed on the content generation page. A user long-presses first image 502, and a target selection area 504 is displayed in first image 502. Target selection area 504 selects the portrait area in first image 502. The user clicks "Creative" button 506, and a generated second image 508 is displayed on the content generation page. Second image 508 retains the portrait area selected by target selection area 504, while the remaining area is the newly generated image content.
[0081] In an embodiment of the present disclosure, the user can display a target selection in the first image by performing a fourth trigger operation on the first image displayed on the content generation page, and display the first image content retained in the first image area in the target selection. At this time, the user triggers the generation and display of the second image through the first trigger operation, and can retain the first image content in the second image, and generate the third image content based on the second image content in the second image area, so that the user can independently choose to retain part of the original image content in the first image, further improving the user's flexibility in configuring the image content in the second image.
[0082] In some embodiments of the present disclosure, in response to the fourth trigger operation, after displaying the target selection area in the first image, the method further includes:
[0083] Receive the fifth trigger operation on the target selection;
[0084] In response to the fifth trigger operation, the coverage of the target selection area in the first image is adjusted to update the first image area.
[0085] In the disclosed embodiment, the fifth trigger operation is used to trigger adjustment of the coverage of the target selection. When the target selection is displayed in the first image, the user performs the fifth trigger operation on the target selection to adjust the coverage of the target selection in the first image. After the adjustment, the image content selected by the target selection is associated with each other.
[0086] Exemplarily, the target selection area covers all target objects in the first image, and the user can make the target selection area cover part of the target objects in the first image through the fifth trigger operation.
[0087] Exemplarily, the target selection area covers the entire background area in the first image, and the user can make the target selection area cover part of the background area in the first image through the fifth trigger operation.
[0088] Figure 6 shows the fifth schematic diagram of the content generation page provided in some embodiments of the present disclosure. As shown in Figure 6, a first image 602 is displayed in the content generation page, and a target selection area 604 is displayed in the first image 602. The target selection area 604 selects a portion of the portrait area. The user can drag the edge position of the target selection area 604 to make the target selection area 604 select the entire portrait area.
[0089] In an embodiment of the present disclosure, when a target selection area is displayed in the first image, the user can adjust the frame selection range of the target selection area in the first image through the fifth trigger operation, thereby flexibly setting the first image content that needs to be retained in the second image, further improving the user's flexibility in configuring the image content in the second image.
[0090] In some embodiments of the present disclosure, the first image area includes any one of the following:
[0091] An image area corresponding to at least part of the target object and an image area corresponding to at least part of the background image features.
[0092] In this embodiment, the first image area is the image area in the target selection area, that is, the image area corresponding to at least part of the target object in the first image can be selected through the target selection area, and the image area corresponding to at least part of the background image features in the first image can also be selected.
[0093] In the disclosed embodiment, the target selection area can select the area where the target object is located in the first image, and can also select the area where the background image features are located in the first image, so that the user can flexibly select the image content to be retained in the first image.
[0094] In some embodiments of the present disclosure, optionally, in response to the first triggering operation, after generating and displaying the second image based on the target object model and the first image, the image generation method further includes:
[0095] Displaying a second control on the content generation page;
[0096] receiving a sixth trigger operation on the second control;
[0097] In response to a sixth trigger operation, second gesture information in the second image is determined based on the third gesture information, the third gesture information being different from the first gesture information.
[0098] In the disclosed embodiment, the second control is triggered by the sixth trigger operation to update the second posture information in the second image using the third posture information, so that the second posture information in the second image no longer matches the first posture information in the first image, allowing the user to conveniently switch whether the first posture information in the first image is retained in the second image. It should be noted that the fourth trigger operation is the operation input performed by the user on the second control, which can be a gesture input such as a long press input, a short press input, a sliding input, etc., which is not limited here.
[0099] Exemplarily, the third posture information may be posture information generated based on the first facial information or background information in the first image, or may be posture information randomly selected from a posture information library, or may be posture information in the second image generated historically.
[0100] Figure 7 shows a sixth schematic diagram of a content generation page provided in some embodiments of the present disclosure. As shown in Figure 7, a generated second image 702 and a posture holding control 704 are displayed in the content generation page. By clicking the posture holding control 704, the user can trigger the update of the second posture information in the second image 702 based on the third posture information, so that the posture of the target object in the updated second image 702 changes.
[0101] In an embodiment of the present disclosure, the user can perform a sixth trigger operation on the second control to trigger the updating of the second posture information in the second image through the third posture information, so that the user can flexibly choose whether the target object in the generated and displayed second image maintains the posture of the target object in the first image.
[0102] In some embodiments of the present disclosure, the sixth trigger operation includes a first sub-trigger operation and a second sub-trigger operation;
[0103] In response to a sixth trigger operation, determining second posture information in the second image based on the third posture information includes:
[0104] In response to a first sub-trigger operation on the second control, displaying at least two fourth images;
[0105] receiving a second sub-trigger operation on a target image in at least two fourth images;
[0106] In response to the second sub-trigger operation, extracting third posture information from the target image;
[0107] The second posture information is determined according to the third posture information.
[0108] In the disclosed embodiment, the sixth trigger operation includes a first sub-trigger operation for triggering the display of a fourth image, and a second sub-trigger operation for selecting a target image in the fourth image and extracting the third posture information in the target image. By performing the first sub-trigger operation on the second control, the user displays multiple fourth images. The fourth image can be an image in an album or a historically generated second image. By performing the second sub-trigger operation on a target image in the fourth image, the user can extract the third posture information in the target image and update the second posture information in the second image based on the third posture information.
[0109] FIG8 illustrates a seventh schematic diagram of a content generation page provided in some embodiments of the present disclosure. As shown in FIG8 , a generated second image 802 and a posture switching control 804 are displayed on the content generation page. A user clicks on the posture switching control 804 to display a floating window 806 on the content generation page. The floating window 806 displays multiple fourth images 808. The user clicks on a target image in the fourth image 808 to extract third posture information from the target image, and updates the second posture information in the second image 802 based on the third posture information, causing the posture of the target object in the updated second image 802 to change.
[0110] In an embodiment of the present disclosure, a user can trigger the display of at least two fourth images by performing a first sub-trigger operation on the second control, and update the second posture information in the already generated second image based on the third posture information in the target image selected from the at least two fourth images, thereby realizing the reuse of the third posture information in the fourth image and further improving the flexibility of configuring the posture of the target object in the second image.
[0111] The image generation method provided in the embodiment of the present disclosure may be executed by an image generation device. In the embodiment of the present disclosure, the image generation device provided in the embodiment of the present disclosure is described by taking the image generation device executing the image generation method as an example.
[0112] In some embodiments of the present disclosure, an image generating apparatus is provided. FIG9 shows a structural block diagram of the image generating apparatus provided by an embodiment of the present disclosure. As shown in FIG9 , the image generating apparatus 900 includes:
[0113] An acquisition module 902 is used to acquire a target object model, where the target object model is generated based on the image of the target object;
[0114] A display module 904 is configured to obtain a first image on a content generation page, where the first image includes a first object feature of a target object, where the first object feature includes facial information and first posture information;
[0115] A generating module 906 is configured to generate a second image based on the target object model and the first image in response to the first trigger operation;
[0116] The display module 904 is configured to display the second image, wherein the second object feature in the second image matches the first object feature.
[0117] In the embodiment of the present disclosure, after the user takes or uploads a first image, the first image is displayed on the content page. The first trigger operation can trigger the generation and display of a second image through the target object model and the first image, so that the second object features and the face and posture of the first object features are matched with the first object features, and the first image can be creatively superimposed based on the first facial information and the second posture information, so that the generated second image can retain the relevant information of the target object in the first image, thereby improving the imaging effect of the second image and the user's control over the second image.
[0118] In some embodiments of the present disclosure, optionally, the generating module 906 is configured to generate a second image according to the first facial information, the first posture information, and the target object model, where the second image includes image configuration information;
[0119] Display module 904, configured to display a second image;
[0120] The image configuration information includes at least one of the following: second posture information, expression information, facial orientation information, clothing information, and background information of the second image.
[0121] In this embodiment, the image configuration information is the configuration information in the second image generated based on the first image, that is, the creative content superimposed on the first image to generate the second image matches the image configuration information, and the image configuration information is the configuration information generated based on the first facial information and the second facial information.
[0122] In the embodiment of the present disclosure, a second image is generated by combining a target object model acquired in advance and the first facial information and first posture information in the first image, so that the image configuration information in the second image is information generated based on the first facial information and the first posture information, thereby further improving the degree of matching between the second image and the first image.
[0123] In some embodiments of the present disclosure, second facial information of the target object in the second image is associated with the first facial information and the target object model; and / or
[0124] Background information in the second image is associated with the first facial information and the first posture information; and / or
[0125] The second posture information in the second image is associated with the first posture information.
[0126] In this embodiment, the second facial information of the target object in the second image is facial information generated based on the first facial information in the first image and the target object model, thereby improving the matching degree between the second facial information and the first facial information.
[0127] In this embodiment, the background information in the second image includes image information of the background area of the second image, which is background image information generated based on the first facial information and first posture information in the first image, so that the background area in the second image matches the first facial information and / or second posture information.
[0128] In this embodiment, the second posture information in the second image is posture information generated based on the first posture information in the first image, so that the posture of the target object in the second image matches that of the target object in the first image.
[0129] In the embodiment of the present disclosure, second facial information, second posture information and background information in the second image can be generated based on the first facial information, first posture information and target object model, further improving the matching degree between the second image and the first image, as well as the imaging effect of the second image.
[0130] In some embodiments of the present disclosure, the image generating apparatus 900 further includes:
[0131] a determination module, configured to display at least two first controls on the content generation page, wherein the at least two first controls are respectively used to determine at least two pieces of first style information;
[0132] A receiving module, configured to receive a second triggering operation on a target control among the at least two first controls;
[0133] a determining module, configured to determine, in response to a second triggering operation, second style information among the at least two first style information;
[0134] a generating module 906 for generating a second image based on the second style information, the first facial information, the first posture information, and the target object model;
[0135] The display module 904 is configured to display the second image.
[0136] In this embodiment, a first control is displayed on a content generation page. The first control is used to determine the first style information required to generate a second image. The number of first controls is at least two. The user performs a second trigger operation on a target control among the at least two first controls, thereby selecting the second style information corresponding to the target control as the style information for generating the second image.
[0137] In this embodiment, before the user generates the second image by performing the first trigger operation, the user can select the second style information required for generating the second image by performing the second trigger operation on a target control among the at least two first controls. During the process of generating the second image based on the first image and the target object model, image configuration information for the second image is generated based on the second style information, thereby facilitating the user to adjust the overall image style of the second image.
[0138] In an embodiment of the present disclosure, before triggering the generation of the second image, the user can perform a second trigger operation on the second control of at least two first controls to select the second style information required to generate the second image, so that the generated and displayed second image matches the second style information selected by the user, allowing the user to flexibly configure the second image to be generated.
[0139] In some embodiments of the present disclosure, the display module 904 is configured to display a first identifier in the first image in response to a third trigger operation, wherein the first identifier is used to display the first posture information.
[0140] In the disclosed embodiment, a first identifier is displayed in a first image, and the first identifier can display first posture information extracted from the first image. Before the user generates and displays the second image through a first trigger operation, the content generation page displays the first image. The user then displays the first identifier on the content display page by performing a third trigger operation. It should be noted that the third trigger operation can be a user triggering a virtual control, a user triggering a physical button, or an operation such as voice input or gesture input, without limitation herein.
[0141] In an embodiment of the present disclosure, before generating a second image through a first image and a target object model, a user can trigger the display of a first identifier in the first image through a third trigger operation. The first identifier can display the recognized first posture information to the user, allowing the user to view the first posture information before triggering the generation and display of the second image.
[0142] In some embodiments of the present disclosure, the image generating apparatus 900 further includes:
[0143] A receiving module, configured to receive a fourth triggering operation on the first image;
[0144] A display module 904 is configured to display a target selection area in the first image in response to a fourth trigger operation, where the target selection area is used to select an area of the first image;
[0145] A determination module, configured to determine first image content in a first image area;
[0146] A generating module 906 is configured to generate third image content based on the target object model and the second image content in the second image region, where the second image region is an image region in the first image excluding the first image region;
[0147] A generating module 906, configured to generate a second image based on the first image content and the third image content;
[0148] The display module 904 is configured to display the second image.
[0149] In this embodiment, the fourth triggering operation is used to trigger the display of a target selection in the first image. The target selection is an image area identified through image recognition, and the image content within the target selection is mutually related image content. It should be noted that the fourth triggering operation is an operation input performed by the user on the first image. This operation input can be a gesture input such as a long press input, a short press input, a sliding input, etc., and is not limited here.
[0150] In this embodiment, the first image area is the image area selected within the target selection area in the first image, and the second image area is the image area outside the target selection area in the first image. The first image content is the image content within the first image area, and this first image content is retained in the generated second image. The second image content is the image content within the second image area, and the third image content in the second image is generated based on this second image content.
[0151] In an embodiment of the present disclosure, the user can display a target selection in the first image by performing a fourth trigger operation on the first image displayed on the content generation page, and display the first image content retained in the first image area in the target selection. At this time, the user triggers the generation and display of the second image through the first trigger operation, and can retain the first image content in the second image, and generate the third image content based on the second image content in the second image area, so that the user can independently choose to retain part of the original image content in the first image, further improving the user's flexibility in configuring the image content in the second image.
[0152] In some embodiments of the present disclosure, the image generating apparatus 900 further includes:
[0153] A receiving module, configured to receive a fifth trigger operation on a target selection area;
[0154] The adjustment module is configured to adjust the coverage of the target selection area in the first image in response to the fifth trigger operation, so as to update the first image area.
[0155] In the disclosed embodiment, the fifth trigger operation is used to trigger adjustment of the coverage of the target selection. When the target selection is displayed in the first image, the user performs the fifth trigger operation on the target selection to adjust the coverage of the target selection in the first image. After the adjustment, the image content selected by the target selection is associated with each other.
[0156] In an embodiment of the present disclosure, when a target selection area is displayed in the first image, the user can adjust the frame selection range of the target selection area in the first image through the fifth trigger operation, thereby flexibly setting the first image content that needs to be retained in the second image, further improving the user's flexibility in configuring the image content in the second image.
[0157] In some embodiments of the present disclosure, the first image area includes any one of the following:
[0158] An image area corresponding to at least part of the target object and an image area corresponding to at least part of the background image features.
[0159] In this embodiment, the first image area is the image area in the target selection area, that is, the image area corresponding to at least part of the target object in the first image can be selected through the target selection area, and the image area corresponding to at least part of the background image features in the first image can also be selected.
[0160] In the disclosed embodiment, the target selection area can select the area where the target object is located in the first image, and can also select the area where the background image features are located in the first image, so that the user can flexibly select the image content to be retained in the first image.
[0161] In some embodiments of the present disclosure, optionally, the display module 904 is configured to display a second control on the content generation page;
[0162] A receiving module, configured to receive a sixth triggering operation on the second control;
[0163] The determining module is configured to determine, in response to a sixth trigger operation, second posture information in the second image based on the third posture information, where the third posture information is different from the first posture information.
[0164] In the disclosed embodiment, the second control is triggered by the sixth trigger operation to update the second posture information in the second image using the third posture information, so that the second posture information in the second image no longer matches the first posture information in the first image, allowing the user to conveniently switch whether the first posture information in the first image is retained in the second image. It should be noted that the fourth trigger operation is the operation input performed by the user on the second control, which can be a gesture input such as a long press input, a short press input, a sliding input, etc., which is not limited here.
[0165] In an embodiment of the present disclosure, the user can perform a sixth trigger operation on the second control to trigger the updating of the second posture information in the second image through the third posture information, so that the user can flexibly choose whether the target object in the generated and displayed second image maintains the posture of the target object in the first image.
[0166] In some embodiments of the present disclosure, the sixth trigger operation includes a first sub-trigger operation and a second sub-trigger operation;
[0167] A display module 904 is configured to display at least two fourth images in response to a first sub-trigger operation on the second control;
[0168] a receiving module, configured to receive a second sub-trigger operation on a target image in at least two fourth images;
[0169] The image generating device 900 includes:
[0170] an extraction module, configured to extract third posture information from the target image in response to the second sub-trigger operation;
[0171] The determining module is configured to determine the second posture information according to the third posture information.
[0172] In the disclosed embodiment, the sixth trigger operation includes a first sub-trigger operation for triggering the display of a fourth image, and a second sub-trigger operation for selecting a target image in the fourth image and extracting the third posture information in the target image. By performing the first sub-trigger operation on the second control, the user displays multiple fourth images. The fourth image can be an image in an album or a historically generated second image. By performing the second sub-trigger operation on a target image in the fourth image, the user can extract the third posture information in the target image and update the second posture information in the second image based on the third posture information.
[0173] In an embodiment of the present disclosure, a user can trigger the display of at least two fourth images by performing a first sub-trigger operation on the second control, and update the second posture information in the already generated second image based on the third posture information in the target image selected from the at least two fourth images, thereby realizing the reuse of the third posture information in the fourth image and further improving the flexibility of configuring the posture of the target object in the second image.
[0174] The image generating device in the embodiment of the present disclosure may be an electronic device or a component in the electronic device, such as an integrated circuit or a chip. The electronic device may be a terminal or other device other than a terminal. For example, the electronic device may be a mobile phone, a tablet computer, a laptop computer, a PDA, an in-vehicle electronic device, a mobile Internet device (MID), an augmented reality (AR) / virtual reality (VR) device, a robot, a wearable device, an ultra-mobile personal computer (UMPC), a netbook or a personal digital assistant (PDA), etc. It may also be a server, a network attached storage (NAS), a personal computer (PC), a television (TV), a teller machine or a self-service machine, etc., and the embodiment of the present disclosure does not specifically limit it.
[0175] The image generation device in the embodiment of the present disclosure may be a device having an operating system. The operating system may be an Android operating system, an iOS operating system, or other possible operating systems, which are not specifically limited in the embodiment of the present disclosure.
[0176] The image generation device provided by the embodiment of the present disclosure can implement each process implemented by the above method embodiment, and to avoid repetition, it will not be described here.
[0177] Optionally, an embodiment of the present disclosure further provides an electronic device. Figure 10 shows a structural block diagram of an electronic device provided according to some embodiments of the present disclosure. As shown in Figure 10, the electronic device 1000 includes a processor 1002 and a memory 1004. The memory 1004 stores programs or instructions that can be run on the processor 1002. When the program or instructions are executed by the processor 1002, the various steps of the above-mentioned method embodiment are implemented and the same technical effect can be achieved. To avoid repetition, they are not repeated here.
[0178] It should be noted that the electronic devices in the embodiments of the present disclosure include the above-mentioned mobile electronic devices and non-mobile electronic devices.
[0179] FIG11 shows a schematic diagram of the hardware structure of an electronic device provided to implement some embodiments of the present disclosure.
[0180] The electronic device 1100 includes but is not limited to components such as a radio frequency unit 1101 , a network module 1102 , an audio output unit 1103 , an input unit 1104 , a sensor 1105 , a display unit 1106 , a user input unit 1107 , an interface unit 1108 , a memory 1109 , and a processor 1110 .
[0181] Those skilled in the art will appreciate that the electronic device 1100 may further include a power source (such as a battery) to power various components. The power source may be logically connected to the processor 1110 via a power management system, thereby enabling the power management system to manage charging, discharging, and power consumption. The electronic device structure shown in FIG11 does not limit the electronic device. The electronic device may include more or fewer components than shown, or may combine certain components, or have different component arrangements, which will not be described in detail here.
[0182] The processor 1110 is configured to obtain a target object model, where the target object model is generated based on an image of the target object;
[0183] The display unit 1106 is configured to obtain a first image on the content generation page, where the first image includes a first object feature of the target object, where the first object feature includes facial information and first posture information;
[0184] The processor 1110 is configured to generate a second image based on the target object model and the first image in response to a first trigger operation;
[0185] The display unit 1106 is configured to display a second image, wherein the second object feature in the second image matches the first object feature.
[0186] In the embodiment of the present disclosure, after the user takes or uploads a first image, the first image is displayed on the content page. The first trigger operation can trigger the generation and display of a second image through the target object model and the first image, so that the second object features and the face and posture of the first object features are matched with the first object features, and the first image can be creatively superimposed based on the first facial information and the second posture information, so that the generated second image can retain the relevant information of the target object in the first image, thereby improving the imaging effect of the second image and the user's control over the second image.
[0187] In some embodiments of the present disclosure, optionally, the processor 1110 is configured to generate a second image according to the first facial information, the first posture information, and the target object model, where the second image includes image configuration information;
[0188] Display unit 1106, configured to display a second image;
[0189] The image configuration information includes at least one of the following: second posture information, expression information, facial orientation information, clothing information, and background information of the second image.
[0190] In this embodiment, the image configuration information is the configuration information in the second image generated based on the first image, that is, the creative content superimposed on the first image to generate the second image matches the image configuration information, and the image configuration information is the configuration information generated based on the first facial information and the second facial information.
[0191] In the embodiment of the present disclosure, a second image is generated by combining a target object model acquired in advance and the first facial information and first posture information in the first image, so that the image configuration information in the second image is information generated based on the first facial information and the first posture information, thereby further improving the degree of matching between the second image and the first image.
[0192] In some embodiments of the present disclosure, the second facial information of the target object in the second image is associated with the first facial information and the target object model; and / or the background information in the second image is associated with the first facial information and the first posture information; and / or the second posture information in the second image is associated with the first posture information.
[0193] In this embodiment, the second facial information of the target object in the second image is facial information generated based on the first facial information in the first image and the target object model, thereby improving the matching degree between the second facial information and the first facial information.
[0194] In this embodiment, the background information in the second image includes image information of the background area of the second image, which is background image information generated based on the first facial information and first posture information in the first image, so that the background area in the second image matches the first facial information and / or second posture information.
[0195] In this embodiment, the second posture information in the second image is posture information generated based on the first posture information in the first image, so that the posture of the target object in the second image matches that of the target object in the first image.
[0196] In the embodiment of the present disclosure, second facial information, second posture information and background information in the second image can be generated based on the first facial information, first posture information and target object model, further improving the matching degree between the second image and the first image, as well as the imaging effect of the second image.
[0197] In some embodiments of the present disclosure, the processor 1110 is configured to display at least two first controls on the content generation page, where the at least two first controls are respectively used to determine at least two pieces of first style information;
[0198] The user input unit 1107 is configured to receive a second trigger operation on a target control among the at least two first controls;
[0199] Processor 1110, configured to determine, in response to a second trigger operation, second style information from the at least two first style information;
[0200] Processor 1110, configured to generate a second image based on the second style information, the first facial information, the first posture information, and the target object model;
[0201] The display unit 1106 is configured to display the second image.
[0202] In this embodiment, a first control is displayed on a content generation page. The first control is used to determine the first style information required to generate a second image. The number of first controls is at least two. The user performs a second trigger operation on a target control among the at least two first controls, thereby selecting the second style information corresponding to the target control as the style information for generating the second image.
[0203] In this embodiment, before the user generates the second image by performing the first trigger operation, the user can select the second style information required for generating the second image by performing the second trigger operation on a target control among the at least two first controls. During the process of generating the second image based on the first image and the target object model, image configuration information for the second image is generated based on the second style information, thereby facilitating the user to adjust the overall image style of the second image.
[0204] In an embodiment of the present disclosure, before triggering the generation of the second image, the user can perform a second trigger operation on the second control of at least two first controls to select the second style information required to generate the second image, so that the generated and displayed second image matches the second style information selected by the user, allowing the user to flexibly configure the second image to be generated.
[0205] In some embodiments of the present disclosure, the display unit 1106 is configured to display a first identifier in the first image in response to a third trigger operation, wherein the first identifier is configured to display the first posture information.
[0206] In the disclosed embodiment, a first identifier is displayed in a first image, and the first identifier can display first posture information extracted from the first image. Before the user generates and displays the second image through a first trigger operation, the content generation page displays the first image. The user then displays the first identifier on the content display page by performing a third trigger operation. It should be noted that the third trigger operation can be a user triggering a virtual control, a user triggering a physical button, or an operation such as voice input or gesture input, without limitation herein.
[0207] In an embodiment of the present disclosure, before generating a second image through a first image and a target object model, a user can trigger the display of a first identifier in the first image through a third trigger operation. The first identifier can display the recognized first posture information to the user, allowing the user to view the first posture information before triggering the generation and display of the second image.
[0208] In some embodiments of the present disclosure, the user input unit 1107 is configured to receive a fourth triggering operation on the first image;
[0209] The display unit 1106 is configured to display a target selection area in the first image in response to a fourth trigger operation, where the target selection area is used to select an area of the first image;
[0210] Processor 1110, configured to determine first image content in a first image area;
[0211] Processor 1110, configured to generate third image content based on the target object model and second image content in a second image region, where the second image region is an image region in the first image excluding the first image region;
[0212] Processor 1110, configured to generate a second image based on the first image content and the third image content;
[0213] The display unit 1106 is configured to display the second image.
[0214] In this embodiment, the fourth triggering operation is used to trigger the display of a target selection in the first image. The target selection is an image area identified through image recognition, and the image content within the target selection is mutually related image content. It should be noted that the fourth triggering operation is an operation input performed by the user on the first image. This operation input can be a gesture input such as a long press input, a short press input, a sliding input, etc., and is not limited here.
[0215] In this embodiment, the first image area is the image area selected within the target selection area in the first image, and the second image area is the image area outside the target selection area in the first image. The first image content is the image content within the first image area, and this first image content is retained in the generated second image. The second image content is the image content within the second image area, and the third image content in the second image is generated based on this second image content.
[0216] In an embodiment of the present disclosure, the user can display a target selection in the first image by performing a fourth trigger operation on the first image displayed on the content generation page, and display the first image content retained in the first image area in the target selection. At this time, the user triggers the generation and display of the second image through the first trigger operation, and can retain the first image content in the second image, and generate the third image content based on the second image content in the second image area, so that the user can independently choose to retain part of the original image content in the first image, further improving the user's flexibility in configuring the image content in the second image.
[0217] In some embodiments of the present disclosure, the user input unit 1107 is used to receive a fifth trigger operation on the target selection area;
[0218] The processor 1110 is configured to adjust the coverage of the target selection in the first image in response to the fifth trigger operation to update the first image area.
[0219] In the disclosed embodiment, the fifth trigger operation is used to trigger adjustment of the coverage of the target selection. When the target selection is displayed in the first image, the user performs the fifth trigger operation on the target selection to adjust the coverage of the target selection in the first image. After the adjustment, the image content selected by the target selection is associated with each other.
[0220] In an embodiment of the present disclosure, when a target selection area is displayed in the first image, the user can adjust the frame selection range of the target selection area in the first image through the fifth trigger operation, thereby flexibly setting the first image content that needs to be retained in the second image, further improving the user's flexibility in configuring the image content in the second image.
[0221] In some embodiments of the present disclosure, the first image area includes any one of the following:
[0222] An image area corresponding to at least part of the target object and an image area corresponding to at least part of the background image features.
[0223] In this embodiment, the first image area is the image area in the target selection area, that is, the image area corresponding to at least part of the target object in the first image can be selected through the target selection area, and the image area corresponding to at least part of the background image features in the first image can also be selected.
[0224] In the disclosed embodiment, the target selection area can select the area where the target object is located in the first image, and can also select the area where the background image features are located in the first image, so that the user can flexibly select the image content to be retained in the first image.
[0225] In some embodiments of the present disclosure, optionally, the display unit 1106 is configured to display a second control on the content generation page;
[0226] The user input unit 1107 is configured to receive a sixth trigger operation on the second control;
[0227] The user input unit 1107 is configured to determine, in response to a sixth trigger operation, second posture information in the second image based on the third posture information, where the third posture information is different from the first posture information.
[0228] In the disclosed embodiment, the second control is triggered by the sixth trigger operation to update the second posture information in the second image using the third posture information, so that the second posture information in the second image no longer matches the first posture information in the first image, allowing the user to conveniently switch whether the first posture information in the first image is retained in the second image. It should be noted that the fourth trigger operation is the operation input performed by the user on the second control, which can be a gesture input such as a long press input, a short press input, a sliding input, etc., which is not limited here.
[0229] In an embodiment of the present disclosure, the user can perform a sixth trigger operation on the second control to trigger the updating of the second posture information in the second image through the third posture information, so that the user can flexibly choose whether the target object in the generated and displayed second image maintains the posture of the target object in the first image.
[0230] In some embodiments of the present disclosure, the sixth trigger operation includes a first sub-trigger operation and a second sub-trigger operation;
[0231] A display unit 1106 is configured to display at least two fourth images in response to the first sub-trigger operation on the second control;
[0232] The user input unit 1107 is configured to receive a second sub-trigger operation on a target image in the at least two fourth images;
[0233] Processor 1110, configured to extract third posture information from the target image in response to the second sub-trigger operation;
[0234] The processor 1110 is configured to determine the second posture information according to the third posture information.
[0235] In the disclosed embodiment, the sixth trigger operation includes a first sub-trigger operation for triggering the display of a fourth image, and a second sub-trigger operation for selecting a target image in the fourth image and extracting the third posture information in the target image. By performing the first sub-trigger operation on the second control, the user displays multiple fourth images. The fourth image can be an image in an album or a historically generated second image. By performing the second sub-trigger operation on a target image in the fourth image, the user can extract the third posture information in the target image and update the second posture information in the second image based on the third posture information.
[0236] In an embodiment of the present disclosure, a user can trigger the display of at least two fourth images by performing a first sub-trigger operation on the second control, and update the second posture information in the already generated second image based on the third posture information in the target image selected from the at least two fourth images, thereby realizing the reuse of the third posture information in the fourth image and further improving the flexibility of configuring the posture of the target object in the second image.
[0237] It should be understood that in the embodiment of the present disclosure, the input unit 1104 may include a graphics processing unit (GPU) 11041 and a microphone 11042, and the graphics processor 11041 processes the image data of the static picture or video obtained by the image capture device (such as a camera) in the video capture mode or the image capture mode. The display unit 1106 may include a display panel 11061, and the display panel 11061 may be configured in the form of a liquid crystal display, an organic light emitting diode, etc. The user input unit 1107 includes a touch panel 11071 and at least one of the other input devices 11072. The touch panel 11071 is also called a touch screen. The touch panel 11071 may include two parts: a touch detection device and a touch controller. Other input devices 11072 may include, but are not limited to, a physical keyboard, function keys (such as volume control keys, switch keys, etc.), a trackball, a mouse, and an operating stick, which will not be repeated here.
[0238] The memory 1109 can be used to store software programs and various data. The memory 1109 may mainly include a first storage area for storing programs or instructions and a second storage area for storing data, wherein the first storage area may store an operating system, applications or instructions required for at least one function (such as a sound playback function, an image playback function, etc.). In addition, the memory 1109 may include a volatile memory or a non-volatile memory, or the memory 1109 may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be random access memory (RAM), static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct RAM bus random access memory (DRRAM). The memory 1109 in the embodiments of the present disclosure includes, but is not limited to, these and any other suitable types of memory.
[0239] Processor 1110 may include one or more processing units. Optionally, processor 1110 integrates an application processor and a modem processor. The application processor primarily handles operations related to the operating system, user interface, and application programs, while the modem processor primarily processes wireless communication signals, such as a baseband processor. It is understood that the modem processor may not be integrated into processor 1110.
[0240] The embodiment of the present disclosure also provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, the various processes of the above-mentioned image generation method embodiment are implemented and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.
[0241] The processor is the processor in the electronic device in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a computer read-only memory ROM, a random access memory RAM, a magnetic disk or an optical disk.
[0242] The embodiment of the present disclosure further provides a chip, which includes a processor and a communication interface. The communication interface and the processor are coupled. The processor is used to run programs or instructions to implement the various processes of the above-mentioned image generation method embodiment and can achieve the same technical effect. To avoid repetition, it will not be repeated here.
[0243] It should be understood that the chip mentioned in the embodiments of the present disclosure can also be called a system-level chip, a system chip, a chip system, or a system-on-chip chip, etc.
[0244] The embodiment of the present disclosure provides a computer program product, which is stored in a storage medium. The program product is executed by at least one processor to implement the various processes of the above-mentioned image generation method embodiment and can achieve the same technical effect. To avoid repetition, it will not be repeated here.
[0245] It should be noted that, in this article, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a..." does not exclude the presence of other identical elements in the process, method, article or device comprising the element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present disclosure is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in the opposite order according to the functions involved. For example, the described method may be performed in an order different from that described, and various steps may also be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.
[0246] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus the necessary general hardware platform, and of course, by hardware, but in many cases the former is a better embodiment. Based on this understanding, the technical solution of the present disclosure can essentially be embodied in the form of a computer software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), including a number of instructions for enabling a terminal (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods of the various embodiments of the present disclosure.
[0247] The embodiments of the present disclosure are described above in conjunction with the accompanying drawings, but the present disclosure is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present disclosure, ordinary technicians in this field can also make many forms without departing from the scope of protection of the purpose of the present disclosure and the claims, all of which are protected by the present disclosure.
Claims
1. An image generation method, comprising: Obtaining a target object model, which is generated based on the image of the target object; Obtaining a first image on a content generation page, the first image including first object features of the target object, and the first object features including first facial information and first pose information; In response to a first trigger operation, generating and displaying a second image based on the target object model and the first image, where the second object features of the target object in the second image match the first object features.
2. The image generation method according to claim 1, wherein, The step of, in response to a first trigger operation, generating and displaying a second image based on the target object model and the first image includes: Generating and displaying the second image according to the first facial information, the first pose information, and the target object model, where the second image includes image configuration information; Wherein, the image configuration information includes at least one of the following: second pose information, expression information, facial orientation information, clothing information, and background information of the second image in the second image.
3. The image generation method according to claim 2, wherein, The second facial information of the target object in the second image is associated with the first facial information and the target object model; and / or The background information in the second image is associated with the first facial information and the first pose information; and / or The second pose information in the second image is associated with the first pose information.
4. The image generation method according to claim 2, wherein, Before the step of, in response to a first trigger operation, generating and displaying a second image based on the target object model and the first image, the image generation method further includes: Displaying at least two first controls on the content generation page, where the at least two first controls are respectively used to determine at least two first style information; Receiving a second trigger operation on a target control among the at least two first controls; In response to the second trigger operation, determining second style information among the at least two first style information; The step of, in response to a first trigger operation, generating and displaying a second image based on the target object model and the first image includes: Generating and displaying the second image according to the second style information, the first facial information, the first pose information, and the target object model.
5. The image generation method according to any one of claims 1 to 4, wherein, Before the step of, in response to a first trigger operation, generating and displaying a second image based on the target object model and the first image, the image generation method includes: In response to a third trigger operation, displaying a first identifier in the first image, where the first identifier is used to display the first pose information.
6. The image generation method according to any one of claims 1 to 4, wherein, Before the step of, in response to a first trigger operation, generating and displaying a second image based on the target object model and the first image, the image generation method further includes: Receiving a fourth trigger operation on the first image; In response to the fourth trigger operation, displaying a target selection area in the first image, where the target selection area is used to select a first image area; The step of, in response to a first trigger operation, generating and displaying a second image based on the target object model and the first image includes: Determining first image content in the first image area; Generate third image content based on the target object model and the second image content in the second image area, where the second image area is the image area in the first image except the first image area; Generate and display the second image based on the first image content and the third image content.
7. The image generation method according to claim 6, wherein, After the target selection area is displayed in the first image in response to the fourth trigger operation, the image generation method further includes: Receiving a fifth trigger operation on the target selection area; In response to the fifth trigger operation, adjusting the coverage range of the target selection area in the first image to update the first image area.
8. The image generation method according to claim 6, wherein, The first image area includes any one of the following: The image area corresponding to at least a part of the target object, the image area corresponding to at least a part of the background image features.
9. The image generation method according to any one of claims 1 to 8, wherein, After generating and displaying the second image based on the target object model and the first image in response to the first trigger operation, the image generation method further includes: Displaying a second control on the content generation page; Receiving a sixth trigger operation on the second control; In response to the sixth trigger operation, determining second pose information in the second image based on third pose information, where the third pose information is different from the first pose information.
10. The image generation method according to claim 9, wherein, The sixth trigger operation includes a first sub-trigger operation and a second sub-trigger operation; In response to the sixth trigger operation, determining second pose information in the second image based on third pose information includes: In response to the first sub-trigger operation on the second control, displaying at least two fourth images; Receiving a second sub-trigger operation on a target image among the at least two fourth images; In response to the second sub-trigger operation, extracting the third pose information in the target image; Determining the second pose information according to the third pose information.
11. An image generation device, comprising: An acquisition module configured to acquire a target object model, where the target object model is generated based on the image of the target object; A display module configured to acquire a first image on a content generation page, where the first image includes first object features of the target object, and the first object features include first facial information and first pose information; A generation module configured to generate a second image based on the target object model and the first image in response to a first trigger operation; The display module configured to display the second image, where the second object features in the second image match the first object features.
12. An electronic device, comprising: A processor and a memory, where the memory stores a program or instruction that can run on the processor, and when the program or instruction is executed by the processor, it implements the image generation method according to any one of claims 1 to 10.
13. A readable storage medium, on which a program or instructions are stored, wherein, When the program or instruction is executed by the processor, it implements the image generation method according to any one of claims 1 to 10.
Citation Information
Patent Citations
Image conversion method and device, computer equipment and storage medium
CN111489287A
Virtual reloading method and device, electronic equipment and readable medium
CN116309005A
Expression image generation method and device, electronic equipment and readable storage medium
CN116543079A
3D virtual image processing method and device, electronic equipment and readable storage medium
CN116912463A
Image processing method, device and equipment
CN117252777A