Video generation method and device, electronic equipment and storage medium

Abstract

The invention provides a video generation method and device, electronic equipment and a storage medium, and belongs to the technical field of multimedia. The method comprises the following steps: displaying a video editing interface, wherein a material generation control and a video track are displayed in the video editing interface; in response to a trigger operation on the material generation control, an artificial intelligence technology is adopted to generate a first material, and the first material comprises at least one of an image material and a video material; in the video track, displaying the first material; and in response to a video generation operation, generating a video based on the first material in the video track. According to the technical scheme, the image / video material generation function is deeply integrated into the video editing scene, material generation and video generation can be seamlessly connected, and therefore the video generation efficiency can be improved.

Description

Technical Field

[0001] The present disclosure relates to the field of multimedia technology, and in particular to a video generation method, device, electronic device and storage medium. Background Art

[0002] With the development of multimedia technology, video has gradually become the main way for people to obtain information and entertainment due to its advantages of rich pictures and texts and vividness. Various video editing applications have emerged. Video editing applications usually provide convenient video editing functions, allowing users to quickly make their own videos.

[0003] In the process of video production, when more image materials or video materials are needed, users usually generate image materials or video materials in an application that supports AI generation and download them to the album; then, they return to the video editing application, pull the album to obtain the AI-generated image materials or video materials, and edit them to generate a new video.

[0004] However, the above technical solution requires cross-application operations, that is, users need to generate materials in applications that support AI generation, save them to the album, and then import them into the video editing application. The operation is cumbersome and incoherent, affecting the efficiency of video generation. Summary of the invention

[0005] The present disclosure provides a video generation method, device, electronic device and storage medium, which realizes the deep integration of image / video material generation function into the video editing scene, and the material generation and video generation can be seamlessly connected, thereby improving the video generation efficiency. The technical solution of the present disclosure is as follows:

[0006] According to one aspect of an embodiment of the present disclosure, a video generation method is provided, including:

[0007] Displaying a video editing interface, wherein the video editing interface displays a material generation control and a video track;

[0008] In response to a triggering operation on the material generation control, using artificial intelligence technology to generate a first material, the first material including at least one of an image material and a video material;

[0009] In the video track, display the first material;

[0010] In response to a video generation operation, a video is generated based on the first material in the video track.

[0011] According to another aspect of an embodiment of the present disclosure, there is provided a video generating device, including:

[0012] A display unit is configured to display a video editing interface, wherein the video editing interface displays a material generation control and a video track;

[0013] A first generating unit is configured to generate a first material by using artificial intelligence technology in response to a triggering operation on the material generating control, wherein the first material includes at least one of an image material and a video material;

[0014] The display unit is further configured to execute in the video track to display the first material;

[0015] The second generating unit is configured to generate a video based on the first material in the video track in response to a video generating operation.

[0016] In some embodiments, the first generating unit includes:

[0017] A display subunit, configured to display a material generation panel in response to a triggering operation on the material generation control;

[0018] An acquisition subunit is configured to acquire prompt information, wherein the prompt information includes at least one of a prompt text and a prompt image, and the prompt information is used to indicate at least one of a content and a style of a material to be generated;

[0019] The display subunit is further configured to display the prompt information in the material generation panel;

[0020] The generating subunit is configured to execute, in response to the confirming generating operation, the generating first material matching the prompt information by adopting artificial intelligence technology.

[0021] In some embodiments, the material generation control includes at least one of an image generation control, a video generation control, and a batch generation control, and the material generation panel includes at least one of an image generation panel, a video generation panel, and a batch generation panel;

[0022] The generating subunit is configured to perform any of the following:

[0023] In response to the confirmation generation operation in the image generation panel, based on the prompt information in the image generation panel, an image material matching the prompt information is generated using artificial intelligence technology;

[0024] In response to the confirmation generation operation in the video generation panel, based on the prompt information in the video generation panel, using artificial intelligence technology to generate video material matching the prompt information;

[0025] In response to the confirmation generation operation in the batch generation panel, based on the multiple prompt information in the batch generation panel, artificial intelligence technology is used to generate image materials or video materials that match the multiple prompt information respectively.

[0026] In some embodiments, the video editing interface also displays other tracks besides the video track;

[0027] The acquisition subunit is configured to determine the prompt information based on the material in the other track when the corresponding material has been added to the other track.

[0028] In some embodiments, the material generation panel includes at least one of an image generation panel and a video generation panel;

[0029] The acquisition subunit is configured to, when corresponding materials have been added to the other tracks, determine the second material at the position from the other tracks based on the position indicated by the time progress line in the other tracks; and determine the prompt information based on the second material.

[0030] In some embodiments, the display unit is configured to display the first material in the video track according to the position of the second material in the other track.

[0031] In some embodiments, the prompt information includes the second material, the length of the first material is equal to the length of the second material, and the length of the material is used to indicate the display duration of the material.

[0032] In some embodiments, the material generation panel is a batch generation panel;

[0033] The acquisition subunit is configured to respectively determine the prompt information corresponding to each of the plurality of second materials based on the plurality of second materials in the other tracks when the corresponding material has been added to the other tracks.

[0034] In some embodiments, the generating subunit is configured to execute, in response to the confirming generating operation, based on the prompt information corresponding to each of the plurality of second materials in the other tracks, respectively generate the first materials corresponding to each of the prompt information by using artificial intelligence technology;

[0035] The display unit is configured to display the first material corresponding to each prompt information in the video track according to the order of the multiple second materials in the other tracks.

[0036] In some embodiments, the video editing interface also displays other tracks besides the video track;

[0037] The display unit is also configured to execute prompt information corresponding to each second material in the other tracks in the material generation panel, and display the editing control corresponding to the prompt information; in response to a triggering operation on the editing control, display the editing panel of the prompt information, and the editing panel is used to edit the prompt information.

[0038] In some embodiments, the video editing interface displays a plurality of other tracks in addition to the video track;

[0039] The acquisition subunit is configured to execute, in response to a selection operation on any other track in the video editing interface, and to determine, based on each second material in the other track, prompt information corresponding to each second material.

[0040] In some embodiments, the display unit is further configured to execute, for any prompt information in the material generation panel, in response to a type selection operation for the prompt information, display the material type corresponding to the prompt information in the material generation panel;

[0041] The generating subunit is configured to execute, in response to a confirmed generating operation, using artificial intelligence technology to generate the first material that matches the prompt information and conforms to a corresponding material type.

[0042] In some embodiments, the display unit is configured to execute, for any prompt information in the material generation panel, a material selection control for the prompt information; in response to a triggering operation on the material selection control, an image type option and a video type option are displayed; and when any type option among the image type option and the video type option is selected, the material type indicated by the selected type option is displayed in the material generation panel.

[0043] In some embodiments, the display unit is configured to display an image type option and a video type option in response to a selection operation of any multiple prompt information in the material generation panel; when any type option among the image type option and the video type option is selected, the material type indicated by the selected type option is displayed in the material generation panel.

[0044] In some embodiments, a template selection control is displayed in the material generation panel;

[0045] The acquisition subunit is configured to display a plurality of text templates in response to a trigger operation on the template selection control; and determine the text template as the prompt information in response to an application operation on any text template.

[0046] In some embodiments, an image acquisition control is displayed in the material generation panel;

[0047] The acquisition subunit is configured to display multiple images in response to a triggering operation on the image acquisition control; and determine the prompt information based on the at least one image in response to a selection operation on at least one image among the multiple images.

[0048] In some embodiments, the acquisition sub-unit is configured to execute, for any image among the multiple images, in response to a selection operation on the image, display the image in a prompt editing interface; in response to a prompt selection operation on the image in the prompt editing interface, determine a prompt area in the image, and determine the image and the area prompt information for indicating the prompt area as the prompt information.

[0049] In some embodiments, the display unit is further configured to execute, in response to a text input operation in the material generation panel, display the input prompt text in the material generation panel;

[0050] The acquisition subunit is configured to perform any of the following:

[0051] In response to a triggering operation on the image acquisition control, based on the prompt text in the material generation panel, the multiple images are displayed, and at least one of the content and style of the multiple images conforms to the prompt text;

[0052] In response to a triggering operation on the image acquisition control, the multiple images are displayed based on the prompt text in the material generation panel, and at least one image among the multiple images whose content and style at least match the prompt text is highlighted.

[0053] In some embodiments, the material generation panel includes a video generation panel, the prompt information in the video generation panel includes multiple images, and the video generation panel displays a first and last frame mode control;

[0054] The generation subunit is configured to execute, in response to confirming the generation operation when the first and last frame mode control is triggered, for any two adjacent images in the multiple images in the video generation panel, use an interpolation algorithm to process the two images to obtain a transition image between the two images; and generate the first material based on the multiple images in the video generation panel and the transition images of the multiple images.

[0055] In some embodiments, the display unit is further configured to display the first material in the material generation panel;

[0056] In response to a selection operation on the first material, when the time progress line is in an idle area in the video track, the first material is displayed after the material added to the video track, and the idle area is an area in the video track where no material exists; or

[0057] In response to a selection operation on the first material, when the time progress line is in a non-idle area in the video track, the first material is displayed between two materials closest to the time progress line in the video track.

[0058] In some embodiments, the display unit is further configured to display a minimize control in the material generation panel during the process of generating the first material; minimize the material generation panel in response to a triggering operation on the minimize control; highlight a first target area in the video track, the first target area being used to indicate a position to be occupied by the first material in the video track; and display the first material in the first target area.

[0059] In some embodiments, the first generating unit is further configured to execute, in response to an update operation on the first material in the video track, regenerate a third material;

[0060] The display unit is further configured to replace the first material in the video track with the third material.

[0061] In some embodiments, the first generating unit is further configured to generate a video material for any image material in the video track in response to a conversion operation on the image material based on the content and length of the image material, wherein the content of the video material is related to the content of the image material, the length of the video material is in a preset ratio to the length of the image material, and the length of the material is used to indicate the display duration of the material;

[0062] The display unit is further configured to replace the image material in the video track with the video material.

[0063] In some embodiments, the display unit is further configured to display a video extension panel in response to an extension operation on any video material in the video track;

[0064] The display unit is further configured to execute, based on the extension prompt information in the video extension panel, displaying in the video track an incremental video material that matches the extension prompt information, the extension prompt information comprising at least one of a prompt text and a prompt image, the extension prompt information being used to indicate at least one of a content and a style of the incremental video material to be generated, the incremental video material being located after the video material and connected to the video material.

[0065] In some embodiments, the display unit is configured to perform any of the following:

[0066] In response to a triggering operation on any video material in the video track, a time window of the video material is displayed in the video track, the length of the time window represents the display duration of the video material, and when the length of the time window is equal to the maximum duration of the video material and a lengthening operation on the time window is detected, the video extension panel is displayed;

[0067] For any video material in the video track, in response to an editing operation of the video material, an extension control is displayed in the video editing interface, and in response to a triggering operation of the extension control, the video extension panel is displayed.

[0068] In some embodiments, the incremental video material is at least one of the following:

[0069] The incremental video material is generated based on the prompt text input in the video extension panel;

[0070] The incremental video material is generated based on a prompt image input into the video extension panel, and the prompt image is an image located at the last frame of the video material.

[0071] In some embodiments, the display unit is configured to highlight a second target area in the video track during the process of generating the incremental video material based on the extended prompt information, the second target area being used to indicate the position to be occupied by the incremental video material in the video track, the second target area being located after the area occupied by the video material and connected to the area occupied by the video material; after the incremental video material is generated, the incremental video material is displayed in the second target area.

[0072] In some embodiments, the display unit is configured to execute, in the process of generating the incremental video material based on the extension prompt information, after the video material in the video track, displaying the generated images in the incremental video material frame by frame until the incremental video material is generated.

[0073] In some embodiments, the apparatus further comprises:

[0074] a determining unit configured to determine, in response to a transition material generating operation, a fourth material and a fifth material indicated by the transition material generating operation;

[0075] The first generating unit is further configured to generate the transition material based on the last frame image in the fourth material and the first frame image in the fifth material when the fifth material is located after the fourth material; or, based on the first frame image in the fourth material and the last frame image in the fifth material when the fifth material is located before the fourth material;

[0076] The transition material is displayed between the fourth material and the fifth material.

[0077] In some embodiments, the determination unit is configured to execute a trigger operation on a transition generation control in the video editing interface to display a transition generation panel, wherein a first generation option and a second generation option are displayed in the transition generation panel, wherein the first generation option is used to indicate generation of a transition material between the fourth material and a previous material of the fourth material, and the second generation option is used to indicate generation of a transition material between the fourth material and a subsequent material of the fourth material, wherein the fourth material is the material indicated by the time progress line in the video track; when the first generation option is selected, the previous material of the fourth material is determined as the fifth material; and when the second generation option is selected, the subsequent material of the fourth material is determined as the fifth material.

[0078] In some embodiments, the determination unit is configured to display the first generation option as being selected in the transition generation panel in response to a triggering operation on the transition generation control in the video editing interface when the first material distance is greater than the second material distance; and to display the second generation option as being selected in the transition generation panel in response to a triggering operation on the transition generation control in the video editing interface when the first material distance is less than the second material distance; wherein the first material distance is the distance between the position indicated by the time progress line in the video track and the previous material of the fourth material, and the second material distance is the distance between the position indicated by the time progress line in the video track and the next material of the fourth material.

[0079] According to another aspect of an embodiment of the present disclosure, an electronic device is provided, the electronic device comprising:

[0080] one or more processors;

[0081] A memory for storing program codes executable by the processor;

[0082] The processor is configured to execute the program code to implement the above-mentioned video generation method.

[0083] According to another aspect of an embodiment of the present disclosure, a computer-readable storage medium is provided. When a program code in the computer-readable storage medium is executed by a processor of an electronic device, the electronic device is enabled to execute the above-mentioned video generating method.

[0084] According to another aspect of an embodiment of the present disclosure, a computer program product is provided, including a computer program / instruction, which implements the above-mentioned video generation method when executed by a processor.

[0085] The disclosed embodiment provides a video generation method. In the process of generating a video in a video editing scene, a material generation control is displayed in a video editing interface so that by triggering the material generation control, artificial intelligence technology can be used to generate at least one of image material and video material, thereby enriching the material used for video generation. The material is then directly displayed in a video track so that after a subsequent video generation operation is triggered, a video can be directly generated based on the material in the video track. The operation is simple and there is no need to jump to other applications to generate image material or video material. The image / video material generation function is deeply integrated into the video editing scene, and the material generation and video generation can be seamlessly connected, thereby improving the video generation efficiency.

[0086] 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

[0087] 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.

[0088] Figure 1 It is a schematic diagram of an implementation environment of a video generation method according to an exemplary embodiment.

[0089] Figure 2 The figure is a flowchart of a video generating method according to an exemplary embodiment.

[0090] Figure 3 The figure is a flowchart of another video generating method according to an exemplary embodiment.

[0091] Figure 4 The diagram is a schematic diagram of a material generation control according to an exemplary embodiment.

[0092] Figure 5 The diagram is a schematic diagram of a material generation panel according to an exemplary embodiment.

[0093] Figure 6 The figure is a schematic diagram showing a method of determining a prompt text according to an exemplary embodiment.

[0094] Figure 7 The figure is a schematic diagram showing another method of determining a prompt text according to an exemplary embodiment.

[0095] Figure 8 The figure is a schematic diagram showing a method of determining a prompt image according to an exemplary embodiment.

[0096] Fig. 9 The figure is a schematic diagram showing another method of determining a prompt image according to an exemplary embodiment.

[0097] Fig.10 The figure is a schematic diagram showing a method of determining a prompt image according to an exemplary embodiment.

[0098] Fig.11 The figure is a schematic diagram showing a method of setting a material type according to an exemplary embodiment.

[0099] Fig.12 is a schematic diagram showing another method of setting a material type according to an exemplary embodiment.

[0100] Fig.13 The diagram is a schematic diagram showing a method of generating video material from first and last frames according to an exemplary embodiment.

[0101] Fig.14 is a schematic diagram showing a minimized material generation panel according to an exemplary embodiment.

[0102] Fig.15 The figure is a schematic diagram of selecting a material according to an exemplary embodiment.

[0103] Fig.16 The figure is a schematic diagram showing a method of updating image material according to an exemplary embodiment.

[0104] Fig.17 The figure is a schematic diagram of converting an image to a video according to an exemplary embodiment.

[0105] Fig.18 It is a schematic diagram showing a trigger extension operation according to an exemplary embodiment.

[0106] Fig.19 The diagram is a schematic diagram of a video extension panel according to an exemplary embodiment.

[0107] Fig. 20 is a schematic diagram of another video extension panel according to an exemplary embodiment.

[0108] Fig.21 The diagram is a schematic diagram showing a method of displaying incremental video materials according to an exemplary embodiment.

[0109] Fig. 22 The diagram is a schematic diagram showing another method of displaying incremental video materials according to an exemplary embodiment.

[0110] Fig.23 The diagram is a schematic diagram showing a method of generating transition material based on the first and last frames according to an exemplary embodiment.

[0111] Fig.24 The figure is a block diagram of a video generating device according to an exemplary embodiment.

[0112] Fig.25 It is a block diagram of a terminal according to an exemplary embodiment. DETAILED DESCRIPTION

[0113] 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.

[0114] 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.

[0115] It should be noted that the information (including but not limited to user device information, user personal information, etc.), data (including but not limited to data used for analysis, stored data, displayed data, etc.) and signals involved in this disclosure are all authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards of relevant countries and regions. For example, the prompt information involved in this disclosure is obtained with full authorization.

[0116] Figure 1 FIG. 1 is a schematic diagram of an implementation environment of a video generation method according to an exemplary embodiment. Figure 1The implementation environment specifically includes: a terminal 101 and a server 102. The terminal 101 and the server 102 can be directly or indirectly connected via wired or wireless communication, which is not limited in the present disclosure.

[0117] The terminal 101 is at least one of a smart phone, a smart watch, a desktop computer, a laptop, an MP3 player, an MP4 player, and a portable laptop computer. An application supporting video generation is running on the terminal 101. The application may be an editing application or a multimedia application, which is not limited in the embodiments of the present disclosure. A user can log in to the application through the terminal 101 to obtain the services provided by the application. For example, a user can generate a video through the application on the terminal 101. In the process of generating a video, the terminal 101 can use artificial intelligence technology to generate image materials or video materials, and then generate a video through the generated materials.

[0118] The terminal 101 generally refers to one of a plurality of terminals, and the present embodiment is described by taking the terminal 101 as an example. Those skilled in the art may know that the number of the above terminals may be more or less. For example, the above terminals may be several, or the above terminals may be dozens or hundreds, or a greater number. The present embodiment does not limit the number and device type of the terminals.

[0119] The server 102 is at least one of a single server, multiple servers, a cloud computing platform, and a virtualization center. The server 102 is used to provide background services for applications that support video generation. The server 102 can be connected to the terminal 101 via a wireless network or a wired network. The server 102 can provide the terminal 101 with various materials such as image materials, video materials, audio materials, and texture materials for generating videos, so that the terminal 101 can subsequently generate videos based on various materials. In some embodiments, the number of the above servers can be more or less, and the embodiments of the present disclosure are not limited to this. Of course, the server 102 also includes other functional servers to provide more comprehensive and diversified services.

[0120] Figure 2 is a flowchart of a video generation method according to an exemplary embodiment. Figure 2 , the video generation method is applied in a terminal, comprising the following steps:

[0121] In step 201, the terminal displays a video editing interface, in which a material generation control and a video track are displayed.

[0122] In the embodiment of the present disclosure, during the process of generating a video, the terminal displays a video editing interface so that the video can be subsequently generated through the video editing interface. The terminal displays a material generation control and a video track in the video editing interface. The material generation control is used to provide at least one of image materials and video materials generated using artificial intelligence technology. The embodiment of the present disclosure does not limit the display style and display position of the material generation control. The video track is used to display the material used in the video generation process, and the material includes at least one of image materials and video materials.

[0123] In step 202, in response to a triggering operation on a material generation control, the terminal generates a first material using artificial intelligence technology, where the first material includes at least one of an image material and a video material.

[0124] In the embodiment of the present disclosure, when the material generation control is triggered, the terminal uses artificial intelligence technology to generate the first material. The first material can be only an image material, or only a video material, or can include both image material and video material. The embodiment of the present disclosure does not limit the type and quantity of the material in the first material. Among them, the process of generating the material using artificial intelligence technology can be implemented based on an AI compiler.

[0125] In step 203, the terminal displays the first material in the video track.

[0126] In the embodiment of the present disclosure, after generating the first material, the terminal displays the first material in the video track. The essence of "displaying the first material" is to display multiple frames of images of the first material. The number of images of the first material is positively correlated with the display duration of the first material.

[0127] The video track supports material editing. That is, in the process of generating a video, the material in the video track can be edited. The user can edit the display duration or display effect of the material through the video track. The edited material will also be displayed in the video track. The embodiment of the present disclosure does not limit whether to edit the first material.

[0128] In step 204, in response to the video generation operation, the terminal generates a video based on the first material in the video track.

[0129] In an embodiment of the present disclosure, when a video generation operation is triggered, the terminal generates a video based on a first material in a video track. The video includes the first material. The display duration of the first material in the video is equal to the display duration of the first material in the video track. The material in the video track is called the first material.

[0130] The disclosed embodiment provides a video generation method. In the process of generating a video in a video editing scene, a material generation control is displayed in a video editing interface so that by triggering the material generation control, artificial intelligence technology can be used to generate at least one of image material and video material, thereby enriching the material used for video generation. The material is then directly displayed in a video track so that after a subsequent video generation operation is triggered, a video can be directly generated based on the material in the video track. The operation is simple and there is no need to jump to other applications to generate image material or video material. The image / video material generation function is deeply integrated into the video editing scene, and the material generation and video generation can be seamlessly connected, thereby improving the video generation efficiency.

[0131] In some embodiments, in response to a trigger operation on a material generation control, using artificial intelligence technology to generate a first material includes:

[0132] In response to a triggering operation on a material generation control, displaying a material generation panel;

[0133] Acquire prompt information, where the prompt information includes at least one of a prompt text and a prompt image, and the prompt information is used to indicate at least one of the content and style of the material to be generated;

[0134] Display prompt information in the material generation panel;

[0135] In response to the confirmation generation operation, artificial intelligence technology is used to generate a first material matching the prompt information.

[0136] The solution provided by the embodiment of the present disclosure can obtain at least one of a prompt text and a prompt image as prompt information during the process of generating materials, so as to subsequently generate the first material based on the prompt information. This not only enriches the material generation method, but also ensures that at least one of the content and style of the generated first material meets the prompt information. Since the prompt information is information actively obtained by the user and can be displayed in the material generation panel, the prompt information can accurately reflect the user's demand for the material, thereby ensuring that the generated first material meets the user's demand and improving the accuracy of material generation.

[0137] In some embodiments, the material generation control includes at least one of an image generation control, a video generation control, and a batch generation control, and the material generation panel includes at least one of an image generation panel, a video generation panel, and a batch generation panel;

[0138] In response to the confirmation generation operation, the first material matching the prompt information is generated using artificial intelligence technology, including any of the following:

[0139] In response to the confirmation generation operation in the image generation panel, based on the prompt information in the image generation panel, an image material matching the prompt information is generated using artificial intelligence technology;

[0140] In response to the confirmation generation operation in the video generation panel, based on the prompt information in the video generation panel, the artificial intelligence technology is used to generate video materials matching the prompt information;

[0141] In response to the confirmation generation operation in the batch generation panel, based on the multiple prompt information in the batch generation panel, artificial intelligence technology is used to generate image materials or video materials that match the multiple prompt information respectively.

[0142] The solution provided by the embodiment of the present disclosure can provide users with at least one of an image generation control, a video generation control and a batch generation control, so that users can obtain prompt information in a corresponding generation panel through a corresponding generation control according to needs to generate required image materials, video materials or batch materials. This not only enriches the material generation method, but also is simple to operate, and can obtain a certain image material, a certain video material or a batch material, etc. required by the user, thereby improving the material acquisition efficiency.

[0143] In some embodiments, other tracks besides the video track are displayed in the video editing interface;

[0144] Get prompt information, including:

[0145] When corresponding materials have been added to other tracks, the prompt information is determined based on the materials in the other tracks.

[0146] The solution provided by the embodiment of the present disclosure can determine prompt information according to the materials added in other tracks in the video editing interface during the process of generating image materials or video materials, thereby ensuring that the image materials or video materials subsequently generated based on the prompt information match the materials added in other tracks. Since the materials added in other tracks are materials actively added by the user, they can accurately reflect the video effects desired by the user (including at least one of the content and style). Therefore, it is ensured that the generated image materials or video materials meet the video effects desired by the user, that is, meet the user's intentions. This can not only reduce the probability of users editing image materials or video materials, which is beneficial to improving video generation efficiency, but also help improve the quality of subsequently generated videos.

[0147] In some embodiments, the material generation panel includes at least one of an image generation panel and a video generation panel;

[0148] When corresponding materials have been added to other tracks, the prompt information is determined based on the materials in other tracks, including:

[0149] In the case where corresponding materials have been added to other tracks, based on the position indicated by the time progress line in other tracks, the second material at the position is determined from other tracks;

[0150] Based on the second material, prompt information is determined.

[0151] The solution provided by the embodiment of the present disclosure, in the process of generating image materials or video materials, since the time progress line can indicate the position of the image material or video material to be generated in the video track, the prompt information is determined according to the second material indicated by the time progress line in other tracks, thereby ensuring that the image material or video material subsequently generated based on the prompt information matches the second material; since the materials indicated by the time progress line in each track will be displayed simultaneously in the subsequently generated video, it is ensured that the image material or video material matching the second material is displayed in the video simultaneously with the second material, which meets the user's intention and is conducive to improving the quality of the subsequently generated video.

[0152] In some embodiments, in a video track, displaying a first material includes:

[0153] According to the position of the second material in other tracks, the first material is displayed in the video track.

[0154] The solution provided by the embodiment of the present disclosure can display the first material according to the position of the second material in other tracks, thereby achieving the purpose of automatically aligning the matching first material and second material. Since the materials aligned between the tracks will be displayed simultaneously in the subsequently generated video, it is guaranteed that the first material matching the second material is displayed in the video simultaneously with the second material. This not only meets the user's intention, but also eliminates the need for the user to manually align the matching materials between the tracks, thus reducing user operations, can improve video generation efficiency, and is also conducive to improving the quality of subsequently generated videos.

[0155] In some embodiments, the prompt information includes the second material, the length of the first material is equal to the length of the second material, and the length of the material is used to indicate the display duration of the material.

[0156] The solution provided by the embodiment of the present disclosure is that the display duration of the first material matching the second material is the same as that of the second material, thereby ensuring that the first material and the second material are displayed and disappear at the same time in the subsequently generated video, thereby ensuring that the materials displayed at each time point in the subsequently generated video match each other, which is beneficial to improving the quality of the video.

[0157] In some embodiments, the material generation panel is a batch generation panel;

[0158] When corresponding materials have been added to other tracks, the prompt information is determined based on the materials in other tracks, including:

[0159] In the case where corresponding materials have been added to other tracks, prompt information corresponding to each of the plurality of second materials is determined based on the plurality of second materials in the other tracks.

[0160] The solution provided by the embodiment of the present disclosure can determine corresponding prompt information respectively according to the multiple second materials in other tracks when multiple second materials have been added, so that corresponding first materials can be generated based on each prompt information at one time later, without the user having to generate corresponding first materials for each second material respectively. The operation is simple and can improve the efficiency of material generation.

[0161] In some embodiments, in response to the confirmation generation operation, artificial intelligence technology is used to generate a first material matching the prompt information, including:

[0162] In response to the confirmation generation operation, based on the prompt information corresponding to each of the plurality of second materials in other tracks, artificial intelligence technology is used to respectively generate first materials corresponding to each of the prompt information;

[0163] In the video track, display the first clip, including:

[0164] The first material corresponding to each prompt information is displayed in the video track according to the order of the multiple second materials in other tracks.

[0165] The solution provided by the embodiment of the present disclosure can not only generate corresponding first materials according to the prompt information corresponding to the multiple second materials in other tracks, that is, it can generate multiple first materials at one time, thereby improving the material generation efficiency; but also the generated multiple first materials can be displayed in the order of the corresponding multiple second materials, so that the matching first materials and second materials are aligned, thereby ensuring that the matching materials are displayed in the video at the same time, which not only meets the user's intention, but also eliminates the need for the user to manually align the matching materials between tracks, reduces user operations, and can improve video generation efficiency and video quality.

[0166] In some embodiments, other tracks besides the video track are displayed in the video editing interface;

[0167] The method also includes:

[0168] For each prompt information corresponding to the second material in other tracks in the material generation panel, display the editing control corresponding to the prompt information;

[0169] In response to a triggering operation on the editing control, an editing panel of the prompt information is displayed, and the editing panel is used to edit the prompt information.

[0170] The solution provided by the embodiment of the present disclosure allows prompt information displayed in the material generation panel to be edited in the corresponding editing panel through corresponding editing controls, thereby ensuring that the prompt information meets the user's intention, which is beneficial to improving the accuracy of subsequent video generation and obtaining a video that meets the user's intention.

[0171] In some embodiments, a plurality of other tracks are displayed in addition to the video track in the video editing interface;

[0172] Get prompt information, including:

[0173] In response to a selection operation on any other track in the video editing interface, prompt information corresponding to each second material is determined based on each second material in the other track.

[0174] According to the solution provided by the embodiments of the present disclosure, during the process of generating image materials or video materials, the user can select any other track in the video editing interface, and determine the prompt information based on the materials in the other selected tracks, thereby ensuring that the prompt information meets the user's intention, which is beneficial to improving the accuracy of subsequent material generation and obtaining materials that meet the user's intention, thereby reducing the probability of users editing the materials, and further helping to improve video generation efficiency.

[0175] In some embodiments, the method further comprises:

[0176] For any prompt information in the material generation panel, in response to a type selection operation for the prompt information, the material type corresponding to the prompt information is displayed in the material generation panel;

[0177] In response to the confirmation generation operation, artificial intelligence technology is used to generate a first material matching the prompt information, including:

[0178] In response to the confirmation generation operation, artificial intelligence technology is used to generate a first material that matches the prompt information and conforms to the corresponding material type.

[0179] The solution provided by the embodiment of the present disclosure can, before generating materials, select the material type to which the material to be generated belongs for each prompt information in the material generation panel, so that in the subsequent material generation process, the corresponding type of material can be generated according to the selected material type, thereby ensuring that the type of generated material meets user needs, which is beneficial to improving the accuracy of subsequent video generation and obtaining a video that meets the user's intentions.

[0180] In some embodiments, for any prompt information in the material generation panel, in response to a type selection operation for the prompt information, the material type corresponding to the prompt information is displayed in the material generation panel, including:

[0181] For any prompt information in the material generation panel, a material selection control for the prompt information is displayed in the material generation panel;

[0182] In response to a trigger operation on a material selection control, an image type option and a video type option are displayed;

[0183] When any one of the image type option and the video type option is selected, the material type indicated by the selected type option is displayed in the material generation panel.

[0184] The solution provided by the embodiment of the present disclosure provides corresponding material selection controls for each prompt information in the material generation panel, so that the user can independently set the material type for each prompt information, which is not only simple to operate but also improves the flexibility of material type setting; and can also intuitively display the selected material type to the user, which is conducive to improving the utilization rate of the material generation panel and the efficiency of information transmission, so that the user can make timely adjustments to the material type that does not meet the intention.

[0185] In some embodiments, for any prompt information in the material generation panel, in response to a type selection operation for the prompt information, the material type corresponding to the prompt information is displayed in the material generation panel, including:

[0186] In response to a selection operation of any plurality of prompt information in the material generation panel, an image type option and a video type option are displayed;

[0187] When any one of the image type option and the video type option is selected, the material type indicated by the selected type option is displayed in the material generation panel.

[0188] The solution provided by the embodiment of the present disclosure can set the material types of multiple prompt information at one time, is simple to operate, and can improve the setting efficiency of the material types of multiple prompt information, thereby helping to improve the generation efficiency of the material.

[0189] In some embodiments, a template selection control is displayed in the material generation panel;

[0190] Get prompt information, including:

[0191] In response to a triggering operation on a template selection control, displaying a plurality of text templates;

[0192] In response to an application operation on any text template, the text template is determined as prompt information.

[0193] The solution provided by the embodiment of the present disclosure can provide multiple text templates for users to choose from during the process of generating materials based on text, which not only enriches the prompt text, but also eliminates the need for users to manually input prompt text. The operation is simple and can improve the efficiency of material generation.

[0194] In some embodiments, an image acquisition control is displayed in the material generation panel;

[0195] Get prompt information, including:

[0196] In response to a triggering operation on an image acquisition control, displaying a plurality of images;

[0197] In response to a selection operation on at least one image among the plurality of images, prompt information is determined based on the at least one image.

[0198] The solution provided by the embodiment of the present disclosure can obtain at least one image as prompt information to generate material. Compared with prompt text, image prompts contain more information and can more accurately reflect the user's requirements for materials, so that the material generated based on the image is more in line with the user's intention, that is, the accuracy rate is higher.

[0199] In some embodiments, in response to a selection operation on at least one image among the multiple images, based on the at least one image, determining prompt information includes:

[0200] For any image among the plurality of images, in response to a selection operation on the image, displaying the image in a prompt editing interface;

[0201] In response to a prompt selection operation on an image in a prompt editing interface, a prompt area in the image is determined, and the image and area prompt information for indicating the prompt area are determined as prompt information.

[0202] The solution provided by the embodiments of the present disclosure can select a prompt area in the image to be used as a prompt before generating material based on the image. This can not only more accurately indicate the user's requirements for the material, making the material generated based on the image more in line with the user's intention, that is, higher accuracy, but also, compared with the solution of generating material based on the entire image, generating material by using a certain area in the image can improve the flexibility of generating material based on the image, thereby being able to flexibly select effective information in the image to generate material.

[0203] In some embodiments, the method further comprises:

[0204] In response to a text input operation in the material generation panel, the input prompt text is displayed in the material generation panel;

[0205] In response to a trigger operation on an image acquisition control, multiple images are displayed, including any of the following:

[0206] In response to a trigger operation on the image acquisition control, based on the prompt text in the material generation panel, multiple images are displayed, and at least one of the content and style of the multiple images conforms to the prompt text;

[0207] In response to a triggering operation on an image acquisition control, multiple images are displayed based on a prompt text in a material generation panel, and at least one image among the multiple images whose content and style at least match the prompt text is highlighted.

[0208] The solution provided by the embodiment of the present disclosure can provide the user with an image that matches the prompt text based on the prompt text input by the user, so that material can be generated based on the image more quickly later, without the user having to manually search for the desired image, thereby improving the efficiency of material generation.

[0209] In some embodiments, the material generation panel includes a video generation panel, the prompt information in the video generation panel includes multiple images, and the video generation panel displays a first and last frame mode control;

[0210] In response to the confirmation generation operation, artificial intelligence technology is used to generate a first material matching the prompt information, including:

[0211] When the first and last frame mode control is triggered, in response to the confirmation generation operation, for any two adjacent images in the plurality of images in the video generation panel, an interpolation algorithm is used to process the two images to obtain a transition image between the two images;

[0212] A first material is generated based on a plurality of images in a video generation panel and transition images of the plurality of images.

[0213] The solution provided by the embodiment of the present disclosure can, in the process of generating video materials based on images, perform interpolation processing on multiple images used for video generation through the first and last frame mode controls to obtain transition images between the multiple images, thereby making the transition between the multiple images in the subsequently generated video more natural and improving the quality of the video.

[0214] In some embodiments, the method further comprises:

[0215] In the material generation panel, the first material is displayed;

[0216] In the video track, display the first clip, including:

[0217] In response to the selection operation of the first material, when the time progress line is in an idle area in the video track, the first material is displayed after the material added in the video track, and the idle area is an area in the video track where no material exists; or,

[0218] In response to a selection operation on the first material, when the time progress line is in a non-idle area in the video track, the first material is displayed between two materials closest to the time progress line in the video track.

[0219] The solution provided by the embodiment of the present disclosure can display the generated first material in the material generation panel for user selection. When the user selects the first material, the first material can be displayed in the video track according to the position of the time progress line. For example, the first material can be displayed after the material added to the video track, or the first material can be displayed between the two materials closest to the time progress line, thereby enriching the way of displaying materials in the video track.

[0220] In some embodiments, the method further comprises:

[0221] During the process of generating the first material, a minimize control is displayed in the material generation panel;

[0222] In response to a triggering operation on the minimize control, the material generation panel is minimized;

[0223] Highlighting a first target area in the video track, the first target area is used to indicate a position to be occupied by the first material in the video track;

[0224] In the video track, display the first clip, including:

[0225] The first material is displayed in the first target area.

[0226] The solution provided by the embodiment of the present disclosure can minimize the material generation panel through the minimization control in the material generation panel during the process of generating materials, so that other operations can be performed in the video editing interface without waiting for the material generation to be completed. For example, other prompt information can be obtained during the generation of the first material to prepare for the generation of the next material, and the existing materials in the video editing interface can be edited, etc., which can improve the video generation efficiency; and after minimizing the material generation panel, the first target area can also be highlighted in the video track to intuitively show the user the position occupied by the first material being generated, which is conducive to improving the user's control over the material generation and user experience.

[0227] In some embodiments, the method further comprises:

[0228] In response to an update operation on the first material in the video track, regenerate a third material;

[0229] Replace the first clip in the video track with the third clip.

[0230] The solution provided by the embodiment of the present disclosure can regenerate new materials and replace the existing materials in the video track through artificial intelligence technology, so that users can adjust unsatisfactory materials in accordance with user intentions.

[0231] In some embodiments, the method further comprises:

[0232] For any image material in the video track, in response to a conversion operation on the image material, a video material is generated based on the content and length of the image material, the content of the video material is related to the content of the image material, the length of the video material and the length of the image material meet a preset proportional relationship, and the length of the material is used to indicate the display duration of the material;

[0233] Replace the image clip in the video track with the video clip.

[0234] The solution provided by the embodiments of the present disclosure can convert the image materials already existing in the video track into video materials with relevant contents and corresponding display duration, increase the dynamic changes of the material content, make the material content more ornamental, and help improve the quality of subsequently generated videos; and the video material can be generated directly based on the image material, without the user having to re-obtain prompt information to generate the video material, the operation is simple, and the efficiency of generating visual materials can be improved.

[0235] In some embodiments, the method further comprises:

[0236] In response to an extension operation on any video material in the video track, a video extension panel is displayed;

[0237] Based on the extension prompt information in the video extension panel, the incremental video material matching the extension prompt information is displayed in the video track, the extension prompt information includes at least one of a prompt text and a prompt image, the extension prompt information is used to indicate at least one of the content and style of the incremental video material to be generated, and the incremental video material is located after the video material and connected to the video material.

[0238] The solution provided by the disclosed embodiment can extend any video material in a video track based on the video material. There is no need to regenerate the complete video material according to the prompt information used for the video material. It is only necessary to generate the extended part (i.e., incremental video material) according to the extension indication information, and connect the extended part with the original video material. Compared with regenerating the complete video material, the generated incremental video material has a smaller amount of data and can be generated faster, thereby improving the efficiency of extending the video.

[0239] In some embodiments, in response to an operation of extending any video material in a video track, a video extension panel is displayed, including any of the following:

[0240] In response to a triggering operation on any video material in a video track, a time window of the video material is displayed in the video track, the length of the time window represents the display duration of the video material, and when the length of the time window is equal to the maximum duration of the video material and a stretching operation on the time window is detected, a video extension panel is displayed;

[0241] For any video material in the video track, in response to an editing operation of the video material, an extension control is displayed in the video editing interface, and in response to a triggering operation on the extension control, a video extension panel is displayed.

[0242] The solution provided by the embodiment of the present disclosure can extend the time window of the video material, and when the time window continues to be extended when the length of the time window reaches the maximum length, a video extension panel is displayed to extend the video material; or, the video extension panel can be displayed to extend the video material by triggering the extension control in the video editing interface. This not only enriches the extension methods of the video material, but also is simple to operate and can improve the efficiency of extending the video.

[0243] In some embodiments, the incremental video material is at least one of the following:

[0244] The incremental video material is generated based on the prompt text entered in the video extension panel;

[0245] The incremental video material is generated based on the prompt image entered in the video extension panel. The prompt image is the image located at the last frame in the video material.

[0246] The solution provided by the embodiment of the present disclosure can generate incremental video materials by inputting prompt text, and can also generate incremental video materials according to the last frame image in the video material to be extended. This not only enriches the generation method of incremental video materials, but also generates incremental video materials according to the last frame image in the video material to be extended, thereby ensuring that the incremental video materials match the video material to be extended, which is beneficial to improving the quality of the video material.

[0247] In some embodiments, based on the extension prompt information in the video extension panel, the incremental video material matching the extension prompt information is displayed in the video track, including:

[0248] In the process of generating the incremental video material based on the extension prompt information, a second target area is highlighted in the video track, the second target area is used to indicate the position to be occupied by the incremental video material in the video track, and the second target area is located after the area occupied by the video material and connected to the area occupied by the video material;

[0249] After the incremental video material is generated, the incremental video material is displayed in the second target area.

[0250] The solution provided by the disclosed embodiment can highlight the second target area in the video track during the process of generating incremental video material, and intuitively show the user the position occupied by the incremental video material being generated. This can not only improve the utilization rate of the video editing interface and the efficiency of information transmission, but also help to enhance the user's control over the material generation, that is, improve the user experience.

[0251] In some embodiments, based on the extension prompt information in the video extension panel, the incremental video material matching the extension prompt information is displayed in the video track, including:

[0252] In the process of generating the incremental video material based on the extended prompt information, after the video material in the video track, the generated images in the incremental video material are displayed frame by frame until the incremental video material is completely generated.

[0253] The solution provided by the disclosed embodiment can, in the process of generating incremental video material, display the generated images in the incremental video material frame by frame after the video material in the video track, and intuitively show the user the generation progress of the incremental video material. This can not only improve the utilization rate of the video editing interface and the efficiency of information transmission, but also help to enhance the user's control over the material generation, that is, improve the user experience.

[0254] In some embodiments, the method further comprises:

[0255] In response to the transition material generation operation, determining the fourth material and the fifth material indicated by the transition material generation operation;

[0256] In the case where the fifth material is located after the fourth material, a transition material is generated based on the last frame image in the fourth material and the first frame image in the fifth material; or, in the case where the fifth material is located before the fourth material, a transition material is generated based on the first frame image in the fourth material and the last frame image in the fifth material;

[0257] Between the fourth material and the fifth material, a transition material is displayed.

[0258] The solution provided by the embodiment of the present disclosure can generate a transition material between any two adjacent materials in a video track, and display the transition material between the two materials, so that the transition between multiple materials in the subsequently generated video is more natural, which is conducive to improving the quality of the video.

[0259] In some embodiments, in response to a transition material generation operation, determining a fourth material and a fifth material indicated by the transition material generation operation includes:

[0260] In response to a triggering operation on a transition generation control in a video editing interface, a transition generation panel is displayed, wherein a first generation option and a second generation option are displayed in the transition generation panel, wherein the first generation option is used to indicate generation of a transition material between a fourth material and a material preceding the fourth material, and the second generation option is used to indicate generation of a transition material between the fourth material and a material following the fourth material, wherein the fourth material is the material indicated by the time progress line in the video track;

[0261] In the case where the first generation option is selected, determining a material preceding the fourth material as the fifth material;

[0262] In the case where the second generation option is selected, a material subsequent to the fourth material is determined as the fifth material.

[0263] The solution provided by the embodiment of the present disclosure displays the first generation option and the second generation option in the transition generation panel, so that in the process of generating transition material, the user can choose whether to generate transition material between the previous material or the next material, so that the generation of transition material is more flexible and controllable, and the transition material that meets the user's intention is obtained, thereby reducing the probability of users editing the material, and further helping to improve the efficiency of video generation.

[0264] In some embodiments, in response to a triggering operation on a transition generation control in a video editing interface, a transition generation panel is displayed, including:

[0265] In a case where the first material distance is greater than the second material distance, in response to a triggering operation on a transition generation control in the video editing interface, displaying in the transition generation panel that the first generation option is in a selected state;

[0266] In a case where the first material distance is less than the second material distance, in response to a triggering operation on a transition generation control in the video editing interface, displaying the second generation option in a selected state in the transition generation panel;

[0267] Among them, the first material distance is the distance between the position indicated by the time progress line in the video track and the previous material of the fourth material, and the second material distance is the distance between the position indicated by the time progress line in the video track and the next material of the fourth material.

[0268] The solution provided by the embodiment of the present disclosure automatically selects the generation option according to the position relationship (i.e., distance) between the position indicated by the time progress line in the video track and the material in the video track, without the need for manual selection by the user. The operation is simple and can improve the efficiency of material generation.

[0269] Above Figure 2The following is only a basic process of the present disclosure. The solution provided by the present disclosure is further described based on a specific implementation method. Figure 3 FIG. 1 is a flowchart of another video generation method according to an exemplary embodiment. Figure 3 , the method comprising:

[0270] In step 301, the terminal displays a video editing interface, in which a material generation control and a video track are displayed.

[0271] In the disclosed embodiment, during the process of generating a video, the terminal displays a material generation control and a video track in the video editing interface. The user can instruct the terminal to use at least one of the image material and video material generated by artificial intelligence technology through the material generation control so as to make a video later. The video track can show the user all the image materials or video materials used in the video generation process.

[0272] The embodiment of the present disclosure does not limit the display timing of the material generation control. Optionally, the material generation control can be fixedly displayed at a certain position in the video editing interface. Alternatively, the material generation control can also be displayed in the video editing interface when a certain condition is met. Optionally, in addition to the video track, other tracks are also displayed in the video editing interface. Other tracks may include audio tracks, subtitle tracks, sticker tracks, etc., which are not limited by the embodiment of the present disclosure. The material generation control can be displayed in the video editing interface only when the material added to other tracks reaches a preset number. For example, when the subtitles added to the subtitle track reach a preset number, the terminal displays the material generation control in the video editing interface.

[0273] Since the materials in all tracks need to be aggregated during the video generation process, if there are materials in other tracks, corresponding image materials or video materials should also be added to the video track to avoid the situation where the subsequently generated video only includes other materials (such as subtitles, audio) at a certain time and there is no picture (such as image material, video material), that is, a black screen. When there are more materials in other tracks, the material generation control can be displayed to prompt the user that the corresponding picture can be generated for the materials in other tracks more quickly through artificial intelligence technology, which is conducive to improving the efficiency of video generation. If there is no material in other tracks, the material generation control can be not displayed to save operating consumption.

[0274] This public embodiment does not limit the display location of the material generation control. For example, the material generation control can be directly displayed in the operation panel of the video editing interface; or, the material generation control can also be displayed on the video track; or, the material generation control can also be displayed in the prompt window. The prompt window is used to prompt the user that the video may have a black screen and instruct the user to generate material through the material generation control.

[0275] For example, Figure 4 is a schematic diagram of a material generation control according to an exemplary embodiment. Figure 4 The video editing interface includes a preview area 401 and an operation area 402. The operation area 402 displays multiple material tracks such as a video track 403, an audio track 404, a subtitle track 405, and a sticker track 406, as well as an operation panel 407. The video track 403 is used to display image materials or video materials used in the video generation process. The preview area 401 is used to preview the material indicated by the time progress line 408 in the video track 403. Figure 4 In (a), the material generation control 409 is fixedly displayed in the operation panel 407. Figure 4 In (b), in the scenario of editing subtitles, the material generation control 409 can be displayed on the video track 403. Figure 4 In (c), when a black screen appears in the preview area 401, the terminal displays a prompt window 410 in the video editing interface to prompt the user that a black screen exists and to instruct the user to generate material through the material generation control. The material generation control 409 is displayed in the prompt window 410.

[0276] In step 302, in response to a triggering operation on a material generation control, the terminal displays a material generation panel.

[0277] In an embodiment of the present disclosure, when a material generation control is triggered, the terminal displays a material generation panel in a video editing interface. The material generation control may include at least one of an image generation control, a video generation control, and a batch generation control. The material generation panel may include at least one of an image generation panel, a video generation panel, and a batch generation panel. The terminal may generate image material through an image generation panel, generate video material through a video generation panel, and generate multiple materials at one time through a batch generation panel. The multiple materials include at least one of an image material and a video material.

[0278] For example, Figure 5 is a schematic diagram of a material generation panel according to an exemplary embodiment. Figure 5, the terminal displays a material generation control 502 in the operation panel 501 of the video editing interface. When the material generation control 502 is triggered, the terminal displays at least one secondary generation control such as an image generation control 503, a video generation control 504, and a batch generation control 505 in the operation panel 501. When the image generation control 503 is triggered, the terminal displays an image generation panel 506 in the video editing interface. The user can enter prompt information such as picture keywords (prompt text), prompt images, material styles, and frame ratios in the image generation panel 506, so that the terminal can subsequently generate image materials based on the prompt information in the image generation panel 506. When the video generation control 504 is triggered, the terminal displays a video generation panel 507 in the video editing interface. The user can enter prompt information such as graphic descriptions (prompt text), prompt images, material instruction requirements, camera movements, and duration in the video generation panel 507, so that the terminal can subsequently generate video materials based on the prompt information in the image generation panel 507. When the batch generation control 505 is triggered, the terminal displays a batch generation panel 508 in the video editing interface. The user can input prompt information and the material type (image or video) of the material to be generated in the batch generation panel 508 , so that the subsequent terminal can generate at least one of the image material and the video material based on the information in the batch generation panel 508 .

[0279] In step 303, the terminal obtains prompt information and displays the prompt information in the material generation panel. The prompt information includes at least one of a prompt text and a prompt image. The prompt information is used to indicate at least one of the content and style of the material to be generated.

[0280] In the embodiment of the present disclosure, the prompt information used to generate the material includes at least one of a prompt text and a prompt image. The prompt information can be information manually input by the user, or can be selected from multiple candidate information, which is not limited in the embodiment of the present disclosure. After obtaining the prompt information, the terminal displays the prompt information in the material generation panel, and intuitively shows the user the prompt information used for subsequent material generation.

[0281] In some embodiments, the prompt information includes prompt text. A template selection control is displayed in the material generation panel. The prompt text can be selected by the user from multiple text templates. Accordingly, the process of the terminal obtaining the prompt information includes: in response to the trigger operation of the template selection control, the terminal displays multiple text templates. Then, in response to the application operation of any text template, the terminal determines the text template as prompt information. The solution provided by the embodiment of the present disclosure can provide multiple text templates for users to choose from in the process of generating materials based on text, which not only enriches the prompt text, but also eliminates the need for users to manually enter the prompt text, is simple to operate, and can improve the efficiency of material generation.

[0282] For example, Figure 6 A schematic diagram showing a method of determining a prompt text according to an exemplary embodiment. Figure 6 In the process of generating image materials based on text, a template selection control 602 is displayed in the image generation panel 601. When the template selection control 602 is triggered, the terminal displays multiple text templates. Multiple text templates can be displayed according to their styles. Due to the display of the screen size, Figure 6 Only the first few text templates are shown as examples. For any text template, the terminal can display an image example corresponding to the text template to exemplarily show the user the style of the image generated based on the text template. When the application control 603 of the text template 2 is triggered, the terminal displays the text template 2 in the prompt box 604 in the image generation panel 601. Alternatively, the user can also directly enter the prompt text in the prompt box 604.

[0283] For example, Figure 7 FIG. 1 is a schematic diagram showing another method of determining a prompt text according to an exemplary embodiment. Figure 7 In the process of generating video material based on text, the video generation panel 701 displays the options of "Image-generated video" and "Text-generated video". When the "Text-generated video" option is selected, the terminal displays a prompt box 702 in the video generation panel 701. In response to the text input operation in the prompt box 702, the terminal displays the input prompt text in the prompt box 702. The prompt text can also come from multiple text templates, similar to Figure 6 The video generation panel 701 also displays quality options such as "high performance" and "high performance" so that the user can specify the quality of the video material. The video generation panel 701 can also display a duration selection control 703, an aspect ratio selection control 704, etc. so that the user can set the duration and aspect ratio of the video material.

[0284] In some embodiments, the prompt information includes a prompt image. An image acquisition control is displayed in the material generation panel. The prompt image can be selected by the user from multiple images. Accordingly, the process of the terminal obtaining the prompt information includes: in response to the triggering operation of the image acquisition control, the terminal displays multiple images. Then, in response to the selection operation of at least one image among the multiple images, the terminal determines the prompt information based on the at least one image. The solution provided by the embodiment of the present disclosure can obtain at least one image as prompt information to generate material. Compared with the prompt text, the image prompt has more information and can more accurately reflect the user's requirements for the material, so that the material generated based on the image is more in line with the user's intention, that is, the accuracy rate is higher.

[0285] Among them, the terminal can use the selected whole image as prompt information, or the terminal can also use the local area in the image as prompt information, which is not limited in the embodiment of the present disclosure. Optionally, in the process of determining the prompt information, the user can select the local area of ​​the image as the prompt. Accordingly, the process of determining the prompt information based on at least one image by the terminal includes: for any image of the multiple images, in response to the selection operation of the image, the terminal displays the image in the prompt editing interface. In response to the prompt selection operation of the image in the prompt editing interface, the terminal determines the prompt area in the image, and determines the image and the regional prompt information used to indicate the prompt area as the prompt information. The scheme provided by the embodiment of the present disclosure can select the prompt area in the image used as a prompt before generating materials based on the image, which can not only more accurately indicate the user's requirements for the material, so that the material generated based on the image is more in line with the user's intention, that is, the accuracy is higher, and compared with the scheme of generating materials based on the entire image, generating materials through a certain area in the image is conducive to improving the flexibility of generating materials based on the image, so that the effective information in the image can be flexibly selected to generate materials.

[0286] For example, Figure 8 FIG. 1 is a schematic diagram showing a method of determining a prompt image according to an exemplary embodiment. Figure 8 In the process of generating image materials based on images, an image acquisition control 802 is displayed in the image generation panel 801. When the image acquisition control 802 is triggered, the terminal displays multiple images. When image 1 is selected, the terminal displays image 1 in the prompt editing interface. The prompt editing interface also displays multiple area options, such as the "character appearance" option and the "subject" option. When any option is selected, the terminal highlights the area indicated by the option in the prompt editing interface, that is, the prompt area. The prompt editing interface also displays a smear control 803 and an elimination control 804. When the smear control 803 is triggered, in response to the touch operation on image 1, the terminal determines the area crossed by the touch operation as the prompt area. When the elimination control 804 is triggered, in response to the touch operation on image 1, the terminal determines the area crossed by the touch operation as the non-prompt area, that is, cancels the prompt. Then, in response to the triggering operation of the completion control 805 in the prompt editing interface, the terminal determines the prompt area in the image, determines the image and the regional prompt information for indicating the prompt area as prompt information, and displays them in the prompt box 806. It can be seen from the prompt box 806 that the prompt area of ​​the image 1 is the main body area, and the main content of the main body area is "a beautiful woman with big eyes and curly hair".

[0287] For the selected prompt image, the terminal can also modify the prompt image. Figure 8, when the image 1 in the prompt box 806 is triggered, the terminal displays the editing panel 807 of the image 1 in the image generation panel 801. The editing panel 807 displays an editing control 808, a replacement control 809, and a deletion control 810. When the editing control 808 is triggered, the terminal displays the prompt editing interface again so that the user can re-edit the prompt area in the image 1. When the replacement control 809 is triggered, the terminal displays multiple images again so that the user can re-select the prompt image. When the deletion control 810 is triggered, the terminal deletes the image 1 in the prompt box 806.

[0288] For example, Fig. 9 FIG. 1 is a schematic diagram showing another method of determining a prompt image according to an exemplary embodiment. Fig. 9 In the process of generating video material based on the image, an image acquisition control 902 is displayed in the video generation panel 901. When the image acquisition control 902 is triggered, the terminal displays multiple images. When image 6 is selected, the terminal displays image 6 in the prompt box 903 of the video generation panel 901. The user can also enter a prompt text in the prompt box 903 so that the video material can be generated based on the prompt image and the prompt text later. In the video generation panel, the terminal can also set the video quality, camera movement and duration. For example, in the process of setting the camera movement, the terminal can also display multiple camera movement options and preview the camera movement effect indicated by the selected camera movement option.

[0289] In the process of displaying multiple images, the terminal can provide images to the user according to the prompt text input by the user. Accordingly, in response to the text input operation in the material generation panel, the terminal displays the input prompt text in the material generation panel. Then, in response to the triggering operation of the image acquisition control, the terminal displays multiple images based on the prompt text in the material generation panel. At least one of the content and style of the multiple images conforms to the prompt text. Alternatively, in response to the triggering operation of the image acquisition control, multiple images are displayed based on the prompt text in the material generation panel, and at least one image in which at least one of the content and style of the multiple images conforms to the prompt text is highlighted. The scheme provided by the embodiment of the present disclosure can provide the user with images that conform to the prompt text according to the prompt text input by the user, so that the material can be generated based on the image more quickly in the future, without the need for the user to manually search for the desired image, and the material generation efficiency can be improved.

[0290] In some embodiments, other tracks besides the video track are also displayed in the video editing interface. The terminal can determine the prompt information according to the materials added in the other tracks. Accordingly, the process of the terminal obtaining the prompt information includes: when the corresponding materials have been added in the other tracks, the terminal determines the prompt information based on the materials in the other tracks.

[0291] The solution provided by the embodiment of the present disclosure can determine prompt information according to the materials added in other tracks in the video editing interface during the process of generating image materials or video materials, thereby ensuring that the image materials or video materials subsequently generated based on the prompt information match the materials added in other tracks. Since the materials added in other tracks are materials actively added by the user, they can accurately reflect the video effects desired by the user (including at least one of the content and style). Therefore, it is ensured that the generated image materials or video materials meet the video effects desired by the user, that is, meet the user's intentions. This can not only reduce the probability of users editing image materials or video materials, which is beneficial to improving video generation efficiency, but also help improve the quality of subsequently generated videos.

[0292] For example, the terminal can generate prompt text or prompt image according to the subtitles in the subtitle track, and display it in the material generation panel. The terminal can also display subtitles used to generate prompt information in the material generation panel, which is not limited in the embodiment of the present disclosure.

[0293] The material generation panel includes at least one of an image generation panel and a video generation panel. Accordingly, the process of the terminal determining the prompt information based on the material in other tracks includes: when the corresponding material has been added to the other tracks, the terminal determines the second material at the position from the other tracks based on the position indicated by the time progress line in the other tracks; and determines the prompt information based on the second material. The material in the other tracks except the video track is called the second material.

[0294] The solution provided by the embodiment of the present disclosure, in the process of generating image materials or video materials, since the time progress line can indicate the position of the image material or video material to be generated in the video track, the prompt information is determined according to the second material indicated by the time progress line in other tracks, thereby ensuring that the image material or video material subsequently generated based on the prompt information matches the second material; since the materials indicated by the time progress line in each track will be displayed simultaneously in the subsequently generated video, it is ensured that the image material or video material matching the second material is displayed in the video simultaneously with the second material, which meets the user's intention and is conducive to improving the quality of the subsequently generated video.

[0295] Alternatively, the material generation panel includes a batch generation panel. Accordingly, the process of the terminal determining prompt information based on the materials in other tracks includes: when corresponding materials have been added to other tracks, the terminal determines the prompt information corresponding to each of the multiple second materials based on the multiple second materials in the other tracks. The solution provided by the embodiment of the present disclosure can determine the corresponding prompt information based on the multiple second materials in the other tracks when multiple second materials have been added to other tracks, so that the corresponding first material can be generated based on each prompt information at one time later, without the user having to generate the corresponding first material for each second material. The operation is simple and can improve the efficiency of material generation.

[0296] For example, Fig.10 FIG. 1 is a schematic diagram showing a method of determining a prompt image according to an exemplary embodiment. Fig.10 , multiple subtitles have been added to the subtitle track, but there are fewer or even no materials in the video track. In this case, the user can use the batch generation control to batch generate multiple materials based on multiple subtitles. In the process of batch generating materials, the terminal displays the prompt information determined based on the multiple subtitles in the form of a list in the batch generation panel. The prompt information corresponding to each subtitle can be generated using artificial intelligence technology.

[0297] In some embodiments, the terminal can also edit the prompt information in the material generation panel. For the prompt information corresponding to each second material in other tracks in the material generation panel, the terminal displays the editing control corresponding to the prompt information. In response to the triggering operation of the editing control, the terminal displays the editing panel of the prompt information. The editing panel is used to edit the prompt information. The solution provided by the embodiment of the present disclosure, for the prompt information displayed in the material generation panel, the prompt information can be edited in the corresponding editing panel through the corresponding editing control, thereby ensuring that the prompt information meets the user's intention, which is beneficial to improving the accuracy of subsequent video generation and obtaining a video that meets the user's intention.

[0298] For example, see Fig.10, each prompt information corresponds to an editing control, and when the editing control is triggered, the terminal displays an editing panel for editing the corresponding prompt information. The embodiment of the present disclosure does not limit the display style of the editing panel. Optionally, the editing panel used to edit the prompt information can be any panel in this solution that can obtain prompt information, such as an image generation panel, a video generation panel, or a video extension panel. That is, when editing the prompt information, the terminal can jump from the current interface to the panel of the corresponding scene to reacquire the prompt information. The scene can be a scene for generating image materials, a scene for generating video materials, or a scene for extending a video, etc. Alternatively, the editing panel can also be a panel that has the same display style as any panel in this solution that can obtain prompt information, and exists independently, etc. Alternatively, the editing panel is different from the display style of any other panel.

[0299] In some embodiments, in addition to the video track, multiple other tracks are displayed in the video editing interface. The user can select any other track from the multiple other tracks to determine the prompt information based on the second material in the selected other track. Accordingly, the process of the terminal obtaining the prompt information is: in response to the selection operation of any other track in the video editing interface, the terminal determines the prompt information corresponding to each second material based on each second material in the other track. Among them, the selection operation can be a long press operation, for example, in response to the long press operation of any other track, the terminal determines the corresponding prompt information based on the second material in the other track that is long pressed. Or, the selection operation includes a long press operation and an application operation on the track, for example, in response to the long press operation of any other track, the terminal displays the application controls of multiple other tracks in the video editing interface, and in response to the triggering operation of the application control of any other track, the terminal determines the corresponding prompt information based on the second material in the other track that is triggered. Or, the selection operation can also be a drag operation, for example, for any other track, in response to the other track being dragged to the video track, the terminal determines the corresponding prompt information based on the second material in the other track. The embodiment of the present disclosure does not limit the selection operation.

[0300] According to the solution provided by the embodiments of the present disclosure, during the process of generating image materials or video materials, the user can select any other track in the video editing interface, and determine the prompt information based on the materials in the other selected tracks, thereby ensuring that the prompt information meets the user's intention, which is beneficial to improving the accuracy of subsequent material generation and obtaining materials that meet the user's intention, thereby reducing the probability of users editing the materials, and further helping to improve video generation efficiency.

[0301] In some embodiments, for any prompt information in the material generation panel, in response to the type selection operation of the prompt information, the terminal displays the material type corresponding to the prompt information in the material generation panel. In response to confirming the generation operation, the terminal uses artificial intelligence technology to generate a first material that matches the prompt information and conforms to the corresponding material type. The solution provided by the embodiment of the present disclosure can select the material type to which the material to be generated belongs for each prompt information in the material generation panel before generating the material, so that in the subsequent material generation process, the corresponding type of material can be generated according to the selected material type, thereby ensuring that the type of the generated material meets the user's needs, which is conducive to improving the accuracy of subsequent video generation and obtaining a video that meets the user's intention.

[0302] The terminal may independently set a material type for each prompt information, or the terminal may set a material type for multiple prompt information at one time. This embodiment of the present disclosure does not limit this.

[0303] In some embodiments, the terminal sets the material type independently for each prompt information. Accordingly, for any prompt information in the material generation panel, the terminal displays the material selection control of the prompt information in the material generation panel. In response to the triggering operation of the material selection control, the terminal displays the image type option and the video type option. When any type option of the image type option and the video type option is selected, the terminal displays the material type indicated by the selected type option in the material generation panel. The solution provided by the embodiment of the present disclosure provides a corresponding material selection control for each prompt information in the material generation panel, so that the user can set the material type independently for each prompt information, which is not only simple to operate, but also improves the flexibility of the material type setting; and it can also intuitively display the selected material type to the user, which is conducive to improving the utilization rate of the material generation panel and the efficiency of information transmission, so that the user can make timely adjustments to the material type that does not meet the intention.

[0304] For example, Fig.11 FIG. 1 is a schematic diagram showing a method of setting a material type according to an exemplary embodiment. Fig.11 Each prompt information has a type selection control corresponding to it, which is used to determine the material type corresponding to the prompt information. The material type includes image type and video type, so that the subsequent terminal can generate image material or video material based on the prompt information. The selected material type can be displayed in the batch generation panel. Fig.11 It can be seen that the material types corresponding to prompt information 1, prompt information 2 and prompt information 5 are image types; the material types corresponding to prompt information 3, prompt information 4 and prompt information 6 are video types.

[0305] In other embodiments, the terminal can set the material type for multiple prompt information at one time. Accordingly, in response to the selection operation of any multiple prompt information in the material generation panel, the terminal displays an image type option and a video type option. When any type option of the image type option and the video type option is selected, the terminal displays the material type indicated by the selected type option in the material generation panel. The solution provided by the embodiment of the present disclosure provides corresponding material selection controls for each prompt information in the material generation panel, so that the user can set the material type independently for each prompt information, which is not only simple to operate, but also improves the flexibility of material type setting; and it can also intuitively display the selected material type to the user, which is conducive to improving the utilization rate of the material generation panel and the efficiency of information transmission, so that the user can make timely adjustments to the material type that does not meet the intention.

[0306] For example, Fig.12 FIG. 1 is a schematic diagram showing another method of setting a material type according to an exemplary embodiment. Fig.12 When prompt information 3, prompt information 4 and prompt information 6 are selected, the terminal displays image type option 1201 and video type option 1202. When video type option 1202 is triggered, the terminal displays prompt information 3, prompt information 4 and prompt information 6 corresponding to the video type.

[0307] In step 304, in response to confirming the generation operation, the terminal uses artificial intelligence technology to generate a first material that matches the prompt information and displays the first material in the video track.

[0308] In the embodiment of the present disclosure, when it is confirmed that the generation operation is triggered, the terminal uses artificial intelligence technology to generate a first material that matches the prompt information, and then displays the first material in the video track.

[0309] In some embodiments, the terminal can use artificial intelligence technology to generate corresponding materials in any of the above-mentioned material generation panels. Accordingly, in response to the confirmation generation operation in the image generation panel, the terminal uses artificial intelligence technology based on the prompt information in the image generation panel to generate image materials that match the prompt information. Or, in response to the confirmation generation operation in the video generation panel, the terminal uses artificial intelligence technology based on the prompt information in the video generation panel to generate video materials that match the prompt information. Or, in response to the confirmation generation operation in the batch generation panel, the terminal uses artificial intelligence technology based on multiple prompt information in the batch generation panel to generate image materials or video materials that match multiple prompt information. The solution provided by the embodiment of the present disclosure can provide users with at least one of an image generation control, a video generation control, and a batch generation control, so that users can obtain prompt information in the corresponding generation panel according to their needs through the corresponding generation control to generate the required image material, video material, or batch material, which not only enriches the material generation method, but also is simple to operate, and can obtain a certain image material, a certain video material, or a batch material required by the user, etc., and improves the material acquisition efficiency.

[0310] In some embodiments, the material generation panel includes a video generation panel. In the process of generating a video based on an image, the terminal can use artificial intelligence technology to expand the content of a single image to obtain video material. Alternatively, the terminal can also use artificial intelligence technology to supplement the transition content of multiple images to obtain video material.

[0311] Optionally, the prompt information in the video generation panel includes multiple images. A first and last frame mode control is displayed in the video generation panel. Accordingly, the process of the terminal generating the first material matching the prompt information includes: when the first and last frame mode control is triggered, in response to confirming the generation operation, for two adjacent images in any order among the multiple images in the video generation panel, the terminal uses an interpolation algorithm to process the two images to obtain a transition image between the two images. The terminal generates the first material based on the multiple images in the video generation panel and the transition images of the multiple images. The solution provided by the embodiment of the present disclosure, in the process of generating video materials based on images, can interpolate the multiple images used for video generation through the first and last frame mode control to obtain a transition image between the multiple images, so that the transition between the multiple images in the subsequently generated video is more natural, thereby improving the quality of the video.

[0312] For example, Fig.13 FIG. 1 is a schematic diagram showing a method of generating a video material from the first and last frames according to an exemplary embodiment. Fig.13, a first and last frame mode control 1302 is displayed in the video generation panel 1301. When the first and last frame mode control 1302 is triggered, the terminal displays a first frame image acquisition control 1303 and a last frame image acquisition control 1304 in the video generation panel 1302. In response to the triggering operation of any image acquisition control, the terminal displays multiple images for the user to select, and displays the image selected by the user at the corresponding position. Fig.13 It can be seen that image 3 is the first frame image and image 6 is the last frame image. Then, in response to the trigger operation of the generation control 1305, the terminal uses an interpolation algorithm to Figure 3 The terminal then processes image 3 and image 6 to obtain a transition image between the two images. Then, the terminal places the transition image between image 3 and image 6 to generate video material. Figure 3 It is the first frame image of the video material. Figure 6 It is the last frame image of the video material.

[0313] In some embodiments, considering that the material generation process usually takes a while, in order not to hinder the user from continuing the operation, the present solution can minimize the material generation panel to achieve asynchronous generation and display of the material. Accordingly, in the process of generating the first material, the terminal displays a minimize control in the material generation panel. In response to the triggering operation of the minimize control, the terminal minimizes the material generation panel. The terminal highlights the first target area in the video track, and the first target area is used to indicate the position to be occupied by the first material in the video track. Then, the terminal displays the first material in the first target area.

[0314] The solution provided by the embodiment of the present disclosure can minimize the material generation panel through the minimization control in the material generation panel during the process of generating materials, so that other operations can be performed in the video editing interface without waiting for the material generation to be completed. For example, other prompt information can be obtained during the generation of the first material to prepare for the generation of the next material, and the existing materials in the video editing interface can be edited, etc., which can improve the video generation efficiency; and after minimizing the material generation panel, the first target area can also be highlighted in the video track to intuitively show the user the position occupied by the first material being generated, which is conducive to improving the user's control over the material generation and user experience.

[0315] For example, Fig.14 is a schematic diagram showing a minimized material generation panel according to an exemplary embodiment. Fig.14In response to the triggering operation of generating control 1402 in video generating panel 1401, the terminal generates video material based on prompt information such as prompt image (image 6), video quality options, camera movement, duration, etc. in video generating panel 1401. In the process of generating video material, the terminal displays minimized control 1403 in video generating panel 1401. When minimized control 1403 is triggered, the terminal minimizes video material generating panel 1401. The terminal highlights the target area (gray part) in video track 1404 to indicate the position to be occupied by the video material in the video track. Then, after the generation is completed, the terminal displays multiple frames of images of the video material in the target area. In the process of generating video material, the terminal can also display the generation progress of the video material, such as 18%, 80%.

[0316] In some embodiments, after the material is generated, the terminal may first display it in the material generation panel for user confirmation, and then display it in the material track. Accordingly, the terminal displays the first material in the material generation panel. Then, in response to the selection operation of the first material, when the time progress line is in an idle area in the video track, the terminal displays the first material after the material added in the video track, and the idle area is an area where there is no material in the video track. Alternatively, in response to the selection operation of the first material, when the time progress line is in a non-idle area in the video track, the terminal displays the first material between the two materials closest to the time progress line in the video track. That is, the terminal can add the newly generated material after the material added in the video track, and can also add and insert the newly generated material between the two added materials nearby.

[0317] The solution provided by the embodiment of the present disclosure can display the generated first material in the material generation panel for user selection. When the user selects the first material, the first material can be displayed in the video track according to the position of the time progress line. For example, the first material can be displayed after the material added to the video track, or the first material can be displayed between the two materials closest to the time progress line, thereby enriching the way of displaying materials in the video track.

[0318] In the process of generating materials, the terminal can generate multiple materials at one time and display them in the material generation panel for the user to select. When any material is selected, the terminal adds the material to the video track.

[0319] For example, Fig.15 FIG. 1 is a schematic diagram showing a method of selecting a material according to an exemplary embodiment. Fig.15In the process of generating image materials, in response to the triggering operation of the generation control 1502 in the image generation panel 1501, the terminal generates multiple image materials based on the prompt information such as the text prompt (text template 2), style, and aspect ratio in the image generation panel 1501. The terminal displays multiple image materials in the image generation panel 1501, including image material 1, image material 2, image material 3, and image material 4. In response to the selection operation of image material 1, the terminal displays multiple frames of image material 1 in the video track 1503. The multiple frames of images are obtained based on copying image material 1. The number of image frames of image material 1 is positively correlated with the display duration of image material 1 in the video to be generated. The user can automatically adjust the number of image frames of image material 1.

[0320] In the process of displaying materials in the video track, in addition to the aforementioned display of the newly generated materials according to the position indicated by the time progress line, the terminal can also display the newly generated materials according to the position of the materials added in other tracks.

[0321] In some embodiments, the first material is generated based on the prompt information corresponding to the second material. Accordingly, the process of the terminal displaying the first material in the video track includes: the terminal displays the first material in the video track according to the position of the second material in other tracks. The solution provided by the embodiment of the present disclosure can display the first material according to the position of the second material in other tracks, and achieves the purpose of automatically aligning the matching first material and second material. Since the materials aligned between the tracks will be displayed simultaneously in the subsequently generated video, it is guaranteed that the first material matching the second material is displayed in the video at the same time as the second material. This not only meets the user's intention, but also eliminates the need for the user to manually align the matching materials between the tracks, reduces user operations, can improve video generation efficiency, and is also conducive to improving the quality of the subsequently generated video.

[0322] Among them, the prompt information used to generate the first material includes the second material. Accordingly, the length of the first material is equal to the length of the second material. The length of the material is used to indicate the display duration of the material. That is, the terminal can generate the first material with the same display duration according to the display duration of the second material in the prompt information. In the process of displaying the first material, the first material and the second material can achieve the effects of position alignment and duration alignment. In the scheme provided by the embodiment of the present disclosure, the display duration of the first material matching the second material is the same as that of the second material, which ensures that the first material and the second material are displayed and disappear at the same time in the subsequently generated video, thereby ensuring that the materials displayed at each time point in the subsequently generated video match each other, which is beneficial to improving the quality of the video.

[0323] In other embodiments, during the process of batch generating materials, there are multiple second materials in other tracks. In response to confirming the generation operation, the terminal uses artificial intelligence technology to generate first materials corresponding to each prompt information based on the prompt information corresponding to each of the multiple second materials in other tracks. Then, the terminal displays the first materials corresponding to each prompt information in the video track in the order of the multiple second materials in other tracks. The solution provided by the embodiment of the present disclosure can not only generate corresponding first materials according to the prompt information corresponding to the multiple second materials in other tracks, that is, it can generate multiple first materials at one time, thereby improving the material generation efficiency; and the generated multiple first materials can be displayed in the order of the corresponding multiple second materials, so that the matching first materials and the second materials are aligned with each other, thereby ensuring that the matching materials will be displayed in the video at the same time, which not only meets the user's intention, but also does not require the user to manually align the matching materials between tracks, reduces user operations, and can improve video generation efficiency and video quality.

[0324] In the embodiment of the present disclosure, after displaying the generated material in the video track, the terminal can also edit the material in the video track. For example, the terminal can regenerate the existing material in the video track; or the terminal can also convert the image material in the video track into the video material; or the terminal can also extend the video material; or the terminal can also perform transition processing on the existing material in the video track, etc., which is not limited in the embodiment of the present disclosure.

[0325] In some embodiments, the terminal can regenerate the existing material in the video track. Accordingly, in response to the update operation of the first material in the video track, the terminal regenerates the third material. Then, the terminal replaces the first material in the video track with the third material. The solution provided by the embodiment of the present disclosure can regenerate new material and replace the existing material in the video track through artificial intelligence technology, so that the user can adjust the unsatisfactory material in accordance with the user's intention.

[0326] For example, Fig.16 FIG. 1 is a schematic diagram showing a method of updating image material according to an exemplary embodiment. Fig.16, for the image material 1 in the video track 1601, in response to the triggering operation of the image generation control 1601, the terminal displays the image generation panel 1603. The image generation panel 1603 displays a plurality of image materials generated previously, a regeneration control 1604 and an adjustment requirement control 1605. When the regeneration control 1604 is triggered, the terminal regenerates a plurality of image materials based on the prompt information used to generate the image material 1, and displays them in the image generation panel 1603. When the adjustment requirement control 1605 is triggered, the terminal can display the prompt information (such as prompt text, style, aspect ratio, etc.) used to generate the image material 1, so that the user can edit the prompt information. Then, in response to the triggering operation of the generation control 1606, the terminal regenerates a plurality of image materials based on the edited prompt information, and displays them in the image generation panel 1603. Then, when the image material 5 is triggered, the terminal replaces the image material 1 in the video track with the image material 5. The principle of updating the video material is the same as the principle of updating the image material, which will not be repeated here.

[0327] In some embodiments, the terminal is capable of converting the image material in the video track into a video material. For any image material in the video track, in response to the conversion operation of the image material, the terminal generates a video material based on the content and length of the image material. Then, the terminal replaces the image material in the video track with the video material. Among them, the content of the video material is related to the content of the image material. The length of the video material and the length of the image material conform to a preset proportional relationship. The length of the material is used to indicate the display duration of the material. The preset proportional relationship can be 1:1, 1:2 or 2:3, etc., and the embodiments of the present disclosure do not limit this. That is, the display duration of the video material can be equal to the display duration of the image material, or it can be unequal to the display duration of the image material, and the embodiments of the present disclosure do not limit this.

[0328] The solution provided by the embodiments of the present disclosure can convert the image materials already existing in the video track into video materials with relevant contents and corresponding display duration, increase the dynamic changes of the material content, make the material content more ornamental, and help improve the quality of subsequently generated videos; and the video material can be generated directly based on the image material, without the user having to re-obtain prompt information to generate the video material, the operation is simple, and the efficiency of generating visual materials can be improved.

[0329] For example, Fig.17 FIG. 1 is a schematic diagram showing a method of converting an image to a video according to an exemplary embodiment. Fig.17For image material 1 in video track 1701, in response to the triggering operation on conversion control 1702, the terminal displays video generation panel 1703. Image material 1 is displayed as a prompt image in video generation panel 1703. In response to the triggering operation on generation control 1704, the terminal generates video material based on image material 1. In the process of generating video material, the terminal can minimize the video generation panel and highlight the location of image material 1 in the video track (gray part). Then, after generating video material 3, the terminal directly replaces image material 1 in the video track with video material 3. Fig.17 It can be seen that the width of video material 3 is equal to the width of image material 1, that is, the display durations of the two are equal.

[0330] In some embodiments, the terminal is capable of extending the video material in the video track. Accordingly, in response to the extension operation of any video material in the video track, the terminal displays a video extension panel. Then, based on the extension prompt information in the video extension panel, the terminal displays the incremental video material matching the extension prompt information in the video track. The extension prompt information includes at least one of a prompt text and a prompt image. The extension prompt information is used to indicate at least one of the content and style of the incremental video material to be generated. The incremental video material is located after the video material and is connected to the video material.

[0331] The solution provided by the disclosed embodiment can extend any video material in a video track based on the video material. There is no need to regenerate the complete video material according to the prompt information used for the video material. It is only necessary to generate the extended part (i.e., incremental video material) through the extension indication information, and connect the extended part with the original video material. Compared with regenerating the complete video material, the generated incremental video material has a smaller amount of data and can be generated faster, thereby improving the efficiency of extending the video.

[0332] Among them, the extension operation can be triggered by lengthening the display time of any video material. Accordingly, the process of the terminal displaying the video extension panel includes: in response to the triggering operation of any video material in the video track, the terminal displays the time window of the video material in the video track. The length of the time window represents the display time of the video material. When the length of the time window is equal to the maximum time of the video material and the lengthening operation of the time window is detected, the terminal displays the video extension panel. The video material can be a video material generated based on artificial intelligence technology, or it can be a video material obtained by shooting, etc., which is not limited in the embodiment of the present disclosure. For video materials generated by artificial intelligence technology, the maximum time of the video material is the time of the video material when it is generated and not edited. For video materials obtained by shooting, the maximum time of the video material is the original time of the video material. That is, when any video material is at the maximum time, if the video material continues to be lengthened, the extension operation is triggered.

[0333] Alternatively, for any video material in the video track, in response to the editing operation of the video material, the terminal displays an extension control in the video editing interface, and in response to the triggering operation of the extension control, displays a video extension panel. That is, the extension operation is triggered by triggering the control.

[0334] The solution provided by the embodiment of the present disclosure can extend the time window of the video material, and when the time window continues to be extended when the length of the time window reaches the maximum length, a video extension panel is displayed to extend the video material; or, the video extension panel can be displayed to extend the video material by triggering the extension control in the video editing interface. This not only enriches the extension methods of the video material, but also is simple to operate and can improve the efficiency of extending the video.

[0335] For example, Fig.18 FIG. 1 is a schematic diagram showing a trigger extension operation according to an exemplary embodiment. Fig.18 , video track 1801 displays multiple frames of video material 1. Fig.18 In (a), in response to the selection operation of video material 1 in video track 1801, the terminal displays a time window (dashed line) of video material 1 around video material 1 in video track 1801. In response to dragging the right side of the time window to the right, the time window is stretched, and the display time of video material 1 is extended accordingly, but the content of video material 1 is not increased. When the display time of video material 1 reaches the maximum length, if the right side of the time window is continued to be dragged to the right, the display time of video material 1 will not be extended, but the extension operation of the content of video material 1 will be triggered, thereby displaying the video extension panel. Or, see Fig.18In (b), the video editing interface displays an extension control 1802. When the extension control 1802 is triggered, the extension operation of the video material 1 is triggered, so that the video extension panel is displayed.

[0336] The incremental video material is generated based on the prompt text entered in the video extension panel. For example, Fig.19 FIG. 1 is a schematic diagram of a video extension panel according to an exemplary embodiment. Fig.19 , a text prompt box 1902 is displayed in the video extension panel 1901. In response to the text input operation on the text prompt box 1902, the terminal displays the input prompt text in the text prompt box 1902. Then, in response to the triggering operation on the extension control 1903, the terminal generates incremental video material based on the prompt text. In the process of generating incremental video material, the terminal can minimize the video extension panel and highlight the position to be occupied by the incremental video material in the video track, similar to Fig.14 The display method in will not be described in detail here.

[0337] Alternatively, the incremental video material is generated based on the prompt image input in the video extension panel. The prompt image is the image located at the last frame in the video material 1 (ie, the last frame image). For example, Fig. 20 FIG. 1 is a schematic diagram of another video extension panel according to an exemplary embodiment. Fig. 20 The video extension panel is similar to the video generation panel. A prompt box 2002 is displayed in the video extension panel 2001. The prompt box 2002 displays the last frame image of the video material 1. The user can also enter a prompt text in the prompt box 2002, or not. In response to the triggering operation of the generation control 2003, the terminal generates an incremental video material based on the last frame image of the video material 1. In the process of generating the incremental video material, the terminal can minimize the video extension panel and highlight the position to be occupied by the incremental video material in the video track, similar to Fig.14 The display method in will not be described in detail here.

[0338] The embodiment of the present disclosure does not limit the method for generating the incremental video material. The solution provided by the embodiment of the present disclosure can generate the incremental video material by inputting the prompt text, or can generate the incremental video material according to the last frame image in the video material to be extended, which not only enriches the method for generating the incremental video material, but also generates the incremental video material according to the last frame image in the video material to be extended, ensuring that the incremental video material matches the video material to be extended, which is conducive to improving the quality of the video material.

[0339] In the process of displaying the incremental video material based on the extended prompt information, the terminal can first generate the incremental video material, and then display the incremental video material as a whole after the incremental video material is generated; or, the terminal can also display the generated image at the same time during the process of generating the incremental video material.

[0340] In some embodiments, in the process of generating incremental video material based on the extended prompt information, the terminal highlights the second target area in the video track. The second target area is used to indicate the position that the incremental video material will occupy in the video track. The second target area is located after the area occupied by the video material and is connected to the area occupied by the video material. Then, after generating the incremental video material, the terminal displays the incremental video material in the second target area. The solution provided by the embodiment of the present disclosure can highlight the second target area in the video track during the process of generating incremental video material, and intuitively show the user the position occupied by the incremental video material being generated, which can not only improve the utilization rate of the video editing interface and the efficiency of information transmission, but also help to enhance the user's sense of control over the material generation, that is, improve the user experience.

[0341] For example, Fig.21 FIG. 1 is a schematic diagram showing a method of displaying incremental video material according to an exemplary embodiment. Fig.21 , the terminal highlights the second target area 2102 (gray part) after the video material 1 in the video track 2101. Then, after the incremental video material is generated, the terminal directly displays the incremental video material in the second target area 2102.

[0342] In other embodiments, in the process of generating incremental video material based on the extended prompt information, the terminal displays the generated images in the incremental video material frame by frame after the video material in the video track until the incremental video material is generated. The solution provided by the disclosed embodiment can display the generated images in the incremental video material frame by frame after the video material in the video track during the process of generating incremental video material, and intuitively show the user the generation progress of the incremental video material, which can not only improve the utilization rate of the video editing interface and the efficiency of information transmission, but also help to enhance the user's sense of control over the material generation, that is, improve the user experience.

[0343] For example, Fig. 22 FIG. 1 is a schematic diagram showing another method of displaying incremental video material according to an exemplary embodiment. Fig. 22 In the process of generating the incremental video material, each time an image in the incremental video material is generated, the terminal displays the image in the video track 2201 in sequence. Fig. 22 It can be seen that the first frame image in the incremental video material has been generated and displayed.

[0344] In some embodiments, the terminal is able to perform transition processing on the existing materials in the video track to connect the content between adjacent materials. Accordingly, in response to the transition material generation operation, the terminal determines the fourth material and the fifth material indicated by the transition material generation operation. In the case where the fifth material is located after the fourth material, the terminal generates the transition material based on the last frame image in the fourth material and the first frame image in the fifth material; or, in the case where the fifth material is located before the fourth material, the terminal generates the transition material based on the first frame image in the fourth material and the last frame image in the fifth material. Then, the transition material is displayed between the fourth material and the fifth material. The scheme provided by the embodiment of the present disclosure can generate a transition material between any two adjacent materials in the video track, and display the transition material between the two materials, so that the transition between multiple materials in the subsequently generated video is more natural, which is conducive to improving the quality of the video.

[0345] Among them, in the process of determining the fourth material and the fifth material indicated by the transition material generation operation, the terminal can display a transition generation panel in response to the triggering operation of the transition generation control in the video editing interface. The transition generation panel displays a first generation option and a second generation option. The first generation option is used to indicate the generation of transition material between the fourth material and the previous material of the fourth material. The second generation option is used to indicate the generation of transition material between the fourth material and the next material of the fourth material. The fourth material is the material indicated by the time progress line in the video track. When the first generation option is selected, the terminal determines the previous material of the fourth material as the fifth material. When the second generation option is selected, the terminal determines the next material of the fourth material as the fifth material.

[0346] The solution provided by the embodiment of the present disclosure displays the first generation option and the second generation option in the transition generation panel, so that in the process of generating transition material, the user can choose whether to generate transition material between the previous material or the next material, so that the generation of transition material is more flexible and controllable, and the transition material that meets the user's intention is obtained, thereby reducing the probability of users editing the material, and further helping to improve the efficiency of video generation.

[0347] Wherein, while displaying the transition generation panel, the terminal can display that a certain generation option in the transition generation panel is automatically selected. Accordingly, when the first material distance is greater than the second material distance, in response to the triggering operation of the transition generation control in the video editing interface, the terminal displays the first generation option in the transition generation panel as being in a selected state. When the first material distance is less than the second material distance, in response to the triggering operation of the transition generation control in the video editing interface, the terminal displays the second generation option in the transition generation panel as being in a selected state. Wherein, the first material distance is the distance between the position indicated by the time progress line in the video track and the previous material of the fourth material, and the second material distance is the distance between the position indicated by the time progress line in the video track and the next material of the fourth material.

[0348] The solution provided by the embodiment of the present disclosure automatically selects the generation option according to the position relationship (i.e., distance) between the position indicated by the time progress line in the video track and the material in the video track, without the need for manual selection by the user. The operation is simple and can improve the efficiency of material generation.

[0349] For example, Fig.23 FIG. 1 is a schematic diagram showing a method of generating transition material according to an exemplary embodiment. Fig.23 , a transition generation control 2301 is displayed in the video editing interface. When the transition generation control 2301 is triggered, the terminal displays a transition generation panel for generating transition materials between materials. The transition generation panel displays a first generation option 2302 and a second generation option 2303. The terminal can determine that the fourth material is material 2 based on the position indicated by the time progress line 2104 in the video track. When the first generation option 2302 is selected, the terminal determines the previous material of material 2 as the fifth material. Then, the terminal can generate a transition material between material 1 and material 2.

[0350] Among them, before generating the transition material, the user can also enter the transition prompt text, creative relevance, generation mode (i.e., video quality requirements), video duration and other information in the transition generation panel as prompt information for generating the transition material. Creative relevance is used to indicate the degree of correlation between the generated transition material and the transition prompt file. Then, based on the prompt information in the transition generation panel, the terminal interpolates material 1 and material 2 to obtain the transition material between material 1 and material 2. In the process of generating the transition material, the terminal can minimize the transition synthesis panel and highlight the position to be occupied by the transition material in the video track, similar to Fig.14 The display method in will not be described in detail here.

[0351] In step 305, in response to the video generation operation, the terminal generates a video based on the first material in the video track.

[0352] In an embodiment of the present disclosure, when a video generation operation is triggered, the terminal generates a video based on a first material in a video track. The video includes the first material. The display duration of the first material in the video is equal to the display duration of the first material in the video track.

[0353] The disclosed embodiment provides a video generation method. In the process of generating a video in a video editing scene, a material generation control is displayed in a video editing interface so that by triggering the material generation control, artificial intelligence technology can be used to generate at least one of image material and video material, thereby enriching the material used for video generation. The material is then directly displayed in a video track so that after a subsequent video generation operation is triggered, a video can be directly generated based on the material in the video track. The operation is simple and there is no need to jump to other applications to generate image material or video material. The image / video material generation function is deeply integrated into the video editing scene, and the material generation and video generation can be seamlessly connected, thereby improving the video generation efficiency.

[0354] All the above optional technical solutions can be arbitrarily combined to form optional embodiments of the present disclosure, and will not be described in detail here.

[0355] Fig.24 is a block diagram of a video generation device according to an exemplary embodiment. Fig.24 , the device comprises:

[0356] The display unit 2401 is configured to display a video editing interface, in which a material generation control and a video track are displayed;

[0357] The first generating unit 2402 is configured to generate a first material by using artificial intelligence technology in response to a triggering operation on a material generating control, wherein the first material includes at least one of an image material and a video material;

[0358] The display unit 2401 is further configured to execute in the video track to display the first material;

[0359] The second generating unit 2403 is configured to generate a video based on the first material in the video track in response to the video generating operation.

[0360] In some embodiments, the first generating unit 2402 includes:

[0361] A display subunit, configured to display a material generation panel in response to a triggering operation on the material generation control;

[0362] An acquisition subunit is configured to acquire prompt information, the prompt information including at least one of a prompt text and a prompt image, the prompt information being used to indicate at least one of a content and a style of a material to be generated;

[0363] The display subunit is further configured to display prompt information in the material generation panel;

[0364] The generating subunit is configured to execute, in response to the confirming generating operation, the generating first material matching the prompt information by using artificial intelligence technology.

[0365] In some embodiments, the material generation control includes at least one of an image generation control, a video generation control, and a batch generation control, and the material generation panel includes at least one of an image generation panel, a video generation panel, and a batch generation panel;

[0366] The generating subunit is configured to perform any of the following:

[0367] In response to the confirmation generation operation in the image generation panel, based on the prompt information in the image generation panel, an image material matching the prompt information is generated using artificial intelligence technology;

[0368] In response to the confirmation generation operation in the video generation panel, based on the prompt information in the video generation panel, the artificial intelligence technology is used to generate video materials matching the prompt information;

[0369] In response to the confirmation generation operation in the batch generation panel, based on the multiple prompt information in the batch generation panel, artificial intelligence technology is used to generate image materials or video materials that match the multiple prompt information respectively.

[0370] In some embodiments, other tracks besides the video track are displayed in the video editing interface;

[0371] The acquisition subunit is configured to determine prompt information based on the materials in other tracks when corresponding materials have been added to other tracks.

[0372] In some embodiments, the material generation panel includes at least one of an image generation panel and a video generation panel;

[0373] The acquisition subunit is configured to determine the second material at the position from other tracks based on the position indicated by the time progress line in other tracks when the corresponding material has been added in other tracks; and determine the prompt information based on the second material.

[0374] In some embodiments, the display unit 2401 is configured to display the first material in the video track according to the position of the second material in other tracks.

[0375] In some embodiments, the prompt information includes the second material, the length of the first material is equal to the length of the second material, and the length of the material is used to indicate the display duration of the material.

[0376] In some embodiments, the material generation panel is a batch generation panel;

[0377] The acquisition subunit is configured to determine the prompt information corresponding to each of the plurality of second materials based on the plurality of second materials in the other tracks when the corresponding materials have been added to the other tracks.

[0378] In some embodiments, the generating subunit is configured to execute, in response to the confirming generating operation, based on the prompt information corresponding to each of the plurality of second materials in other tracks, respectively generate the first materials corresponding to each of the prompt information by using artificial intelligence technology;

[0379] The display unit 2401 is configured to display the first material corresponding to each prompt information in the video track according to the order of multiple second materials in other tracks.

[0380] In some embodiments, other tracks besides the video track are displayed in the video editing interface;

[0381] The display unit 2401 is also configured to execute prompt information corresponding to each second material in other tracks in the material generation panel, and display editing controls corresponding to the prompt information; in response to a triggering operation on the editing control, display an editing panel for the prompt information, and the editing panel is used to edit the prompt information.

[0382] In some embodiments, a plurality of other tracks are displayed in addition to the video track in the video editing interface;

[0383] The acquisition subunit is configured to execute, in response to a selection operation on any other track in the video editing interface, and to determine the prompt information corresponding to each second material based on each second material in the other track.

[0384] In some embodiments, the display unit 2401 is further configured to execute, for any prompt information in the material generation panel, in response to a type selection operation for the prompt information, display the material type corresponding to the prompt information in the material generation panel;

[0385] The generating subunit is configured to execute, in response to the confirming generating operation, using artificial intelligence technology to generate a first material that matches the prompt information and conforms to the corresponding material type.

[0386] In some embodiments, the display unit 2401 is configured to execute a material selection control for displaying prompt information in the material generation panel for any prompt information in the material generation panel; display an image type option and a video type option in response to a triggering operation on the material selection control; and when any type option among the image type option and the video type option is selected, display the material type indicated by the selected type option in the material generation panel.

[0387] In some embodiments, the display unit 2401 is configured to execute an operation in response to selecting any multiple prompt information in the material generation panel to display an image type option and a video type option; when any type option among the image type option and the video type option is selected, the material type indicated by the selected type option is displayed in the material generation panel.

[0388] In some embodiments, a template selection control is displayed in the material generation panel;

[0389] The acquisition subunit is configured to display a plurality of text templates in response to a trigger operation on a template selection control; and determine the text template as prompt information in response to an application operation on any text template.

[0390] In some embodiments, an image acquisition control is displayed in the material generation panel;

[0391] The acquisition subunit is configured to display multiple images in response to a trigger operation on the image acquisition control; and determine prompt information based on the at least one image in response to a selection operation on at least one of the multiple images.

[0392] In some embodiments, the acquisition subunit is configured to execute, for any image among multiple images, in response to a selection operation on the image, display the image in a prompt editing interface; in response to a prompt selection operation on the image in the prompt editing interface, determine a prompt area in the image, and determine the image and the area prompt information for indicating the prompt area as prompt information.

[0393] In some embodiments, the display unit 2401 is further configured to execute a prompt text input in response to a text input operation in the material generation panel, and display the input prompt text in the material generation panel;

[0394] The acquisition subunit is configured to perform any of the following:

[0395] In response to a trigger operation on the image acquisition control, based on the prompt text in the material generation panel, multiple images are displayed, and at least one of the content and style of the multiple images conforms to the prompt text;

[0396] In response to a triggering operation on an image acquisition control, multiple images are displayed based on a prompt text in a material generation panel, and at least one image among the multiple images whose content and style at least match the prompt text is highlighted.

[0397] In some embodiments, the material generation panel includes a video generation panel, the prompt information in the video generation panel includes multiple images, and the video generation panel displays a first and last frame mode control;

[0398] The generation subunit is configured to execute, in response to confirming the generation operation, when the first and last frame mode controls are triggered, for two adjacent images in any order among the multiple images in the video generation panel, using an interpolation algorithm to process the two images to obtain a transition image between the two images; and generate a first material based on the multiple images in the video generation panel and the transition images of the multiple images.

[0399] In some embodiments, the display unit 2401 is further configured to execute in the material generation panel to display the first material;

[0400] In response to the selection operation of the first material, when the time progress line is in an idle area in the video track, the first material is displayed after the material added in the video track, and the idle area is an area in the video track where no material exists; or,

[0401] In response to a selection operation on the first material, when the time progress line is in a non-idle area in the video track, the first material is displayed between two materials closest to the time progress line in the video track.

[0402] In some embodiments, the display unit 2401 is further configured to display a minimize control in the material generation panel during the process of generating the first material; minimize the material generation panel in response to a triggering operation on the minimize control; highlight a first target area in the video track, the first target area being used to indicate a position to be occupied by the first material in the video track; and display the first material in the first target area.

[0403] In some embodiments, the first generating unit 2402 is further configured to execute, in response to an update operation on the first material in the video track, regenerate the third material;

[0404] The display unit is further configured to replace the first material in the video track with the third material.

[0405] In some embodiments, the first generating unit 2402 is further configured to generate a video material for any image material in the video track in response to a conversion operation on the image material based on the content and length of the image material, wherein the content of the video material is related to the content of the image material, the length of the video material and the length of the image material meet a preset proportional relationship, and the length of the material is used to indicate the display duration of the material;

[0406] The display unit 2401 is further configured to replace the image material in the video track with the video material.

[0407] In some embodiments, the display unit 2401 is further configured to display a video extension panel in response to an extension operation on any video material in the video track;

[0408] The display unit 2401 is also configured to execute the extension prompt information in the video extension panel, and display the incremental video material matching the extension prompt information in the video track, the extension prompt information includes at least one of a prompt text and a prompt image, and the extension prompt information is used to indicate at least one of the content and style of the incremental video material to be generated, and the incremental video material is located after the video material and connected to the video material.

[0409] In some embodiments, the display unit 2401 is configured to perform any of the following:

[0410] In response to a triggering operation on any video material in a video track, a time window of the video material is displayed in the video track, the length of the time window represents the display duration of the video material, and when the length of the time window is equal to the maximum duration of the video material and a stretching operation on the time window is detected, a video extension panel is displayed;

[0411] For any video material in the video track, in response to an editing operation of the video material, an extension control is displayed in the video editing interface, and in response to a triggering operation on the extension control, a video extension panel is displayed.

[0412] In some embodiments, the incremental video material is at least one of the following:

[0413] The incremental video material is generated based on the prompt text entered in the video extension panel;

[0414] The incremental video material is generated based on the prompt image entered in the video extension panel. The prompt image is the image located at the last frame in the video material.

[0415] In some embodiments, the display unit 2401 is configured to highlight a second target area in the video track during the process of generating incremental video material based on the extended prompt information, the second target area being used to indicate the position to be occupied by the incremental video material in the video track, the second target area being located after the area occupied by the video material and being connected to the area occupied by the video material; after the incremental video material is generated, the incremental video material is displayed in the second target area.

[0416] In some embodiments, the display unit 2401 is configured to execute, in the process of generating the incremental video material based on the extension prompt information, displaying the generated images in the incremental video material frame by frame after the video material in the video track until the incremental video material is generated.

[0417] In some embodiments, the apparatus further comprises:

[0418] a determining unit configured to determine, in response to the transition material generating operation, a fourth material and a fifth material indicated by the transition material generating operation;

[0419] The first generating unit 2402 is further configured to generate a transition material based on the last frame image in the fourth material and the first frame image in the fifth material when the fifth material is located after the fourth material; or generate a transition material based on the first frame image in the fourth material and the last frame image in the fifth material when the fifth material is located before the fourth material;

[0420] The display unit is further configured to display a transition material between the fourth material and the fifth material.

[0421] In some embodiments, the determination unit is configured to execute a trigger operation in response to a transition generation control in a video editing interface, display a transition generation panel, and display a first generation option and a second generation option in the transition generation panel. The first generation option is used to indicate the generation of a transition material between a fourth material and a previous material of the fourth material, and the second generation option is used to indicate the generation of a transition material between the fourth material and a subsequent material of the fourth material, where the fourth material is the material indicated by the time progress line in the video track; when the first generation option is selected, the previous material of the fourth material is determined as the fifth material; when the second generation option is selected, the subsequent material of the fourth material is determined as the fifth material.

[0422] In some embodiments, the determination unit is configured to display the first generation option as being selected in the transition generation panel in response to a triggering operation on a transition generation control in a video editing interface when the first material distance is greater than the second material distance; and to display the second generation option as being selected in the transition generation panel in response to a triggering operation on a transition generation control in a video editing interface when the first material distance is less than the second material distance; wherein the first material distance is the distance between the position indicated by the time progress line in the video track and the previous material of the fourth material, and the second material distance is the distance between the position indicated by the time progress line in the video track and the next material of the fourth material.

[0423] The disclosed embodiment provides a video generation method. In the process of generating a video in a video editing scene, a material generation control is displayed in a video editing interface so that by triggering the material generation control, artificial intelligence technology can be used to generate at least one of image material and video material, thereby enriching the material used for video generation. The material is then directly displayed in a video track so that after a subsequent video generation operation is triggered, a video can be directly generated based on the material in the video track. The operation is simple and there is no need to jump to other applications to generate image material or video material. The image / video material generation function is deeply integrated into the video editing scene, and the material generation and video generation can be seamlessly connected, thereby improving the video generation efficiency.

[0424] It should be noted that the video generation device provided in the above embodiment only uses the division of the above functional units as an example to illustrate when generating a video. In actual applications, the above functions can be assigned to different functional units as needed, that is, the internal structure of the electronic device is divided into different functional units to complete all or part of the functions described above. In addition, the video generation device provided in the above embodiment and the video generation method embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0425] 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.

[0426] When an electronic device is provided as a terminal, Fig.25 FIG. 2 is a block diagram of a terminal 2500 according to an exemplary embodiment. Fig.25FIG2 is a block diagram of a terminal 2500 provided by an exemplary embodiment of the present disclosure. The terminal 2500 may be a smart phone, a tablet computer, an MP3 player (Moving Picture Experts Group Audio Layer III), an MP4 player (Moving Picture Experts Group Audio Layer IV), a laptop computer or a desktop computer. The terminal 2500 may also be referred to as a user device, a portable terminal, a laptop terminal, a desktop terminal or other names.

[0427] Typically, the terminal 2500 includes: a processor 2501 and a memory 2502 .

[0428] The processor 2501 may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 2501 may be implemented in at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). The processor 2501 may also include a main processor and a coprocessor. The main processor is a processor for processing data in the awake state, also known as a CPU (Central Processing Unit); the coprocessor is a low-power processor for processing data in the standby state. In some embodiments, the processor 2501 may be integrated with a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the display screen. In some embodiments, the processor 2501 may also include an AI (Artificial Intelligence) processor, which is used to process computing operations related to machine learning.

[0429] The memory 2502 may include one or more computer-readable storage media, which may be non-transitory. The memory 2502 may also include a high-speed random access memory and a non-volatile memory, such as one or more disk storage devices, flash memory storage devices. In some embodiments, the non-transitory computer-readable storage medium in the memory 2502 is used to store at least one computer program, which is used to be executed by the processor 2501 to implement the video generation method provided in the method embodiment of the present application.

[0430] In some embodiments, the terminal 2500 may also optionally include: a peripheral device interface 2503 and at least one peripheral device. The processor 2501, the memory 2502 and the peripheral device interface 2503 may be connected via a bus or a signal line. Each peripheral device may be connected to the peripheral device interface 2503 via a bus, a signal line or a circuit board. Specifically, the peripheral device includes: at least one of a radio frequency circuit 2504, a display screen 2505, a camera assembly 2506, an audio circuit 2507 and a power supply 2508.

[0431] The peripheral device interface 2503 may be used to connect at least one peripheral device related to I / O (Input / Output) to the processor 2501 and the memory 2502. In some embodiments, the processor 2501, the memory 2502, and the peripheral device interface 2503 are integrated on the same chip or circuit board; in some other embodiments, any one or two of the processor 2501, the memory 2502, and the peripheral device interface 2503 may be implemented on a separate chip or circuit board, which is not limited in this embodiment.

[0432] The radio frequency circuit 2504 is used to receive and transmit RF (Radio Frequency) signals, also known as electromagnetic signals. The radio frequency circuit 2504 communicates with the communication network and other communication devices through electromagnetic signals. The radio frequency circuit 2504 converts the electrical signal into an electromagnetic signal for transmission, or converts the received electromagnetic signal into an electrical signal. In some embodiments, the radio frequency circuit 2504 includes: an antenna system, an RF transceiver, one or more amplifiers, a tuner, an oscillator, a digital signal processor, a codec chipset, a user identity module card, and the like. The radio frequency circuit 2504 can communicate with other terminals through at least one wireless communication protocol. The wireless communication protocol includes, but is not limited to: the World Wide Web, a metropolitan area network, an intranet, various generations of mobile communication networks (2G, 3G, 4G and 5G), a wireless local area network and / or a WiFi (Wireless Fidelity) network. In some embodiments, the radio frequency circuit 2504 may also include circuits related to NFC (Near Field Communication), which is not limited in this application.

[0433] The display screen 2505 is used to display a UI (User Interface). The UI may include graphics, text, icons, videos, and any combination thereof. When the display screen 2505 is a touch display screen, the display screen 2505 also has the ability to collect touch signals on the surface or above the surface of the display screen 2505. The touch signal can be input to the processor 2501 as a control signal for processing. At this time, the display screen 2505 can also be used to provide virtual buttons and / or virtual keyboards, also known as soft buttons and / or soft keyboards. In some embodiments, the display screen 2505 can be one, set on the front panel of the terminal 2500; in other embodiments, the display screen 2505 can be at least two, respectively set on different surfaces of the terminal 2500 or in a folding design; in other embodiments, the display screen 2505 can be a flexible display screen, set on a curved surface or a folding surface of the terminal 2500. Even, the display screen 2505 can also be set to a non-rectangular irregular figure, that is, a special-shaped screen. The display screen 2505 can be made of materials such as LCD (Liquid Crystal Display) and OLED (Organic Light-Emitting Diode).

[0434] The camera assembly 2506 is used to capture images or videos. In some embodiments, the camera assembly 2506 includes a front camera and a rear camera. Typically, the front camera is disposed on the front panel of the terminal, and the rear camera is disposed on the back of the terminal. In some embodiments, there are at least two rear cameras, which are any one of a main camera, a depth of field camera, a wide-angle camera, and a telephoto camera, so as to realize the fusion of the main camera and the depth of field camera to realize the background blur function, the fusion of the main camera and the wide-angle camera to realize panoramic shooting and VR (Virtual Reality) shooting function or other fusion shooting functions. In some embodiments, the camera assembly 2506 may also include a flash. The flash may be a monochrome temperature flash or a dual-color temperature flash. A dual-color temperature flash refers to a combination of a warm light flash and a cold light flash, which can be used for light compensation at different color temperatures.

[0435] The audio circuit 2507 may include a microphone and a speaker. The microphone is used to collect sound waves from the user and the environment, and convert the sound waves into electrical signals and input them into the processor 2501 for processing, or input them into the radio frequency circuit 2504 to achieve voice communication. For the purpose of stereo acquisition or noise reduction, there may be multiple microphones, which are respectively arranged at different parts of the terminal 2500. The microphone may also be an array microphone or an omnidirectional acquisition microphone. The speaker is used to convert the electrical signal from the processor 2501 or the radio frequency circuit 2504 into sound waves. The speaker may be a traditional film speaker or a piezoelectric ceramic speaker. When the speaker is a piezoelectric ceramic speaker, it can not only convert the electrical signal into sound waves audible to humans, but also convert the electrical signal into sound waves inaudible to humans for purposes such as ranging. In some embodiments, the audio circuit 2507 may also include a headphone jack.

[0436] The power supply 2508 is used to power various components in the terminal 2500. The power supply 2508 can be an alternating current, a direct current, a disposable battery, or a rechargeable battery. When the power supply 2508 includes a rechargeable battery, the rechargeable battery can be a wired rechargeable battery or a wireless rechargeable battery. A wired rechargeable battery is a battery charged through a wired line, and a wireless rechargeable battery is a battery charged through a wireless coil. The rechargeable battery can also be used to support fast charging technology.

[0437] Those skilled in the art will understand that Fig.25 The structure shown in the figure does not constitute a limitation on the terminal 2500, and the terminal 2500 may include more or fewer components than those shown in the figure, or combine certain components, or adopt a different component arrangement.

[0438] In an exemplary embodiment, a computer-readable storage medium including instructions is also provided, such as a memory 2502 including instructions, and the instructions can be executed by a processor 2501 of a terminal 2500 to complete the above-mentioned video generation method. Optionally, the computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0439] A computer program product comprises a computer program / instruction, which implements the above-mentioned video generation method when executed by a processor.

[0440] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. The present disclosure 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 description and examples are to be considered exemplary only, and the true scope and spirit of the present disclosure are indicated by the following claims.

[0441] 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. A video generation method, characterized in that: The method comprises: Displaying a video editing interface, wherein the video editing interface displays a material generation control and a video track; In response to a triggering operation on the material generation control, using artificial intelligence technology to generate a first material, the first material including at least one of an image material and a video material; In the video track, display the first material; In response to a video generation operation, a video is generated based on the first material in the video track.

2. The video generation method according to claim 1, characterized in that: The step of generating the first material by using artificial intelligence technology in response to the triggering operation of the material generation control includes: In response to a triggering operation on the material generation control, displaying a material generation panel; Acquire prompt information, where the prompt information includes at least one of a prompt text and a prompt image, and the prompt information is used to indicate at least one of a content and a style of a material to be generated; Displaying the prompt information in the material generation panel; In response to the confirmation generation operation, artificial intelligence technology is used to generate the first material matching the prompt information.

3. The video generation method according to claim 2, characterized in that: The material generation control includes at least one of an image generation control, a video generation control, and a batch generation control, and the material generation panel includes at least one of an image generation panel, a video generation panel, and a batch generation panel; In response to the confirming generation operation, using artificial intelligence technology to generate the first material matching the prompt information includes any of the following: In response to the confirmation generation operation in the image generation panel, based on the prompt information in the image generation panel, an image material matching the prompt information is generated using artificial intelligence technology; In response to the confirmation generation operation in the video generation panel, based on the prompt information in the video generation panel, using artificial intelligence technology to generate video material matching the prompt information; In response to the confirmation generation operation in the batch generation panel, based on the multiple prompt information in the batch generation panel, artificial intelligence technology is used to generate image materials or video materials that match the multiple prompt information respectively.

4. The video generation method according to claim 2, characterized in that: The video editing interface also displays other tracks besides the video track; The obtaining of prompt information includes: In the case that corresponding materials have been added to the other tracks, the prompt information is determined based on the materials in the other tracks.

5. The video generation method according to claim 4, characterized in that: The material generation panel includes at least one of an image generation panel and a video generation panel; In the case where the corresponding material has been added to the other track, determining the prompt information based on the material in the other track includes: In the case where the corresponding material has been added to the other track, based on the position indicated by the time progress line in the other track, determine the second material at the position from the other track; The prompt information is determined based on the second material.

6. The video generation method according to claim 5, characterized in that: The step of displaying the first material in the video track includes: The first material is displayed in the video track according to the position of the second material in the other tracks.

7. The video generation method according to claim 5, characterized in that: The prompt information includes the second material, the length of the first material is equal to the length of the second material, and the length of the material is used to indicate the display duration of the material.

8. The video generation method according to claim 4, characterized in that: The material generation panel includes a batch generation panel; In the case where the corresponding material has been added to the other track, determining the prompt information based on the material in the other track includes: In the case that corresponding materials have been added to the other tracks, the prompt information corresponding to each of the plurality of second materials is determined respectively based on the plurality of second materials in the other tracks.

9. The video generation method according to claim 8, characterized in that: In response to the confirming generation operation, using artificial intelligence technology to generate the first material matching the prompt information includes: In response to the confirmation generation operation, based on the prompt information corresponding to each of the plurality of second materials in the other tracks, the artificial intelligence technology is used to respectively generate the first materials corresponding to each of the prompt information; The step of displaying the first material in the video track includes: In the video track, the first material corresponding to each prompt information is displayed according to the order of the multiple second materials in the other tracks.

10. The video generation method according to claim 2, characterized in that: The video editing interface also displays other tracks besides the video track; The method further comprises: For the prompt information corresponding to each second material in the other tracks in the material generation panel, display an editing control corresponding to the prompt information; In response to a triggering operation on the editing control, an editing panel of the prompt information is displayed, and the editing panel is used to edit the prompt information.

11. The video generation method according to claim 10, characterized in that: In addition to the video track, the video editing interface also displays multiple other tracks; The obtaining of prompt information includes: In response to a selection operation on any other track in the video editing interface, prompt information corresponding to each second material is determined based on each second material in the other track.

12. The video generation method according to claim 2, characterized in that: The method further comprises: For any prompt information in the material generation panel, in response to a type selection operation for the prompt information, displaying the material type corresponding to the prompt information in the material generation panel; In response to the confirming generation operation, using artificial intelligence technology to generate the first material matching the prompt information includes: In response to confirming the generation operation, artificial intelligence technology is used to generate the first material that matches the prompt information and conforms to the corresponding material type.

13. The video generation method according to claim 12, characterized in that: For any prompt information in the material generation panel, in response to a type selection operation for the prompt information, displaying the material type corresponding to the prompt information in the material generation panel includes: For any prompt information in the material generation panel, display a material selection control of the prompt information in the material generation panel; In response to a triggering operation on the material selection control, displaying an image type option and a video type option; When any one of the image type option and the video type option is selected, the material type indicated by the selected type option is displayed in the material generation panel.

14. The video generation method according to claim 12, characterized in that: For any prompt information in the material generation panel, in response to a type selection operation for the prompt information, displaying the material type corresponding to the prompt information in the material generation panel includes: In response to a selection operation of any plurality of prompt information in the material generation panel, displaying an image type option and a video type option; When any one of the image type option and the video type option is selected, the material type indicated by the selected type option is displayed in the material generation panel.

15. The video generation method according to claim 2, characterized in that: A template selection control is displayed in the material generation panel; The obtaining of prompt information includes: In response to a triggering operation on the template selection control, displaying a plurality of text templates; In response to an application operation on any text template, the text template is determined as the prompt information.

16. The video generation method according to claim 2, characterized in that: An image acquisition control is displayed in the material generation panel; The obtaining of prompt information includes: In response to a triggering operation on the image acquisition control, displaying a plurality of images; In response to a selection operation on at least one image among the multiple images, the prompt information is determined based on the at least one image.

17. The video generation method according to claim 16, characterized in that: The step of determining the prompt information based on the at least one image in response to the selection operation of at least one image among the multiple images includes: For any image among the plurality of images, in response to a selection operation on the image, displaying the image in a prompt editing interface; In response to a prompt selection operation on the image in the prompt editing interface, a prompt area in the image is determined, and the image and area prompt information for indicating the prompt area are determined as the prompt information.

18. The video generation method according to claim 16, characterized in that: The method further comprises: In response to a text input operation in the material generation panel, displaying the input prompt text in the material generation panel; The displaying of multiple images in response to the triggering operation on the image acquisition control includes any of the following: In response to a triggering operation on the image acquisition control, based on the prompt text in the material generation panel, the multiple images are displayed, and at least one of the content and style of the multiple images conforms to the prompt text; In response to a triggering operation on the image acquisition control, the multiple images are displayed based on the prompt text in the material generation panel, and at least one image among the multiple images whose content and style at least match the prompt text is highlighted.

19. The video generation method according to claim 2, characterized in that: The material generation panel includes a video generation panel, the prompt information in the video generation panel includes multiple images, and the video generation panel displays a first and last frame mode control; In response to the confirming generation operation, using artificial intelligence technology to generate the first material matching the prompt information includes: In the case where the first and last frame mode control is triggered, in response to the confirmation generation operation, for any order of two adjacent images in the plurality of images in the video generation panel, an interpolation algorithm is used to process the two images to obtain a transition image between the two images; The first material is generated based on the multiple images in the video generation panel and transition images of the multiple images.

20. The video generation method according to claim 2, characterized in that: The method further comprises: In the material generation panel, displaying the first material; The step of displaying the first material in the video track includes: In response to a selection operation on the first material, when the time progress line is in an idle area in the video track, the first material is displayed after the material added to the video track, and the idle area is an area in the video track where no material exists; or In response to a selection operation on the first material, when the time progress line is in a non-idle area in the video track, the first material is displayed between two materials closest to the time progress line in the video track.

21. The video generation method according to claim 2, characterized in that: The method further comprises: During the process of generating the first material, displaying a minimized control in the material generation panel; In response to a triggering operation on the minimization control, minimizing the material generation panel; Highlighting a first target area in the video track, where the first target area is used to indicate a position to be occupied by the first material in the video track; The step of displaying the first material in the video track includes: The first material is displayed in the first target area.

22. The video generation method according to claim 1, characterized in that: The method further comprises: In response to an update operation on the first material in the video track, regenerate a third material; The first material in the video track is replaced by the third material.

23. The video generation method according to claim 1, characterized in that: The method further comprises: For any image material in the video track, in response to a conversion operation on the image material, a video material is generated based on the content and length of the image material, wherein the content of the video material is related to the content of the image material, the length of the video material is in a preset proportional relationship with the length of the image material, and the length of the material is used to indicate the display duration of the material; The image material in the video track is replaced by the video material.

24. The video generation method according to claim 1, characterized in that: The method further comprises: In response to an extension operation on any video material in the video track, displaying a video extension panel; Based on the extension prompt information in the video extension panel, the incremental video material matching the extension prompt information is displayed in the video track, the extension prompt information includes at least one of a prompt text and a prompt image, the extension prompt information is used to indicate at least one of the content and style of the incremental video material to be generated, and the incremental video material is located after the video material and connected to the video material.

25. The video generation method according to claim 24, characterized in that: In response to the extension operation of any video material in the video track, displaying the video extension panel includes any of the following: In response to a triggering operation on any video material in the video track, a time window of the video material is displayed in the video track, the length of the time window represents the display duration of the video material, and when the length of the time window is equal to the maximum duration of the video material and a lengthening operation on the time window is detected, the video extension panel is displayed; For any video material in the video track, in response to an editing operation of the video material, an extension control is displayed in the video editing interface, and in response to a triggering operation of the extension control, the video extension panel is displayed.

26. The video generation method according to claim 24, characterized in that: The incremental video material is at least one of the following: The incremental video material is generated based on the prompt text input in the video extension panel; The incremental video material is generated based on a prompt image input into the video extension panel, and the prompt image is an image located at the last frame of the video material.

27. The video generation method according to claim 24, characterized in that: The step of displaying, in the video track, the incremental video material matching the extension prompt information based on the extension prompt information in the video extension panel includes: In the process of generating the incremental video material based on the extension prompt information, a second target area is highlighted in the video track, the second target area is used to indicate the position to be occupied by the incremental video material in the video track, and the second target area is located after the area occupied by the video material and connected to the area occupied by the video material; After the incremental video material is generated, the incremental video material is displayed in the second target area.

28. The video generation method according to claim 24, characterized in that: The step of displaying, in the video track, the incremental video material matching the extension prompt information based on the extension prompt information in the video extension panel includes: In the process of generating the incremental video material based on the extension prompt information, after the video material in the video track, the generated images in the incremental video material are displayed frame by frame until the incremental video material is completely generated.

29. The video generation method according to claim 1, characterized in that: The method further comprises: In response to a transition material generation operation, determining a fourth material and a fifth material indicated by the transition material generation operation; In the case where the fifth material is located after the fourth material, a transition material is generated based on the last frame image in the fourth material and the first frame image in the fifth material; or, in the case where the fifth material is located before the fourth material, the transition material is generated based on the first frame image in the fourth material and the last frame image in the fifth material; The transition material is displayed between the fourth material and the fifth material.

30. The video generation method according to claim 29, characterized in that: The step of determining, in response to a transition material generation operation, a fourth material and a fifth material indicated by the transition material generation operation comprises: In response to a triggering operation on a transition generation control in the video editing interface, a transition generation panel is displayed, wherein a first generation option and a second generation option are displayed in the transition generation panel, wherein the first generation option is used to indicate generation of a transition material between the fourth material and a material preceding the fourth material, and the second generation option is used to indicate generation of a transition material between the fourth material and a material following the fourth material, wherein the fourth material is the material indicated by the time progress line in the video track; In the case where the first generation option is selected, determining a material preceding the fourth material as the fifth material; In a case where the second generation option is selected, a material subsequent to the fourth material is determined as the fifth material.

31. The video generation method according to claim 30, characterized in that: The step of displaying a transition generation panel in response to a triggering operation on a transition generation control in the video editing interface includes: In a case where the first material distance is greater than the second material distance, in response to a triggering operation on the transition generation control in the video editing interface, displaying the first generation option in the transition generation panel as being in a selected state; In a case where the first material distance is smaller than the second material distance, in response to a triggering operation on the transition generation control in the video editing interface, displaying the second generation option in the transition generation panel as being in a selected state; Among them, the first material distance is the distance between the position indicated by the time progress line in the video track and the previous material of the fourth material, and the second material distance is the distance between the position indicated by the time progress line in the video track and the next material of the fourth material.

32. A video generating device, characterized in that: The device comprises: A display unit is configured to display a video editing interface, wherein the video editing interface displays a material generation control and a video track; A first generating unit is configured to generate a first material by using artificial intelligence technology in response to a triggering operation on the material generating control, wherein the first material includes at least one of an image material and a video material; The display unit is further configured to execute in the video track to display the first material; The second generating unit is configured to generate a video based on the first material in the video track in response to a video generating operation.

33. An electronic device, characterized in that: The electronic device comprises: one or more processors; a memory for storing program code executable by the processor; The processor is configured to execute the program code to implement the video generating method as described in any one of claims 1 to 31.

34. 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 video generating method as described in any one of claims 1 to 31.

35. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the video generating method according to any one of claims 1 to 31 is implemented.

Images