Information display method and device, electronic equipment and storage medium

Abstract

The invention relates to an information display method and device, electronic equipment and a storage medium. The method can comprise the steps that a first interface is displayed; the first interface comprises a first image input control; in response to an input operation on a reference image based on the first image input control, displaying a second interface; the second interface comprises a second image input control, and the reference image comprises a first object; in response to an input operation on an additional image based on the second image input control, displaying target prompt information under the condition that the additional image and the reference image meet a preset image association condition, the additional image meeting the preset image association condition is an image which contains the first object and is similar to the reference image; the target prompt information represents that a video generation model corresponding to the first object is successfully generated based on the reference image and the additional image. The video generation diversity and flexibility can be improved.

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence technology, and in particular to an information display method, device, electronic device and storage medium. Background Art

[0002] Video generation big models are a cutting-edge direction in the field of artificial intelligence, focusing on developing advanced technologies that can automatically create, edit and process video content. These models are usually based on deep learning and generative artificial intelligence technologies, and can perform various complex video tasks, such as text-to-video generation, image-to-video generation, etc.

[0003] In the related art, videos can be generated by selecting a preset video generation model. The corresponding generated videos have a strong randomness and may not meet the user's video generation needs. In addition, due to the limited number of preset video generation models, the generated video content is relatively fixed and lacks diversity and flexibility. Summary of the invention

[0004] The present disclosure provides an information display method, device, electronic device and storage medium to at least solve the problem in the related art that the video content generated based on the preset video generation model does not meet the user's needs, and the generated video content is relatively fixed and lacks diversity and flexibility. The technical solution of the present disclosure is as follows:

[0005] According to a first aspect of an embodiment of the present disclosure, there is provided an information display method, including:

[0006] Displaying a first interface; the first interface includes a first image input control;

[0007] In response to an input operation on a reference image based on the first image input control, a second interface is displayed; the second interface includes a second image input control, and the reference image includes a first object;

[0008] In response to an input operation on an additional image based on the second image input control, target prompt information is displayed when the additional image and the benchmark image meet a preset image association condition; the additional image that meets the preset image association condition is an image that contains the first object and is similar to the benchmark image; the target prompt information represents a video generation model corresponding to the first object that is successfully generated based on the benchmark image and the additional image.

[0009] In an exemplary embodiment, the first interface further includes first input prompt information and a first example image, wherein the first input prompt information is used to indicate that a reference image containing global feature information of the first object is to be input, and the first example image is used to indicate that the image quality of the reference image to be input should meet a first image quality condition;

[0010] The displaying of the second interface in response to the input operation of the reference image based on the first image input control comprises:

[0011] In response to an input operation on the reference image based on the first image input control, the second interface is displayed if the reference image meets the first image quality condition.

[0012] In an exemplary embodiment, the second interface further includes second input prompt information and a second example image; the second input prompt information is used to indicate inputting an additional image containing the first object, and the second example image is used to indicate that the additional image to be input should meet a second image quality condition and the preset image association condition, and the preset image association condition is determined based on the layout display information of the first object in the reference image;

[0013] In response to the input operation of the additional image based on the second image input control, when the additional image and the reference image meet a preset image association condition, displaying target prompt information includes:

[0014] In response to an input operation on the additional image based on the second image input control, the target prompt information is displayed if the additional image meets the preset image association condition and the second image quality condition.

[0015] In an exemplary embodiment, the second interface further includes a plurality of image input statistical ranges corresponding to the additional image to be input, and model training effect prompt information corresponding to each of the plurality of image input statistical ranges;

[0016] The method further comprises:

[0017] In response to an input operation on an additional image based on the second image input control, a target image input statistical range where the additional image has been input and model training effect prompt information corresponding to the target image input statistical range are highlighted.

[0018] In an exemplary embodiment, the method further comprises:

[0019] In response to an input operation on the additional image based on the second image input control, when the input additional image does not meet the preset image association condition, first abnormal image prompt information is displayed, and when the input additional image does not meet the second image quality condition, second abnormal image prompt information is displayed; the first abnormal prompt information includes the additional image that does not meet the preset image association condition and first abnormal reason information, and the second abnormal image prompt information includes the additional image that does not meet the second image quality condition and second abnormal reason information.

[0020] In an exemplary embodiment, the second image input control includes an image real-time acquisition control;

[0021] The method further comprises:

[0022] In response to a triggering operation based on the real-time image acquisition control, image acquisition indication information is displayed in the second interface.

[0023] In an exemplary embodiment, the method further comprises:

[0024] In response to the video generation instruction, display a video generation interface; the video generation interface includes video generation model selection information;

[0025] In response to a model selection operation based on the video generation model selection information, a target video generated based on a target video generation model is displayed; the target video generation model is a model corresponding to the model selection operation, the target video includes a second object, and the target video generation model is obtained by model training based on a baseline image containing the second object and an additional image containing the second object.

[0026] In an exemplary embodiment, the video generation interface also includes video material configuration information;

[0027] In response to the model selection operation based on the video generation model selection information, displaying the target video generated based on the target video generation model includes:

[0028] In response to a video material configuration operation based on the video material configuration information and a model selection operation based on the video generation model selection information, the target video is displayed; the target video contains target video material, and the target video material is determined based on the video material configuration operation; the target video material includes at least one of text material and image material.

[0029] According to a second aspect of an embodiment of the present disclosure, there is provided an information display device, including:

[0030] A first interface display unit is configured to display a first interface; the first interface includes a first image input control;

[0031] A second interface display unit is configured to display a second interface in response to an input operation on a reference image based on the first image input control; the second interface includes a second image input control, and the reference image includes a first object;

[0032] A prompt information display unit is configured to execute an input operation on an additional image based on the second image input control, and to display target prompt information when the additional image and the benchmark image meet a preset image association condition; the additional image that meets the preset image association condition is an image that contains the first object and is similar to the benchmark image; the target prompt information represents a video generation model corresponding to the first object that is successfully generated based on the benchmark image and the additional image.

[0033] In an exemplary embodiment, the first interface further includes first input prompt information and a first example image, wherein the first input prompt information is used to indicate that a reference image containing global feature information of the first object is to be input, and the first example image is used to indicate that the image quality of the reference image to be input should meet a first image quality condition;

[0034] The second interface display unit is configured to execute:

[0035] In response to an input operation on the reference image based on the first image input control, the second interface is displayed if the reference image meets the first image quality condition.

[0036] In an exemplary embodiment, the second interface further includes second input prompt information and a second example image; the second input prompt information is used to indicate inputting an additional image containing the first object, and the second example image is used to indicate that the additional image to be input should meet a second image quality condition and the preset image association condition, and the preset image association condition is determined based on the layout display information of the first object in the reference image;

[0037] The prompt information display unit is configured to execute:

[0038] In response to an input operation on the additional image based on the second image input control, the target prompt information is displayed if the additional image meets the preset image association condition and the second image quality condition.

[0039] In an exemplary embodiment, the second interface further includes a plurality of image input statistical ranges corresponding to the additional image to be input, and model training effect prompt information corresponding to each of the plurality of image input statistical ranges;

[0040] The device also includes:

[0041] The highlighting display unit is configured to execute, in response to an input operation of the additional image based on the second image input control, a target image input statistical range where the additional image has been input, and model training effect prompt information corresponding to the target image input statistical range.

[0042] In an exemplary embodiment, the apparatus further comprises:

[0043] An abnormal prompt information display unit is configured to execute an input operation on the additional image based on the second image input control, and to display first abnormal image prompt information when the input additional image does not meet the preset image association condition, and to display second abnormal image prompt information when the input additional image does not meet the second image quality condition; the first abnormal prompt information includes the additional image that does not meet the preset image association condition and first abnormal cause information, and the second abnormal image prompt information includes the additional image that does not meet the second image quality condition and second abnormal cause information.

[0044] In an exemplary embodiment, the second image input control includes an image real-time acquisition control;

[0045] The device also includes:

[0046] The image acquisition indication information display unit is configured to display the image acquisition indication information in the second interface in response to a trigger operation based on the real-time image acquisition control.

[0047] In an exemplary embodiment, the apparatus further comprises:

[0048] A video generation interface display unit is configured to execute in response to the video generation instruction and display a video generation interface; the video generation interface includes video generation model selection information;

[0049] A target video display unit is configured to execute a model selection operation in response to the video generation model selection information, and display a target video generated based on a target video generation model; the target video generation model is a model corresponding to the model selection operation, the target video includes a second object, and the target video generation model is obtained by model training based on a baseline image containing the second object and an additional image containing the second object.

[0050] In an exemplary embodiment, the video generation interface also includes video material configuration information;

[0051] The target video display unit is configured to execute:

[0052] A display unit is configured to perform a video material configuration operation based on the video material configuration information and a model selection operation based on the video generation model selection information to display the target video; the target video contains a target video material, and the target video material is determined based on the video material configuration operation; the target video material includes at least one of text material and image material.

[0053] According to a third aspect of an embodiment of the present disclosure, there is provided an electronic device, comprising: a processor; and a memory for storing instructions executable by the processor; wherein the processor is configured to execute the instructions to implement the information display method as described above.

[0054] According to a fourth aspect of an embodiment of the present disclosure, a computer-readable storage medium is provided. When instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the information display method as described above.

[0055] According to a fifth aspect of an embodiment of the present disclosure, a computer program product is provided, which includes a computer program, and the computer program is stored in a readable storage medium. At least one processor of a computer device reads and executes the computer program from the readable storage medium, so that the device executes the above-mentioned information display method.

[0056] The technical solution provided by the embodiments of the present disclosure brings at least the following beneficial effects:

[0057] In the training process of the video generation model disclosed in the present invention, a first interface including a first image input control may be first displayed, and the first image input control may be used to input a reference image so as to obtain object reference information of a first object contained in the reference image from the reference image; then, in response to an input operation on the reference image based on the first image input control, a second interface including a second image input control may be displayed, and the second image input control may be used to input an additional image, and when the additional image meets a preset image association condition, the additional image may supplement the object information of the first object in the reference image, that is, the additional image may include more object information associated with the first object, and thus a video generation model corresponding to the first object may be generated; thereby, the reference object information of the first object is first determined by inputting the reference image, and then more object information of the first object is supplemented by inputting the additional image, so that sufficient object information about the first object can be obtained during the model training process, so that the generated video generation model can accurately and stably generate a video containing the first object. Furthermore, when the user needs to generate a video containing a specific object, the model can be trained based on the image containing the specific object to obtain a video generation model corresponding to the specific object. The video generated by the video generation model corresponding to the specific object can meet the user's video generation needs, that is, meet the user's needs to generate personalized videos; and the video generation models trained and generated by different users may be different. Users can generate video content based on the video generation model trained independently, without relying on a preset video generation model, thereby improving the diversity and flexibility of video generation.

[0058] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] The drawings herein are incorporated into and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the description are used to explain the principles of the present disclosure, and do not constitute improper limitations on the present disclosure.

[0060] Figure 1 It is a schematic diagram of an implementation environment according to an exemplary embodiment.

[0061] Figure 2 The present invention is a flow chart of an information display method according to an exemplary embodiment.

[0062] Figure 3 is a schematic diagram of a first interface according to an exemplary embodiment.

[0063] Figure 4 is a first schematic diagram of a second interface according to an exemplary embodiment.

[0064] Figure 5 The figure is a schematic diagram showing a statistical range of image input according to an exemplary embodiment.

[0065] Figure 6 is a second schematic diagram of a second interface according to an exemplary embodiment.

[0066] Figure 7 is a third schematic diagram of the second interface according to an exemplary embodiment.

[0067] Figure 8 This is a first schematic diagram of a video generation interface according to an exemplary embodiment.

[0068] Fig. 9 is a second schematic diagram of a video generation interface according to an exemplary embodiment.

[0069] Fig.10 The figure is a schematic diagram of a customized model training process according to an exemplary embodiment.

[0070] Fig.11 The figure is a block diagram of an information display device according to an exemplary embodiment.

[0071] Fig.12 The figure is a schematic diagram showing the structure of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION

[0072] In order to enable ordinary persons in the art to better understand the technical solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the accompanying drawings.

[0073] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0074] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for display, data for analysis, etc.) involved in this disclosure are all information and data authorized by the user or fully authorized by all parties.

[0075] See also Figure 1, which shows a schematic diagram of an implementation environment provided by an embodiment of the present disclosure, the implementation environment may include: at least one video processing terminal 110 and a video server 120, and the video processing terminal 110 and the video server 120 can communicate data through a network.

[0076] Specifically, during the model training process, the video processing end 110 may respond to the model training operation and receive the reference image and the additional image, and then send the reference image and the additional image to the video server 120 for model training to obtain the target video generation model. During the video generation process, the video processing end 110 may respond to the video generation operation and generate the target video based on the target video generation model. In the process of generating the target video based on the target video generation model, the target video generation model may be stored in the video processing end 110, so that the video processing end 110 can directly generate the target video based on the locally stored target video generation model; the target video generation model may be stored in the video server 120, so that the video processing end 110 can send a video generation request to the video server 120, thereby facilitating the video server 120 to generate the target video based on the target video generation model, and return the target video to the video processing end.

[0077] The video processing terminal 110 can communicate with the video server 120 based on the browser / server mode (B / S) or the client / server mode (C / S). The video processing terminal 110 may include: physical devices such as smart phones, tablet computers, laptops, digital assistants, smart wearable devices, vehicle terminals, servers, etc., and may also include software running in physical devices, such as applications, etc. The operating system running on the video processing terminal 110 in the embodiment of the present disclosure may include but is not limited to Android system, IOS system, Linux, Windows, etc.

[0078] The video server 120 and the video processing end 110 may establish a communication connection via wired or wireless communication. The video server 120 may include an independently operated server, or a distributed server, or a server cluster consisting of multiple servers, wherein the server may be a cloud server.

[0079] In order to solve the problem that the video content generated based on the preset video generation model in the related art does not meet the user's needs, and the generated video content is relatively fixed, lacks diversity and flexibility; the present disclosure provides an information display method, the execution subject of the method can be the above-mentioned video processing end, please refer to Figure 2 , the method may include:

[0080] S210. Display a first interface; the first interface includes a first image input control.

[0081] In this embodiment, the training and generating video generation model function may be a function integrated in the target application, where the target application may be an instant messaging application, a short video application, a video production reference program, etc., which is not specifically limited in this embodiment. Specifically, when video generation model training is required, the training process of the video generation model can be started by triggering a model training entry or a model training control, etc. The image input in this embodiment may be a static picture, a dynamic picture, a video image, etc.

[0082] When the training process of the video generation model corresponding to a specific object is started, a first interface including a first image input control may be displayed first, wherein the first image input control may include a first image upload control and a first image real-time acquisition control, the first image upload control may be used to upload an image stored locally on the video processing end, and the first image real-time acquisition control may be used to acquire images in real time and upload them. The specific object in this embodiment may be a specific person, a specific animal, a specific scene, a specific style, a specific composition, etc., and the video generation model for the specific object obtained by the corresponding training can generate a video containing a specific person, or generate a video containing a specific style, or generate a video containing a specific composition, etc.

[0083] Furthermore, the first interface also includes first input prompt information and a first example image, wherein the first input prompt information is used to indicate the input of a reference image containing global feature information of the first object, and the first example image is used to indicate that the image quality of the reference image to be input should meet a first image quality condition.

[0084] The first input prompt information may also be displayed in the vicinity of the first image input control, and the first input prompt information may be used to indicate the image content information that the reference image to be input should contain; specifically, the first input prompt information may be used to indicate that the reference image to be input should contain the front feature information or global feature information of a specific object, etc., wherein the first input prompt information may be displayed in the form of a window or panel. For example, the first input prompt information may be used to indicate the input of a reference image containing front face information of a human face, or the first input prompt information may be used to indicate the input of a reference image containing global style features, or the first input prompt information may be used to indicate the input of a reference image containing global composition features.

[0085] The first image quality condition may be that the image should contain positive feature information or global feature information of a specific object, the image should not be occluded, the image should be clear and not blurred, etc.; the corresponding first example image may include a positive image and a negative image, wherein the positive image may include an image containing positive feature information or global information of a specific object, and the negative image may include an image that does not contain positive feature information or global information of a specific object, an occluded image, a blurred image, etc.

[0086] Accordingly, taking the specific object as a specific person as an example, the global feature information corresponding to the specific person may be front face information of the face, and the first input prompt information is used to indicate inputting a reference image containing front face information of the face and corresponding image requirements; please refer to Figure 3 , which shows a schematic diagram of the first interface, wherein the first interface 310 includes a first image upload control 320 and a first image real-time acquisition control 330, and the first input prompt information 340 may be "upload a frontal video of a face for 10s"; the first example image 350 may include a positive example image of a frontal face image example image, a negative example image of a non-face frontal image example image, a negative example image of an occluded image example image, and a negative example image of a blurred image example image, wherein the positive example image may correspond to identification information representing the recommendation intention, such as "recommended" or "√", and the negative example image may correspond to identification information representing the non-recommendation intention, such as "not recommended" or "×", etc. Specifically, the first process node information 360 may also be displayed in the first interface, and the process node information in the first interface may represent that the current node is a reference image input node, and the next node is an additional image input node.

[0087] S220. In response to an input operation on a reference image based on the first image input control, display a second interface; the second interface includes a second image input control, and the reference image includes a first object.

[0088] Specifically, displaying the second interface in response to an input operation on a reference image based on the first image input control includes: displaying the second interface in response to an input operation on the reference image based on the first image input control when the reference image satisfies the first image quality condition.

[0089] In this embodiment, by displaying the first input prompt information in the first interface, the user can clearly understand that the benchmark image uploaded in the current step needs to include the global feature information of the first object, that is, the content information that the benchmark image should contain; by displaying the first example image in the first interface, the user can clearly understand the image quality requirements that the benchmark image uploaded in the current step should meet, thereby providing the user with clear image information input guidance, improving the pass rate of input images and reducing the length of time spent in the benchmark image input step; on the other hand, on the basis of improving the pass rate of input images and reducing the length of time spent in the benchmark image input step, the flow efficiency of the training process can be improved, and the second interface can be displayed as soon as possible to enter the additional image input node.

[0090] When the reference image input is completed, a second interface including a second image input control may be displayed, wherein the second image input control may include a second image upload control and a second image real-time acquisition control, the second image upload control may be used to upload images stored locally on the video processing end, and the second image real-time acquisition control may be used to acquire images in real time and upload them.

[0091] Furthermore, the second interface also includes second input prompt information and a second example image; the second input prompt information is used to indicate the input of an additional image containing the first object, and the second example image is used to indicate that the additional image to be input should meet a second image quality condition and the preset image association condition, and the preset image association condition is determined based on the layout display information of the first object in the reference image.

[0092] According to the above content, the additional image that satisfies the preset image association condition with the reference image can be an image that contains the same first object as the reference image and is similar to the reference image. Specifically, when the first object contained in the reference image is the target face information, the corresponding additional image that satisfies the preset image association condition with the reference image contains the target face information, and the layout display information of the target face information in the additional image is the same as or similar to the layout display information of the target face information in the reference image.

[0093] The layout display information of the first object in the reference image may include proportion information of the first object in the reference image, for example, proportion information of the target facial information in the reference image is 1 / n, and the corresponding preset image association condition is that the proportion information of the target facial information in the image is greater than or equal to 1 / n, and the corresponding second example image includes an example image in which the proportion information of the target facial information in the image is greater than or equal to 1 / n. In the case where the first object included in the reference image is the target composition, the corresponding additional image that satisfies the preset image association condition with the reference image includes the target composition information, and the proportion information of each object involved in the target composition information in the additional image is the same or similar to the proportion information of each object involved in the target composition information in the reference image; for example, the target composition information in the reference image involves the first person and the second person, and the proportion information of the first person and the second person is a:b, the first person is a close view, and the second person is a distant view, and the corresponding preset image association condition is that the composition ratio of the first person and the second person in the composition information is a:b or close to a:b, and the first person is a close view, and the second person is a distant view, and the corresponding second example image includes the composition ratio of the first person and the second person is a:b, and the first person is a close view, and the second person is a distant view. Where n, a, and b are all greater than 0.

[0094] The layout display information of the first object in the reference image may also include the number of first objects in the reference image. The number of objects in the corresponding second example image is consistent with the number of first objects in the reference image. When the reference image contains a target facial information, the corresponding second example image may include an image containing facial information. When the target composition information contained in the reference image involves two persons, a first person and a second person, the corresponding second example image may include an image of composition information formed by the two persons.

[0095] The second image quality condition may be that the image should have no occlusion, the image should be clear and not blurred, etc.; the corresponding second example image may include a positive image and a negative image, wherein the positive image may include an image containing a specific object and having no occlusion, and an image containing a specific object and having a clear image, and the negative image may include an image with occlusion, a blurred image, etc.

[0096] Accordingly, taking the specific object as a specific person as an example, the global feature information corresponding to the specific person may be front face information of the face, and the second input prompt information is used to instruct input of a supplementary image containing the face information of the first object, and the first object may be an object contained in the reference image; see Figure 4, which shows a first schematic diagram of the second interface, wherein the second interface 410 includes a second image upload control 420 and a second image real-time acquisition control 430, and the second input prompt information 440 may be "upload a supplementary video containing a face"; the second example image 450 may include an example image that meets the preset image association condition and an example image that meets the second image quality condition, wherein the example image 450 that meets the preset image association condition may include an example image in which the proportion of target face information in the image is greater than or equal to 1 / n and an example image image containing face information, and the example image that meets the second image quality condition may include an image containing a specific object without occlusion, an image containing a specific object and with a clear image, and a negative example image including an image with occlusion, a blurred image, etc. The positive example image may correspond to identification information representing the recommendation intention, such as "recommended" or "√", and the negative example image may correspond to identification information representing the non-recommendation intention, such as "not recommended" or "×", etc. The second interface may also display second process node information 460, and the process node information in the second interface may represent that the current node is an additional image input node, and the previous node is a reference image input node.

[0097] S230. In response to an input operation on an additional image based on the second image input control, target prompt information is displayed when the additional image and the baseline image satisfy a preset image association condition; the additional image that satisfies the preset image association condition is an image that contains the first object and is similar to the baseline image; the target prompt information represents a video generation model corresponding to the first object that is successfully generated based on the baseline image and the additional image.

[0098] Accordingly, in response to the input operation of the additional image based on the second image input control, when the additional image and the reference image meet the preset image association condition, displaying the target prompt information includes:

[0099] In response to an input operation on the additional image based on the second image input control, the target prompt information is displayed if the additional image meets the preset image association condition and the second image quality condition.

[0100] In this embodiment, by displaying the second input prompt information in the second interface, the user can clearly understand that the additional image uploaded in the current step needs to contain the same first object as in the baseline image, that is, clearly understand the content information that the additional image should contain; by displaying the second example image that meets the preset image association condition in the second interface, the user can further understand the conditions that the first object in the additional image to be uploaded should meet, so that the uploaded additional image can be further associated and matched with the baseline image, that is, the baseline image and the additional image are similar, thereby facilitating model training based on similar features corresponding to the first object in the baseline image and the additional image, and obtaining a stable video generation model; and because the preset image association condition is based on the layout display information of the first object in the baseline image The information is determined by the first object, so that different preset image association conditions can be determined for different first objects and different layout display information of the first object, that is, the preset image association conditions are adaptively and dynamically changed based on the actual layout information; further, by displaying the second example image that meets the second image quality condition in the second interface, the user can clearly understand the image quality requirements that the additional image uploaded in the current step should meet; on the one hand, it can provide users with clear image information input guidance, improve the pass rate of input images and reduce the length of time spent in the additional image input step; on the other hand, on the basis of improving the pass rate of input images and reducing the length of time spent in the additional image input step, it can improve the flow efficiency of the training process, enter the model training node as soon as possible, and improve the model generation efficiency.

[0101] When a video generation model is obtained by model training based on a reference image and an additional image, target prompt information can be displayed. The target prompt information can be used to prompt that the video generation model is successfully trained and generated based on the reference image and the additional image, and that the video generation model can generate a video containing the first object; that is, by inputting a reference image and an additional image containing the first object, a video generation model capable of generating a video containing the first object is generated.

[0102] In the training process of the video generation model disclosed in the present invention, a first interface including a first image input control may be first displayed, and the first image input control may be used to input a reference image so as to obtain object reference information of a first object contained in the reference image from the reference image; then, in response to an input operation on the reference image based on the first image input control, a second interface including a second image input control may be displayed, and the second image input control may be used to input an additional image, and when the additional image meets a preset image association condition, the additional image may supplement the object information of the first object in the reference image, that is, the additional image may include more object information associated with the first object, and thus a video generation model corresponding to the first object may be generated; thereby, the reference object information of the first object is first determined by inputting the reference image, and then more object information of the first object is supplemented by inputting the additional image, so that sufficient object information about the first object can be obtained during the model training process, so that the generated video generation model can accurately and stably generate a video containing the first object. Furthermore, when the user needs to generate a video containing a specific object, the model can be trained based on the image containing the specific object to obtain a video generation model corresponding to the specific object. The video generated by the video generation model corresponding to the specific object can meet the user's video generation needs, that is, meet the user's needs to generate personalized videos; and the video generation models trained and generated by different users may be different. Users can generate video content based on the video generation model trained independently, without relying on a preset video generation model, thereby improving the diversity and flexibility of video generation.

[0103] In a specific embodiment, the second interface also includes multiple image input statistical ranges corresponding to the additional image to be input, and model training effect prompt information corresponding to each of the multiple image input statistical ranges;

[0104] The method further comprises:

[0105] In response to an input operation on an additional image based on the second image input control, a target image input statistical range where the additional image has been input and model training effect prompt information corresponding to the target image input statistical range are highlighted.

[0106] The multiple image input statistical ranges may be multiple image input quantity ranges or multiple image input duration ranges, and may be arranged and displayed accordingly based on the order of quantity from small to large. Accordingly, the larger the quantity corresponding to the image input statistical range, the better the model training effect is; conversely, the model training effect prompt information indicates that the model training effect is worse. They may also be arranged and displayed in order from small to large based on the duration. The longer the duration corresponding to the image input statistical range, the better the model training effect is; conversely, the model training effect prompt information indicates that the model training effect is worse. Further, the multiple image input statistical ranges include a basic range and a supplementary range, wherein when the input additional image is within the basic range, the model training operation based on the input reference image and the input additional image may be started accordingly, and when the input additional image does not reach the basic range, the model training operation may not be started accordingly.

[0107] Specifically, the second input diagram information may also include a prompt to input as many additional images as possible to improve the model training effect. For example, a prompt to input a first number of additional images can start the model training operation, and inputting additional images greater than the first number can obtain a better model training effect. For another example, a prompt to input additional images of a first length can start the model training operation, and inputting additional images greater than a second length can obtain a better model training effect.

[0108] Please refer to Figure 5, which shows a schematic diagram of the image input statistical range display, the second input prompt information may also include a prompt to input as many additional images as possible to improve the model training effect, for example, the second input prompt information 510 may specifically be "after adding t1 segment or t1s of video, the model training can be started, and after adding t5 segment or t5s of video, the best model training effect can be obtained"; wherein the multiple image input statistical ranges 520 may include 0-t1, t1-t2, t2-t3, t3-t4, t4-t5, etc., and t1<t2<t3<t4<t5, wherein the corresponding t1, t2, t3, t4, t5 may be a quantity or a duration, t1 may be the minimum number or minimum duration of additional images for starting model training, and the corresponding additional image quantity or duration in the input When the duration reaches t1, the corresponding model training effect prompt information may be "first level", when the number of additional images input or the duration reaches t2, the corresponding model training effect prompt information may be "second level", when the number of additional images input or the duration reaches t3, the corresponding model training effect prompt information may be "third level", when the number of additional images input or the duration reaches t4, the corresponding model training effect prompt information may be "fourth level", when the number of additional images input or the duration reaches t5, the corresponding model training effect prompt information may be "fifth level", where the model training effects of each level are first level, second level, third level, fourth level and fifth level from bad to good. It should be noted that the number of multiple image input statistical ranges here can be determined according to the specific implementation situation, and the number of corresponding model training effect levels is also adapted thereto, and the examples in this embodiment do not limit it.

[0109] In this embodiment, multiple image input statistical ranges corresponding to the additional images to be input and the corresponding model training effect prompt information are displayed to facilitate users to clearly understand that the model training effects corresponding to additional images input in different ranges are different, so as to guide users to input as many additional images as possible to improve the model training effect.

[0110] In an optional embodiment, the information display method of this embodiment may further include:

[0111] In response to an input operation on the additional image based on the second image input control, when the input additional image does not meet the preset image association condition, first abnormal image prompt information is displayed, and when the input additional image does not meet the second image quality condition, second abnormal image prompt information is displayed; the first abnormal prompt information includes the additional image that does not meet the preset image association condition and first abnormal reason information, and the second abnormal image prompt information includes the additional image that does not meet the second image quality condition and second abnormal reason information.

[0112] Real-time image detection can also be performed on the input additional images to detect whether the input additional images meet the preset image association conditions and the second image quality conditions. For the input additional images that do not meet the preset image association conditions or do not meet the second image quality conditions, a prompt display can be given.

[0113] According to the above content, it can be known that the preset image association condition is determined based on the layout display information of the first object in the reference image. The layout display information of the first object in the reference image may include the proportion information of the first object in the reference image. The layout display information of the first object in the reference image may also include the number of first objects in the reference image.

[0114] For an image in the input additional image that does not satisfy the preset image association condition, the image that does not satisfy the preset image association condition and the first abnormal reason information of the image may be displayed. The first abnormal reason information may be that layout display information of the first object in the input additional image is different from the layout display information of the first object in the reference image. Specifically, the proportion information of the first object in the input additional image is inconsistent with the proportion information of the first object in the reference image, or the number of first objects in the input additional image is different from the number of first objects in the reference image, or the input additional image does not contain the first object in the reference image, etc.

[0115] The second image quality condition may be that the image should not be blocked, the image should be clear and not blurred, etc. Accordingly, for an image that does not meet the second image quality condition among the input additional images, the image that does not meet the second image quality condition and the second abnormal reason information of the image may be displayed, and the second abnormal reason information may be that the image has blockage, the image is blurred and unclear, etc.

[0116] See also Figure 6, which shows a second schematic diagram of the second interface, in which the input additional images that meet the preset image association condition and the second image quality condition, i.e., normal images, and the input additional images that do not meet the preset image association condition or the second image quality condition, i.e., abnormal images, can also be displayed in the second interface; wherein the normal image is displayed in the first display area 610, and the abnormal image is displayed in the second display area 620, and the first display area and the second display area are different display areas in the second interface; further, the first display area can also include a second image upload control 630 and a second image real-time acquisition control 640, and in the case of inputting the current image, the current image can be detected in real time, and the detection status prompt information can be displayed, and the image that passes the image detection can be displayed in the first display area, and the image that fails the image detection can be displayed in the second display area. In the second area, the images 1, 2, and 3 can be specifically displayed, and the corresponding abnormal reasons are that the specific object is not included, there is occlusion, and it is too blurred.

[0117] In this embodiment, real-time image detection can be performed on the input additional images, and abnormal reminders can be given for the input additional images that do not meet the preset image association conditions or do not meet the second image quality conditions, so that the user can clearly understand the conditions that the input images should meet, and then input images that meet the corresponding conditions, thereby improving the input efficiency and accuracy of the additional images, and then performing model training based on images that meet the conditions, and being able to train a stable video generation model.

[0118] Furthermore, the second image input control includes a real-time image acquisition control;

[0119] The method further comprises:

[0120] In response to a triggering operation based on the real-time image acquisition control, image acquisition indication information is displayed in the second interface.

[0121] The real-time image acquisition control may specifically be a control for triggering real-time image acquisition. In one example, when the real-time image acquisition control is triggered, image acquisition instruction information may be displayed in the second interface accordingly; in another example, the image acquisition instruction information may also be displayed in the second interface at the initial moment of displaying the second interface. The image acquisition instruction information may be used to indicate the acquisition angle or acquisition action during the real-time acquisition process, and the image acquisition instruction information may include image instruction information and text instruction information, etc. For example, when the first object is a person, the corresponding image acquisition instruction information may include instruction information for guiding the person to perform different actions, or the image acquisition instruction information may include instruction information for guiding the person to capture images from different angles, etc.

[0122] See also Figure 7 , which shows a third schematic diagram of the second interface, wherein the second interface includes a real-time image acquisition control 710. When the real-time image acquisition control 710 is triggered, image acquisition indication information 720 can be displayed in the second interface accordingly. The image acquisition indication information 720 may include a smiling image, a shaking head image, a blinking image, an open mouth image, etc.

[0123] In this embodiment, by displaying the image acquisition instruction information in the second interface, the user can be given corresponding acquisition guidance during the real-time image acquisition process, so that the acquired image can meet the corresponding image requirements, that is, a qualified additional image. On the one hand, the user can quickly acquire additional images that meet the requirements according to the image acquisition instruction information, thereby improving the input efficiency and the pass rate of the additional images; on the other hand, on the basis of improving the input efficiency and the pass rate of the additional images, the efficiency of model training and the model stability can be improved.

[0124] The above method of this embodiment can generate a video generation model corresponding to a specific object, that is, a video containing the specific object can be generated based on the video generation model corresponding to the specific object. Specifically, this embodiment also provides a video generation method, the execution subject of the method can be the above video processing end, and the method may include:

[0125] In response to the video generation instruction, display a video generation interface; the video generation interface includes video generation model selection information;

[0126] In response to a model selection operation based on the video generation model selection information, a target video generated based on a target video generation model is displayed; the target video generation model is a model corresponding to the model selection operation, the target video includes a second object, and the target video generation model is obtained by model training based on a baseline image containing the second object and an additional image containing the second object.

[0127] When it is necessary to generate a video, a video generation entry or a video generation control can be triggered to generate a video generation instruction; when the video processing end responds to the video generation instruction, a video generation interface can be displayed accordingly; the video generation interface may include video template selection information, and the target video generation model can be selected from the candidate video generation models by triggering the video template selection information; wherein the candidate video generation models can be obtained based on the above-mentioned method of model training by inputting a reference image and additional images.

[0128] See also Figure 8, which shows a first schematic diagram of a video generation interface, wherein the video generation interface 810 may include video template selection information 820 and a video preview area 830; when the video template selection information 820 is triggered, candidate video generation models may be displayed: model 1, model 2, model 3, model 4, etc., and model 1 is selected as the target video generation model. When the video generation confirmation control 840 is triggered, the target video corresponding to model 1 may be displayed in the video preview area 830. If model 1 is the video generation model corresponding to the target person, the target person may be included in the corresponding generated target video.

[0129] In this embodiment, when video generation is required, the target video generation model can be selected from the candidate video generation models by triggering the video generation model selection information. The target video generation model corresponds to the required specific object, and the target video generation model is a stable video generation model obtained by training based on a large number of images containing specific objects. It is thereby possible to generate a target video containing a specific object, thereby improving the flexibility, convenience and stability of target video generation.

[0130] In a specific embodiment, the video generation interface also includes video material configuration information;

[0131] In response to the model selection operation based on the video generation model selection information, displaying the target video generated based on the target video generation model includes:

[0132] In response to a video material configuration operation based on the video material configuration information and a model selection operation based on the video generation model selection information, the target video is displayed; the target video contains target video material, and the target video material is determined based on the video material configuration operation; the target video material includes at least one of text material and image material.

[0133] The text material or image material configured based on the video material configuration information can be applied to the target video, that is, the final text material or image material will be presented in the target video; the video material configuration information may include text material configuration information and image material configuration information, and the text material configuration can be achieved by inputting text information, and the image material configuration can be achieved by inputting image information; the input text information can be a text description of the overall effect of the video, or a detailed description of a specific object in the video, etc.; the input image information can be the information that is finally displayed in the target video, or it can be reference information generated as a target video, etc.

[0134] Specifically, see Fig. 9, which shows a second schematic diagram of a video generation interface, wherein the video generation interface may include video template selection information, a video preview area, and video material configuration information 910; the video material configuration information may specifically include text material configuration information and image material configuration information, the text material configuration information may include a text material tag 920 and a text box control 930, and text material configuration may be achieved by inputting text in the text box control; the image material configuration information may include an image material tag 940 and an image input control 950, and image material configuration may be achieved by inputting images based on the image input control. Further, in the case of triggering the video template selection information, candidate video generation models may be displayed: model 1, model 2, model 3, model 4, etc., and model 1 may be selected as the target video generation model. In the case of triggering the video generation confirmation control, the target video corresponding to model 1 may be displayed in the video preview area. If model 1 is a video generation model corresponding to a target person, the target person may be included in the corresponding generated target video; in the case of configuring text material and image material, the corresponding material information may be reflected in the target video. For example, the target video generation model corresponds to person a, and the text material can be "light passes through the leaves to form mottled shadows, and soft light falls on the face of person a". The corresponding generated target video can present a video effect that includes person a and soft light falls on the face of person a.

[0135] In this embodiment, on the basis of selecting the target model for video generation, additional materials can be further added for generating the target video. The addable materials may include text materials and image materials, etc., so that the final generated target video can include the specific object corresponding to the target model, and can also include the added text materials or image materials. That is, the user can select the corresponding target video generation model and the additional materials required to be added according to the specific video requirements, thereby improving the flexibility and diversity of target video generation.

[0136] The following is a specific example to illustrate the implementation process of the present disclosure. Fig.10 The implementation process may include a customized model training process and a video generation process. Taking uploading a video as an example, the customized model training process may include:

[0137] S1010. Upload a frontal close-up video of a specific object.

[0138] S1020. Add more video footage of the same specific object from different angles.

[0139] S1030. Determine whether the uploaded video material meets the algorithm's requirements for training videos; if so, execute step S1040; if not, execute step S1020.

[0140] S1040. Perform similarity detection on the front close-up video of the specific object and the more supplementary video materials from different angles to determine whether the more supplementary video materials from different angles are the same object video as the front close-up video of the specific object; if so, execute step S1050; if not, execute step S1020.

[0141] S1050. Start model training.

[0142] S1060. The model is trained successfully and a target video generation model is generated.

[0143] The video generation process may include:

[0144] 1. Enter the video generation page.

[0145] 2. Select the model corresponding to the user-customized target object, and enter material information such as text, pictures or videos as auxiliary data for video generation.

[0146] 3. Combine the customized model and the input auxiliary data to generate a stable video containing the target object.

[0147] In this embodiment, through the two steps of uploading a reference image and uploading an additional image, the user is guided to provide appropriate image data for model training to start model training, thereby training a stable and high-performance video generation model, so as to facilitate the stable generation of videos containing specific objects in subsequent video generation.

[0148] It should be noted that any method in this embodiment can be combined based on actual implementation conditions and have corresponding beneficial effects, which will not be described in detail here.

[0149] Fig.11 is a block diagram of an information display device according to an exemplary embodiment. Fig.11 , the device comprises:

[0150] The first interface display unit 1010 is configured to display a first interface; the first interface includes a first image input control;

[0151] The second interface display unit 1120 is configured to display a second interface in response to an input operation on a reference image based on the first image input control; the second interface includes a second image input control, and the reference image includes a first object;

[0152] The prompt information display unit 1130 is configured to execute an input operation on an additional image based on the second image input control, and to display target prompt information when the additional image and the benchmark image meet a preset image association condition; the additional image that meets the preset image association condition is an image that contains the first object and is similar to the benchmark image; the target prompt information represents a video generation model corresponding to the first object that is successfully generated based on the benchmark image and the additional image.

[0153] In an exemplary embodiment, the first interface further includes first input prompt information and a first example image, wherein the first input prompt information is used to indicate that a reference image containing global feature information of the first object is to be input, and the first example image is used to indicate that the image quality of the reference image to be input should meet a first image quality condition;

[0154] The second interface display unit is configured to execute:

[0155] In response to an input operation on the reference image based on the first image input control, the second interface is displayed if the reference image meets the first image quality condition.

[0156] In an exemplary embodiment, the second interface further includes second input prompt information and a second example image; the second input prompt information is used to indicate inputting an additional image containing the first object, and the second example image is used to indicate that the additional image to be input should meet a second image quality condition and the preset image association condition, and the preset image association condition is determined based on the layout display information of the first object in the reference image;

[0157] The prompt information display unit is configured to execute:

[0158] In response to an input operation on the additional image based on the second image input control, the target prompt information is displayed if the additional image meets the preset image association condition and the second image quality condition.

[0159] In an exemplary embodiment, the second interface further includes a plurality of image input statistical ranges corresponding to the additional image to be input, and model training effect prompt information corresponding to each of the plurality of image input statistical ranges;

[0160] The device also includes:

[0161] The highlighting display unit is configured to execute, in response to an input operation of the additional image based on the second image input control, a target image input statistical range where the additional image has been input, and model training effect prompt information corresponding to the target image input statistical range.

[0162] In an exemplary embodiment, the apparatus further comprises:

[0163] An abnormal prompt information display unit is configured to execute an input operation on the additional image based on the second image input control, and to display first abnormal image prompt information when the input additional image does not meet the preset image association condition, and to display second abnormal image prompt information when the input additional image does not meet the second image quality condition; the first abnormal prompt information includes the additional image that does not meet the preset image association condition and first abnormal cause information, and the second abnormal image prompt information includes the additional image that does not meet the second image quality condition and second abnormal cause information.

[0164] In an exemplary embodiment, the second image input control includes an image real-time acquisition control;

[0165] The device also includes:

[0166] The image acquisition indication information display unit is configured to display the image acquisition indication information in the second interface in response to a trigger operation based on the real-time image acquisition control.

[0167] In an exemplary embodiment, the apparatus further comprises:

[0168] A video generation interface display unit is configured to execute in response to the video generation instruction and display a video generation interface; the video generation interface includes video generation model selection information;

[0169] A target video display unit is configured to execute a model selection operation in response to the video generation model selection information, and display a target video generated based on a target video generation model; the target video generation model is a model corresponding to the model selection operation, the target video includes a second object, and the target video generation model is obtained by model training based on a baseline image containing the second object and an additional image containing the second object.

[0170] In an exemplary embodiment, the video generation interface also includes video material configuration information;

[0171] The target video display unit is configured to execute:

[0172] A display unit is configured to perform a video material configuration operation based on the video material configuration information and a model selection operation based on the video generation model selection information to display the target video; the target video contains a target video material, and the target video material is determined based on the video material configuration operation; the target video material includes at least one of text material and image material.

[0173] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0174] In an exemplary embodiment, a computer-readable storage medium including instructions is also provided. Optionally, the computer-readable storage medium may be a ROM, a random access memory (RAM), a CD-ROM, a tape, a floppy disk, an optical data storage device, etc.; when the instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute any of the methods described above.

[0175] In an exemplary embodiment, a computer program product is also provided, which includes a computer program stored in a readable storage medium, and at least one processor of a computer device reads and executes the computer program from the readable storage medium, so that the device performs any of the above methods.

[0176] Fig.12 is a block diagram of an electronic device for multimedia content sharing according to an exemplary embodiment. The electronic device may be a terminal, and its internal structure diagram may be as shown in FIG. Fig.12 As shown, it may include an RF (Radio Frequency) circuit 1210, a memory 1220 including one or more computer-readable storage media, an input unit 1230, a display unit 1240, a sensor 1250, an audio circuit 1260, a WiFi (wireless fidelity) module 1270, a processor 1280 including one or more processing cores, and a power supply 1290. Those skilled in the art will understand that Fig.12 The terminal structure shown in the figure does not constitute a limitation on the terminal, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0177] The RF circuit 1210 can be used for receiving and sending signals during information transmission or calls. In particular, after receiving the downlink information of the base station, it is handed over to one or more processors 1280 for processing; in addition, the data related to the uplink is sent to the base station. Generally, the RF circuit 1210 includes but is not limited to an antenna, at least one amplifier, a tuner, one or more oscillators, a user identity module (SIM) card, a transceiver, a coupler, an LNA (Low Noise Amplifier), a duplexer, etc. In addition, the RF circuit 1210 can also communicate with the network and other terminals through wireless communication. Wireless communication can use any communication standard or protocol, including but not limited to GSM (Global System of Mobile communication), GPRS (General Packet Radio Service), CDMA (Code Division Multiple Access), WCDMA (Wideband Code Division Multiple Access), LTE (Long Term Evolution), email, SMS (Short Messaging Service), etc.

[0178] The memory 1220 can be used to store software programs and modules, and the processor 1280 executes various functional applications and data processing by running the software programs and modules stored in the memory 1220. The memory 1220 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, application programs required for functions, etc.; the data storage area may store data created according to the use of the terminal, etc. In addition, the memory 1220 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices. Accordingly, the memory 1220 may also include a memory controller to provide the processor 1280 and the input unit 1230 with access to the memory 1220.

[0179] The input unit 1230 can be used to receive input digital or character information, and generate keyboard, mouse, joystick, optical or trackball signal input related to user settings and function control. Specifically, the input unit 1230 may include a touch-sensitive surface 1231 and other input devices 1232. The touch-sensitive surface 1231, also known as a touch display screen or a touch pad, can collect user touch operations on or near it (such as operations performed by the user using any suitable object or accessory such as a finger, stylus, etc. on or near the touch-sensitive surface 1231), and drive the corresponding connection device according to a pre-set program. Optionally, the touch-sensitive surface 1231 may include two parts: a touch detection device and a touch controller. Among them, the touch detection device detects the user's touch direction, detects the signal brought by the touch operation, and transmits the signal to the touch controller; the touch controller receives the touch information from the touch detection device, converts it into touch point coordinates, and then sends it to the processor 1280, and can receive and execute commands sent by the processor 1280. In addition, the touch-sensitive surface 1231 may be implemented in various types such as resistive, capacitive, infrared, and surface acoustic wave. In addition to the touch-sensitive surface 1231, the input unit 1230 may further include other input devices 1232. Specifically, the other input devices 1232 may include, but are not limited to, one or more of a physical keyboard, a function key (such as a volume control key, a switch key, etc.), a trackball, a mouse, a joystick, and the like.

[0180] The display unit 1240 can be used to display information input by the user or information provided to the user and various graphical user interfaces of the terminal, which can be composed of graphics, text, icons, videos and any combination thereof. The display unit 1240 may include a display panel 1241. Optionally, the display panel 1241 may be configured in the form of LCD (Liquid Crystal Display), OLED (Organic Light-Emitting Diode), etc. Further, the touch-sensitive surface 1231 may cover the display panel 1241. When the touch-sensitive surface 1231 detects a touch operation on or near it, it is transmitted to the processor 1280 to determine the type of touch event, and then the processor 1280 provides corresponding visual output on the display panel 1241 according to the type of touch event. Among them, the touch-sensitive surface 1231 and the display panel 1241 can be two independent components to realize input and output functions, but in some embodiments, the touch-sensitive surface 1231 and the display panel 1241 can also be integrated to realize input and output functions.

[0181] The terminal may also include at least one sensor 1250, such as a light sensor, a motion sensor, and other sensors. Specifically, the light sensor may include an ambient light sensor and a proximity sensor, wherein the ambient light sensor may adjust the brightness of the display panel 1241 according to the brightness of the ambient light, and the proximity sensor may turn off the display panel 1241 and / or the backlight when the terminal is moved to the ear. As a type of motion sensor, the gravity acceleration sensor can detect the magnitude of acceleration in each direction (generally three axes), and can detect the magnitude and direction of gravity when stationary. It can be used for applications that identify the terminal posture (such as horizontal and vertical screen switching, related games, magnetometer posture calibration), vibration recognition related functions (such as pedometer, tapping), etc.; as for other sensors such as gyroscopes, barometers, hygrometers, thermometers, infrared sensors, etc. that can also be configured in the terminal, they will not be repeated here.

[0182] The audio circuit 1260, the speaker 1261, and the microphone 1262 can provide an audio interface between the user and the terminal. The audio circuit 1260 can transmit the electrical signal converted from the received audio data to the speaker 1261, which is converted into a sound signal for output; on the other hand, the microphone 1262 converts the collected sound signal into an electrical signal, which is received by the audio circuit 1260 and converted into audio data, and then the audio data is output to the processor 1280 for processing, and then sent to another terminal through the RF circuit 1210, or the audio data is output to the memory 1220 for further processing. The audio circuit 1260 may also include an earplug jack to provide communication between an external headset and the terminal.

[0183] WiFi is a short-range wireless transmission technology. The terminal can help users send and receive emails, browse web pages, and access streaming media through the WiFi module 1270. It provides users with wireless broadband Internet access. Fig.12 A WiFi module 1270 is shown, but it is understandable that it is not an essential component of the terminal and can be omitted as needed without changing the essence of the invention.

[0184] The processor 1280 is the control center of the terminal. It uses various interfaces and lines to connect various parts of the entire terminal. It executes various functions of the terminal and processes data by running or executing software programs and / or modules stored in the memory 1220, and calling data stored in the memory 1220, so as to monitor the terminal as a whole. Optionally, the processor 1280 may include one or more processing cores; preferably, the processor 1280 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface and application programs, etc., and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 1280.

[0185] The terminal also includes a power supply 1290 (such as a battery) for supplying power to each component. Preferably, the power supply can be logically connected to the processor 1280 through a power management system, so that the power management system can manage charging, discharging, and power consumption management. The power supply 1290 can also include one or more DC or AC power supplies, recharging systems, power failure detection circuits, power converters or inverters, power status indicators, and other arbitrary components.

[0186] Although not shown, the terminal may also include a camera, a Bluetooth module, etc., which will not be described in detail herein. Specifically in this embodiment, the display unit of the terminal is a touch screen display, and the terminal further includes a memory, and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by one or more processors to execute instructions in the method embodiment of the present invention.

[0187] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present disclosure are indicated by the following claims.

[0188] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. An information display method, characterized in that: include: Displaying a first interface; the first interface includes a first image input control; In response to an input operation on a reference image based on the first image input control, a second interface is displayed; the second interface includes a second image input control, and the reference image includes a first object; In response to an input operation of an additional image based on the second image input control, when the additional image and the reference image meet a preset image association condition, displaying target prompt information; The additional image satisfying the preset image association condition is an image containing the first object and being similar to the reference image; The target prompt information represents a video generation model corresponding to the first object that is successfully generated based on the reference image and the additional image.

2. The method according to claim 1, characterized in that The first interface also includes first input prompt information and a first example image, wherein the first input prompt information is used to indicate that a reference image containing global feature information of the first object should be input, and the first example image is used to indicate that the image quality of the reference image to be input should meet a first image quality condition; The displaying of the second interface in response to the input operation of the reference image based on the first image input control comprises: In response to an input operation on the reference image based on the first image input control, the second interface is displayed if the reference image meets the first image quality condition.

3. The method according to claim 1, characterized in that The second interface also includes second input prompt information and a second example image; the second input prompt information is used to indicate inputting an additional image containing the first object, and the second example image is used to indicate that the additional image to be input should meet a second image quality condition and the preset image association condition, and the preset image association condition is determined based on layout display information of the first object in the reference image; In response to the input operation of the additional image based on the second image input control, when the additional image and the reference image meet a preset image association condition, displaying target prompt information includes: In response to an input operation on the additional image based on the second image input control, the target prompt information is displayed if the additional image meets the preset image association condition and the second image quality condition.

4. The method according to claim 1 or 3, characterized in that: The second interface also includes a plurality of image input statistical ranges corresponding to the additional image to be input, and model training effect prompt information corresponding to each of the plurality of image input statistical ranges; The method further comprises: In response to an input operation on an additional image based on the second image input control, a target image input statistical range where the additional image has been input and model training effect prompt information corresponding to the target image input statistical range are highlighted.

5. The method according to claim 3, characterized in that: The method further comprises: In response to an input operation on the additional image based on the second image input control, when the input additional image does not meet the preset image association condition, first abnormal image prompt information is displayed, and when the input additional image does not meet the second image quality condition, second abnormal image prompt information is displayed; the first abnormal prompt information includes the additional image that does not meet the preset image association condition and first abnormal reason information, and the second abnormal image prompt information includes the additional image that does not meet the second image quality condition and second abnormal reason information.

6. The method according to claim 3, characterized in that The second image input control includes a real-time image acquisition control; The method further comprises: In response to a triggering operation based on the real-time image acquisition control, image acquisition indication information is displayed in the second interface.

7. The method according to claim 1, characterized in that The method further comprises: In response to the video generation instruction, display a video generation interface; the video generation interface includes video generation model selection information; In response to a model selection operation based on the video generation model selection information, a target video generated based on a target video generation model is displayed; the target video generation model is a model corresponding to the model selection operation, the target video includes a second object, and the target video generation model is obtained by model training based on a baseline image containing the second object and an additional image containing the second object.

8. The method according to claim 7, characterized in that The video generation interface also includes video material configuration information; In response to the model selection operation based on the video generation model selection information, displaying the target video generated based on the target video generation model includes: In response to a video material configuration operation based on the video material configuration information and a model selection operation based on the video generation model selection information, the target video is displayed; the target video contains target video material, and the target video material is determined based on the video material configuration operation; the target video material includes at least one of text material and image material.

9. An information display device, characterized in that: include: A first interface display unit is configured to display a first interface; the first interface includes a first image input control; A second interface display unit is configured to display a second interface in response to an input operation on a reference image based on the first image input control; the second interface includes a second image input control, and the reference image includes a first object; a prompt information display unit configured to display target prompt information in response to an input operation on an additional image based on the second image input control, when the additional image and the reference image meet a preset image association condition; The additional image satisfying the preset image association condition is an image containing the first object and being similar to the reference image; The target prompt information represents a video generation model corresponding to the first object that is successfully generated based on the reference image and the additional image.

10. An electronic device, characterized in that: include: processor; a memory for storing instructions executable by the processor; The processor is configured to execute the instructions to implement the information display method as described in any one of claims 1 to 8.

11. A computer-readable storage medium, characterized in that: When the instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the information presentation method as claimed in any one of claims 1 to 8.

12. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the information display method according to any one of claims 1 to 8 is implemented.

Images