Video generation method and apparatus, device, and medium

Abstract

Embodiments of the present disclosure relate to the technical field of artificial intelligence, and relate to a video generation method and apparatus, a device, and a medium. The method comprises: in response to an inputted video style and inputted filming summary information, displaying a filming editing interface, wherein the filming editing interface comprises: at least one filming scene and filming material information corresponding to the filming scene, wherein the filming material information matches the video style and the filming summary information and is used for indicating multimedia information required for the filming scene during filming; acquiring filming setting information corresponding to the at least one filming scene; and in response to a filming triggering operation on the filming editing interface, performing filming on the basis of the filming setting information and the filming material information corresponding to the at least one filming scene, to generate a target video.

Description

Video generation method, device, equipment and medium

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to the Chinese patent application filed on September 28, 2023, with application number 202311279283.3 and invention name “A video generation method, device, equipment and medium”. The entire contents of that application are incorporated by reference into this application. Technical Field

[0003] The present disclosure relates to the field of artificial intelligence technology, and in particular to a video generation method, apparatus, device, and medium. Background Art

[0004] At present, short videos are widely used in all walks of life. For example, users shoot short video stories related to an item in order to promote the item.

[0005] However, in the process of shooting short videos, users need to set the shooting material information corresponding to each shooting scene, such as shooting background, character dialogue, character props, etc. The operation is cumbersome, and the manually set shooting material information may not be comprehensive enough, resulting in low efficiency of short video shooting and the shooting video effect fails to meet the needs.

[0006] Summary of the Invention

[0007] In order to solve the above technical problems or at least partially solve the above technical problems, the present disclosure provides a video generation method, apparatus, device and medium.

[0008] The present disclosure provides a video generation method, the method comprising:

[0009] In response to the input video style and shooting summary information, displaying a shooting editing interface, wherein the shooting editing interface includes: at least one shooting scene, and shooting material information corresponding to the shooting scene, wherein the shooting material information matches the video style and the shooting summary information and is used to indicate multimedia information required for the shooting scene during shooting;

[0010] Acquiring shooting setting information corresponding to the at least one shooting scene;

[0011] In response to a shooting trigger operation on the shooting editing interface, shooting is performed based on the shooting setting information and the shooting material information corresponding to the at least one shooting scene to generate a target video.

[0012] In an optional embodiment, the method further includes:

[0013] Acquire at least one shooting scene based on the scene processing instruction and the video style feedback, and shooting material information corresponding to the shooting scene;

[0014] The scene processing instruction is generated based on the shooting summary information and preset shooting scene elements.

[0015] In an optional implementation manner, the shooting material information includes: environment description information and character dialogue information, wherein:

[0016] The environment description information and the character dialogue information are extracted from the original text information by parsing the scene processing instructions based on a first model that matches the video style.

[0017] In an optional implementation manner, the shooting material information further includes: shooting background, wherein:

[0018] The shooting background is generated by processing the environment description information based on a second model that matches the video style, wherein the shooting background includes: an image background or a video background.

[0019] In an optional implementation manner, the shooting material information further includes: character props, wherein:

[0020] The character props are generated by processing the character description information extracted from the original text information based on a second model that matches the video style.

[0021] In an optional implementation manner, the shooting material information corresponding to the shooting scene displayed on the shooting editing interface includes:

[0022] In response to a selection operation of a target shooting scene from the at least one shooting scene, displaying target environment description information and target character dialogue information corresponding to the target shooting scene in a first area of ​​the shooting editing interface, wherein a shooting duration of the target shooting scene is determined based on a length of the target character dialogue information; and

[0023] A target shooting background corresponding to the target scene is displayed in a second area of ​​the shooting editing interface, wherein the target shooting background matches the environment description information.

[0024] In an optional embodiment, the method further includes:

[0025] In response to a modification and update operation on the target environment description information, updating and displaying a target shooting background matching the modified target environment description information in the second area;

[0026] and / or,

[0027] In response to the modification and update operation on the target character dialogue information, the shooting duration of the target shooting scene is updated based on the length of the modified target character dialogue information.

[0028] In an optional embodiment, the character indication area is displayed on the target shooting background, further comprising:

[0029] In response to a triggering operation on a character setting control in the shooting editing interface, acquiring character feature information corresponding to the character indication area;

[0030] A target character is determined according to the character feature information, and the target character is associated with the character indication area and displayed during shooting.

[0031] In an optional embodiment, the method further includes:

[0032] In response to a scene adding operation, adding a new shooting scene and shooting material information corresponding to the new shooting scene to the shooting editing interface; and / or,

[0033] In response to a deletion operation on a target shooting scene in the at least one shooting scene, the target shooting scene and target shooting material information corresponding to the target shooting scene are deleted in the shooting editing interface.

[0034] In an optional implementation, the shooting setting information includes: a continuous mode and an interval mode, and the shooting based on the shooting setting information corresponding to the at least one shooting scene and the shooting material information includes:

[0035] In response to setting the continuous mode for multiple shooting scenes, automatically switching to the next shooting scene after the shooting time of the current shooting scene is reached based on the shooting material information of the current shooting scene, and continuing shooting based on the shooting material information of the next shooting scene;

[0036] or,

[0037] In response to setting the interval mode for multiple shooting scenes, shooting is stopped after the shooting time of the current shooting scene is reached based on the shooting material information of the current shooting scene, and the next shooting scene is jumped to based on the switching instruction of the next shooting scene, and shooting is continued based on the shooting material information of the next shooting scene.

[0038] In an optional embodiment, the shooting setting information includes: a character prop mode, and the shooting based on the shooting setting information corresponding to the at least one shooting scene and the shooting material information includes:

[0039] In response to setting the target character to a partial prop mode, rendering the partial props and the target character during shooting; or

[0040] In response to setting the target character to the all-props mode, the target character is subjected to matting technology during filming, and the matting result and all the props are rendered; or

[0041] In response to setting the target character to the virtual prop mode, the virtual prop is controlled and processed according to the skeletal motion information of the reference character during shooting.

[0042] In an optional implementation, the shooting setting information includes: a person mode and an empty shot mode, and the shooting based on the shooting setting information corresponding to the at least one shooting scene and the shooting material information includes:

[0043] In response to setting the target shooting scene to the person mode, the background picture or background video corresponding to the target shooting scene is set as the background during shooting, and the person in the camera is placed in the foreground; or

[0044] In response to setting the target shooting scene to the empty shot mode, the background picture or background video corresponding to the target shooting scene is set as the foreground during shooting, and the person in the camera is hidden in the shooting scene.

[0045] The present disclosure also provides a video generation device, comprising:

[0046] A display module is configured to display a shooting editing interface in response to the input video style and shooting summary information, wherein the shooting editing interface includes: at least one shooting scene, and shooting material information corresponding to the shooting scene, wherein the shooting material information matches the video style and the shooting summary information and is used to indicate multimedia information required for the shooting scene during shooting;

[0047] A first acquisition module, configured to acquire shooting setting information corresponding to the at least one shooting scene;

[0048] A generating module is used to respond to a shooting trigger operation on the shooting editing interface, shoot based on the shooting setting information corresponding to the at least one shooting scene and the shooting material information, and generate a target video.

[0049] An embodiment of the present disclosure also provides an electronic device, comprising: a processor; a memory for storing instructions executable by the processor; the processor for reading the executable instructions from the memory and executing the instructions to implement the video generation method provided in the embodiment of the present disclosure.

[0050] The embodiments of the present disclosure further provide a computer-readable storage medium, wherein the storage medium stores a computer program, and the computer program is used to execute the video generation method provided by the embodiments of the present disclosure.

[0051] The technical solution provided by the embodiments of the present disclosure has the following advantages over the prior art: the video generation solution provided by the embodiments of the present disclosure displays a shooting editing interface in response to input video style and shooting summary information, wherein the shooting editing interface includes: at least one shooting scene, and shooting material information corresponding to the shooting scene, wherein the shooting material information matches the video style and shooting summary information, and is used to indicate the multimedia information required for the shooting scene during shooting; obtains shooting setting information corresponding to at least one shooting scene; and in response to a shooting trigger operation on the shooting editing interface, shoots based on the shooting setting information and shooting material information corresponding to at least one shooting scene to generate a target video. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] The above and other features, advantages, and aspects of the various embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and that the originals and elements are not necessarily drawn to scale.

[0053] FIG1 is a flow chart of a video generation method provided by an embodiment of the present disclosure;

[0054] FIG2 is a flow chart of another video generation method provided by an embodiment of the present disclosure;

[0055] FIG3a is a schematic diagram of a video style provided by an embodiment of the present disclosure;

[0056] FIG3 b is a schematic diagram of a shooting summary information input page provided by an embodiment of the present disclosure;

[0057] FIG4a is a schematic diagram of a shooting and editing interface provided by an embodiment of the present disclosure;

[0058] FIG4 b is a schematic diagram of another shooting and editing interface provided by an embodiment of the present disclosure;

[0059] FIG4c is a schematic diagram of another shooting and editing interface provided by an embodiment of the present disclosure;

[0060] FIG5a is a schematic diagram of a video shooting interface provided by an embodiment of the present disclosure;

[0061] FIG5 b is a schematic diagram of another shooting interface provided by an embodiment of the present disclosure;

[0062] FIG6a is a schematic diagram of another shooting editing interface provided by an embodiment of the present disclosure;

[0063] FIG6 b is a schematic diagram of another video shooting interface provided by an embodiment of the present disclosure;

[0064] FIG7 is a schematic structural diagram of a video generating device provided by an embodiment of the present disclosure;

[0065] FIG8 is a schematic structural diagram of an electronic device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0066] The following describes embodiments of the present disclosure in more detail with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as limited to the embodiments described herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are for illustrative purposes only and are not intended to limit the scope of protection of the present disclosure.

[0067] It should be understood that the various steps described in the method embodiments of the present disclosure may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect.

[0068] As used herein, the term "including" and its variations are open-ended, i.e., "including but not limited to." The term "based on" means "based, at least in part, on." The term "one embodiment" means "at least one embodiment," the term "another embodiment" means "at least one additional embodiment," and the term "some embodiments" means "at least some embodiments." Other terms are defined in the following description.

[0069] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0070] It should be noted that the modifications of "one" and "multiple" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, they should be understood as "one or more".

[0071] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0072] FIG1 is a flow chart of a video generation method provided by an embodiment of the present disclosure. The method can be executed by a video generation device, wherein the device can be implemented using software and / or hardware and can generally be integrated into an electronic device. As shown in FIG1 , the method includes:

[0073] Step 101: Display a shooting editing interface in response to input video style and shooting summary information, wherein the shooting editing interface includes: at least one shooting scene, and shooting material information corresponding to the shooting scene, wherein the shooting material information matches the video style and shooting summary information and is used to indicate the multimedia information required for the shooting scene during shooting.

[0074] Among them, the video style can determine the picture style of the generated video. For example, if the video style is magic style, the picture style of the generated video is a magic-type video picture; among them, the video style can be a pre-trained video style model provided to the user for selection, such as a video style model trained by related subjects, or a video style model generated by training data provided by a specific user (such as a user with thematic features).

[0075] The disclosed embodiments do not limit the method for inputting video styles. For example, a plurality of different video styles, such as magic style, pastoral style, etc., are displayed on a display interface, and a user's selection of any one of the video styles is received and determined as the input video style; for another example, a video style input control is displayed on a display interface, and a user triggers the video style input control, imports a file of the relevant video style, and determines the input video style.

[0076] In the embodiment of the present disclosure, shooting summary information can be input according to the actual shooting scene requirements. The embodiment of the present disclosure does not limit the input method of the shooting summary information. For example, an input box is displayed on the display interface, and an example "Generate a story about Little A riding a pig to fly" is displayed below the input box, so that the user can enter shooting summary information such as "Fighting the elves and the magician in the castle ruins" in the input box; for example, the user inputs the shooting summary information "Generate a story about Little B making trouble in heaven" through voice.

[0077] In an embodiment of the present disclosure, a shooting editing interface is displayed, including at least one shooting scene and shooting material information corresponding to the shooting scene, wherein the shooting material information is used to indicate the multimedia information required for the shooting scene during shooting, such as one or more of environment description information, character dialogue information, shooting background (image background or video background), character props, etc.

[0078] In an embodiment of the present disclosure, the shooting material information is matched with the video style and the shooting summary information. That is, the video style and the shooting summary information can be sent to the server, and the server determines at least one shooting scene and the shooting material information corresponding to each shooting scene based on the video style and the shooting summary information; the video style and the shooting summary information can also be sent to the server, and the server generates a scene processing instruction based on the shooting summary information and preset shooting scene elements, and then determines at least one shooting scene and the shooting material information corresponding to each shooting scene based on the video style and the scene processing instruction.

[0079] In an embodiment of the present disclosure, a shooting editing interface is displayed in response to input video style and shooting summary information, including: receiving the video style based on a user's selection operation on a preset video style list on the display page, and receiving shooting summary information based on text information input by the user into a text input box on the display page, obtaining one or more shooting scenes matching the video style and shooting summary information, and shooting material information corresponding to each shooting scene and displaying them on the shooting editing interface.

[0080] In the embodiments of the present disclosure, there are many ways to display the shooting material information corresponding to the shooting scene on the shooting editing interface. In some embodiments, in response to the selection operation of the target shooting scene in at least one shooting scene, the target environment description information and target character dialogue information corresponding to the target shooting scene are displayed in the first area of ​​the shooting editing interface, and the target shooting background corresponding to the target scene is displayed in the second area of ​​the shooting editing interface. In other embodiments, in response to the selection operation of the target shooting scene in at least one shooting scene, the target shooting background and character props corresponding to the target scene are displayed in the shooting editing interface, and the target environment description information corresponding to the target shooting scene is voice broadcast. The above methods are only examples of the shooting material information corresponding to the shooting scene displayed on the shooting editing interface. The present disclosure does not specifically limit the methods of displaying the shooting material information corresponding to the shooting scene on the shooting editing interface.

[0081] Step 102: Acquire shooting setting information corresponding to at least one shooting scene.

[0082] The shooting setting information includes one or more of continuous mode, interval mode, role prop mode, character mode and empty shot mode, and one shooting scene may correspond to one or more of the shooting setting information.

[0083] In the embodiment of the present disclosure, there are many ways to obtain shooting setting information corresponding to at least one shooting scene, such as obtaining multiple shooting scenes set to continuous mode and setting the target character to partial prop mode; for example, obtaining multiple shooting scenes set to interval mode, setting the target character to virtual prop mode and setting the target shooting scene to empty shot mode; the specific settings are selected according to the actual application scenario.

[0084] Step 103 : In response to a shooting trigger operation on the shooting editing interface, shooting is performed based on shooting setting information and shooting material information corresponding to at least one shooting scene to generate a target video.

[0085] In the disclosed embodiment, there are many ways to perform shooting based on the shooting setting information and shooting material information corresponding to at least one shooting scene. In a first embodiment, in response to setting multiple shooting scenes to a continuous mode, after the shooting time of the current shooting scene is reached based on the shooting material information of the current shooting scene, the shooting is automatically switched to the next shooting scene, and the shooting is continued based on the shooting material information of the next shooting scene; in a second embodiment, in response to setting multiple shooting scenes to an interval mode, after the shooting time of the current shooting scene is reached based on the shooting material information of the current shooting scene, the shooting is stopped, and the switching instruction of the next shooting scene is used to jump to the next shooting scene, and the shooting is continued based on the shooting material information of the next shooting scene.

[0086] In a third embodiment, in response to setting the target character to partial prop mode, partial props and the target character are rendered during shooting; in a fourth embodiment, in response to setting the target character to full prop mode, the target character is subjected to matting technology during shooting, and the matting result and all props are rendered. In a fifth embodiment, in response to setting the target character to virtual prop mode, the virtual props are controlled and processed according to the skeletal motion information of the reference character during shooting.

[0087] In a sixth embodiment, in response to setting the target shooting scene to a person mode, the background picture or background video corresponding to the target shooting scene is set as the background during shooting, and the person in the camera is placed in the foreground; in a seventh embodiment, in response to setting the target shooting scene to an empty shot mode, the background picture or background video corresponding to the target shooting scene is set as the foreground during shooting, and the person in the camera is hidden in the shooting scene.

[0088] The above is merely an example of a method of shooting based on shooting setting information and shooting material information corresponding to at least one shooting scene. The embodiments of the present disclosure do not specifically limit the method of shooting based on shooting setting information and shooting material information corresponding to at least one shooting scene.

[0089] The video generation solution provided by the embodiment of the present disclosure displays a shooting editing interface in response to the input video style and shooting summary information, wherein the shooting editing interface includes: at least one shooting scene, and shooting material information corresponding to the shooting scene, wherein the shooting material information matches the video style and shooting summary information and is used to indicate the multimedia information required for the shooting scene when shooting; obtaining shooting setting information corresponding to at least one shooting scene; and in response to a shooting trigger operation on the shooting editing interface, shooting is performed based on the shooting setting information and shooting material information corresponding to at least one shooting scene to generate a target video. With the above technical solution, the user only needs to input the shooting summary information and select the video style to obtain the multimedia information required for shooting, thereby improving the effect and efficiency of obtaining the shooting material information. Moreover, based on the user's triggering, the target video can be generated by shooting according to the shooting setting information and shooting material information corresponding to the shooting scene, further improving the video shooting effect under the video scene and meeting the user's usage needs.

[0090] In some embodiments, the video generation method may further include: obtaining at least one shooting scene based on scene processing instructions and video style feedback, and shooting material information corresponding to the shooting scene; wherein the scene processing instructions are generated based on shooting summary information and preset shooting scene elements.

[0091] In the embodiments of the present disclosure, in some implementations, the shooting summary information is analyzed, such as whether the shooting summary information includes the number of scenes, environmental description information, etc. The shooting summary information includes all required shooting scene elements and can be directly processed according to the video style and shooting summary information by the first model with the text generation function to obtain at least one shooting scene and the shooting material information corresponding to the shooting scene and feedback to the terminal device.

[0092] In other embodiments, the video style and shooting summary information can be sent to a server. The server can analyze the shooting summary information and supplement it based on preset shooting scene elements, such as the number of scenes, environmental description information, character dialogue information, etc., to obtain a scene processing instruction. Then, the first model processes the scene processing instruction and the video style to obtain at least one shooting scene and the shooting material information corresponding to the shooting scene, and feeds it back to the terminal device. In other words, the first model generates a text including environmental description information, character dialogue information, etc. based on the scene processing instruction. Among them, the shooting scene elements can be selected and set according to the actual application shooting needs, such as the specific number of scenes, the number of characters, etc., to further meet the needs of multiple scenarios and enhance the user experience.

[0093] It is understandable that there are many kinds of shooting material information corresponding to the shooting scenes, such as environment description information, character dialogue information, shooting background, character props, etc. Different shooting material information generation methods can be selected and set according to the application scenario.

[0094] In some embodiments, the shooting material information includes: environment description information and character dialogue information, wherein the environment description information and character dialogue information are based on a first model that matches the video style, and the scene processing instructions are parsed to obtain original text information and extracted from the original text information.

[0095] Specifically, a first model matching the video style is obtained, and then the scene processing instructions are parsed and processed by the first model to obtain original text information, and then the environment description information and character dialogue information are extracted from the original text information.

[0096] For example, the input video style is a family leisure style. The scene processing instructions are parsed by the first model, and the obtained environment description information is "at home, the sun is shining, and the kitten is lying on the sofa", and the character dialogue information is "Protagonist: Baby, come and give you something delicious", "Kitten: (a soft meow)".

[0097] In other implementations, the shooting material information further includes: a shooting background, which is generated by processing the environment description information based on a second model that matches the video style, wherein the shooting background includes: an image background or a video background.

[0098] Specifically, after generating environmental description information based on the first model, a second model matching the video style is obtained to process the environmental description information and generate an image background or video background as the shooting background. The second model can generate an image or video based on a command, or generate an image or video with a similar style based on an image or video. Image size information can also be pre-set, so that the shooting background generated by the second model based on the environmental description information and the preset image size can further meet user needs.

[0099] In some further implementations, the shooting material information further includes: character props, where the character props are generated by processing character description information extracted from the original text information based on a second model that matches the video style.

[0100] Specifically, the original text information generated by the first model includes character description information. A second model that matches the video style is obtained to process the character description information to generate character props, such as jewelry props, virtual props, partial props, and full-body props, further improving the generated video quality.

[0101] It should be noted that the original text information generated by parsing the first model can be divided into multiple shooting scenes, and each shooting scene is parsed to obtain shooting material information such as environment description information, character description information, character dialogue information, etc. If the shooting material information of a certain shooting scene is not available, it is supplemented by the first model.

[0102] It should be noted that character props do not need to be generated based on AI models. Instead, they can be tied to the video style and directly made into a specific prop package for calling. When users select a character, they will select the corresponding character props, further improving the efficiency and effectiveness of video generation.

[0103] In the above scheme, scene processing instructions are generated through shooting summary information and preset shooting scene elements, so that shooting scenes are generated according to the scene processing instructions and video style, and shooting material information such as environment description information, character dialogue information, shooting background and character props corresponding to the shooting scene are displayed on the shooting editing interface, further improving the diversity of shooting material information and thus enhancing the user experience.

[0104] In some embodiments, the video generation method may further include: in response to a scene adding operation, adding a new shooting scene and shooting material information corresponding to the new shooting scene in the shooting editing interface; and / or, in response to a deletion operation of a target shooting scene in at least one shooting scene, deleting the target shooting scene and the target shooting material information corresponding to the target shooting scene in the shooting editing interface.

[0105] Specifically, users can edit (such as delete, modify, etc.) existing shooting scenes and the shooting material information corresponding to the shooting scenes, such as environment description information, character dialogue information, etc., and can also add new shooting scenes and the shooting material information corresponding to the new shooting scenes.

[0106] In the above scheme, users can edit existing shooting scenes by themselves, such as deleting one or more existing shooting scenes, and editing or regenerating the shooting material information such as the environment description information, character dialogue information, etc. corresponding to one or more existing shooting scenes through the first model, and the second model can process the regenerated environment description information to generate new image backgrounds, video backgrounds and other shooting backgrounds. In addition, new shooting scenes and shooting material information corresponding to the new shooting scenes can be added to further meet the user's personalized needs, enhance the user's shooting experience, and the video generation effect.

[0107] FIG2 is a flow chart of another video generation method provided by an embodiment of the present disclosure. This embodiment further optimizes the above-mentioned video generation method based on the above-mentioned embodiment. As shown in FIG2 , the method includes:

[0108] Step 201: Receive video style and shooting summary information.

[0109] For example, Figure 3a is a schematic diagram of a video style provided in an embodiment of the present disclosure, which shows a schematic diagram of a video style selection page. The video style selection page includes video style 1 and video style 2. The video style 1 and video style 2 are set in the form of pictures. When the user triggers the video style 1 and video style 2, the terminal device can receive the trigger operation of the input video style and perform subsequent operations such as displaying a display page for inputting shooting summary information.

[0110] For example, Figure 3b is a schematic diagram of a shooting summary information input page provided by an embodiment of the present disclosure. The figure shows a schematic diagram of a shooting summary information input page, including an input text box and example information, such as "Please refer to Xiaohong and Xiaohui to generate a story about havoc in heaven" and "This is an example." The user can enter shooting summary information as needed, such as "Generate a story about Xiao A riding a pig to fly." The figure also includes a "Generate Script" control as the shooting summary information.

[0111] Step 202: Obtain at least one shooting scene based on the scene processing instruction and the video style feedback, as well as shooting material information corresponding to the shooting scene; wherein the scene processing instruction is generated based on the shooting summary information and preset shooting scene elements.

[0112] Specifically, the video style and shooting summary information can be sent to the server. The server generates a scene processing instruction based on the shooting summary information and preset shooting scene elements, and then determines at least one shooting scene and the shooting material information corresponding to each shooting scene based on the video style and the scene processing instruction.

[0113] Specifically, a first model matching the video style is obtained, and then the scene processing instructions are parsed by the first model to obtain original text information, and then the environment description information and character dialogue information are extracted from the original text information; after the environment description information is generated according to the first model, a second model matching the video style is obtained to process the environment description information to generate an image background or a video background as a shooting background; a second model matching the video style is obtained to process the character description information to generate character props.

[0114] It should be noted that if the original text information generated by the first model does not meet the requirements for obtaining environmental description information, character dialogue information, and subsequent character props, etc., it can be processed multiple times so that the obtained original text information can subsequently obtain environmental description information, character dialogue information, and subsequent character props, etc., to ensure the subsequent generation of video effects and further meet the user's shooting needs.

[0115] Step 203: In response to a selection operation of a target shooting scene in at least one shooting scene, target environment description information and target character dialogue information corresponding to the target shooting scene are displayed in a first area of ​​the shooting editing interface, wherein the shooting duration of the target shooting scene is determined based on the length of the target character dialogue information.

[0116] Step 204: Display a target shooting background corresponding to the target scene in a second area of ​​the shooting editing interface, wherein the target shooting background matches the environment description information.

[0117] For example, Figure 4a is a schematic diagram of a shooting and editing interface provided by an embodiment of the present disclosure. The figure shows a schematic diagram of a shooting and editing interface. As shown in the figure, the first area displays the target environment description information as "at home, the sun is shining, and the kitten is lying on the sofa", and the character dialogue information is "protagonist: baby, come and give you something delicious", "kitten: (a gentle meow)", and the shooting time of the scene can be determined based on the length of the target character dialogue information, and can also be adjusted according to user needs.

[0118] In addition, the second area of ​​the shooting editing interface shown in Figure 4a displays the target shooting background corresponding to the target scene, which matches the environmental description information. The figure also includes the target scene duration (9 seconds), image position controls (to adjust the background image or background video to the foreground or background), save controls, shooting controls, controls for editing the current shooting scene, controls for adding a new shooting scene, and controls for character settings.

[0119] In an embodiment of the present disclosure, in response to a modification and update operation on the target environment description information, the target shooting background matching the modified target environment description information is updated and displayed in the second area; and / or, in response to a modification and update operation on the target character dialogue information, the shooting duration of the target shooting scene is updated based on the length of the modified target character dialogue information.

[0120] For example, for the triggering operation of editing the current shooting scene control shown in FIG4a, the re-editing interface shown in FIG4b is displayed, and new target environment description information and / or new target character dialogue information can be input. For example, the target character dialogue information in FIG4b is modified to "Music: Piano background music, Protagonist: Come, baby, let me comb your hair" and "Kitten: (gentle meow)". The shooting duration of the target shooting scene can also be updated according to the length of the modified target character dialogue information. The figure also includes the use control and the regeneration clip control. Therefore, the result of the modification and update operation in response to the target character dialogue information is shown in FIG4c.

[0121] In an embodiment of the present disclosure, displaying a character indication area on a target shooting background also includes: in response to a triggering operation on a character setting control in a shooting editing interface, obtaining character characteristic information set corresponding to the character indication area; determining a target character based on the character characteristic information, and displaying the target character in association with the character indication area during shooting.

[0122] For example, triggering the "Add Left-Side Character" and "Add Right-Side Character" character setting controls shown in FIG4a can retrieve character characteristic information corresponding to the character indicator area, determine the target character based on the character characteristic information, and associate the target character with the character indicator area during filming. The character characteristic information includes information such as the character's age and gender.

[0123] Step 205: In response to the scene adding operation, a new shooting scene and shooting material information corresponding to the new shooting scene are added to the shooting editing interface.

[0124] Exemplarily, for the triggering operation of adding a new shooting scene control shown in FIG. 4 a , a new shooting scene and shooting material information corresponding to the new shooting scene are added.

[0125] Step 206 : In response to a deletion operation on the target shooting scene in the at least one shooting scene, the target shooting scene and target shooting material information corresponding to the target shooting scene are deleted in the shooting editing interface.

[0126] Specifically, the target shooting scene in the at least one shooting scene may be deleted, and the target shooting material information corresponding to the target shooting scene may be deleted simultaneously with the deletion of the target shooting scene.

[0127] After step 204 , step 205 and / or step 206 may be executed. The execution order of steps 204 to 206 may be determined according to actual conditions. FIG. 2 is only an example.

[0128] Step 207: In response to setting the multiple shooting scenes to continuous mode, after the shooting time of the current shooting scene is reached based on the shooting material information of the current shooting scene, automatically switch to the next shooting scene and continue shooting based on the shooting material information of the next shooting scene.

[0129] Step 208: In response to setting the multiple shooting scenes to interval mode, stop shooting after the shooting time of the current shooting scene is reached based on the shooting material information of the current shooting scene, jump to the next shooting scene based on the switching instruction of the next shooting scene, and continue shooting based on the shooting material information of the next shooting scene.

[0130] Specifically, the shooting duration can be automatically generated based on the character dialogue information, or it can be set as needed. During shooting, each shooting scene can automatically switch to the next shooting scene after reaching the preset shooting duration. You can also turn off the automatic switching function and choose to manually switch to the next shooting scene by clicking the screen during shooting.

[0131] Step 209: In response to setting the target character to the partial prop mode, rendering is performed on the partial props and the target character during shooting.

[0132] Step 210: In response to setting the target character to the all-props mode, the target character is subjected to matting technology during shooting, and the matting result and all props are rendered.

[0133] Step 211: In response to setting the target character to the virtual prop mode, the virtual prop is controlled and processed according to the skeletal motion information of the reference character during shooting.

[0134] It is understandable that the original text information generated by the first model and different shooting methods correspond to different prop types, such as jewelry props (such as a hat), full-body props (such as a whole body image with bone points) and virtual props (such as a little bear); among them, virtual props can be pre-set.

[0135] For example, if you choose to shoot with ornaments and props, you can use human faces or human bodies, and after recognizing the human face, you can present the generated character props. For example, as shown in FIG5a , the display result of rendering the hat prop and the target character during shooting is shown.

[0136] For example, if you choose to use full-body props for shooting, the generated body remains unchanged, and the matting technology is used to only cut out the face position and place it on the generated body. For example, as shown in Figure 5b, the target character is processed with the matting technology during shooting, and the matting result and all the props are rendered and displayed.

[0137] In addition, during shooting, the virtual props are controlled, processed and displayed according to the skeletal movement information of the reference character, thereby meeting the user's diverse shooting needs and improving the video shooting experience.

[0138] Step 212: In response to setting the target shooting scene to the person mode, the background image or background video corresponding to the target shooting scene is set as the background during shooting, and the person in the camera is placed in the foreground.

[0139] Step 213: In response to setting the target shooting scene to the empty shot mode, the background image or background video corresponding to the target shooting scene is set as the foreground during shooting, and the person in the camera is hidden in the shooting scene.

[0140] Specifically, if a person is required to play a certain role, the background picture or background video corresponding to the target shooting scene needs to be set as the background; if no person is required to play a certain role, the background picture or background video corresponding to the target shooting scene is set as the foreground (that is, the background picture or background video appears in the foreground), and the person in the camera is hidden in the shooting scene.

[0141] For example, the picture position control display interface in the shooting editing interface shown in Figure 4a can be shown in Figure 6a, and scene attributes can be selected, such as "character scene", "empty shot" and "cancel" as shown in the figure, and the remark information "Select character scene, you can shoot characters in the scene, select empty shot, there will be no characters".

[0142] For example, if you choose to shoot with virtual props, the screen uses the "foreground", presents the generated virtual image on the background, recognizes human body movements, allows the human body to control the movements of the virtual image while the human body does not appear on the screen. For example, as shown in Figure 6b, when shooting, the background picture or background video corresponding to the target shooting scene is set as the foreground, the character in the camera is hidden in the shooting scene, and the virtual prop bear is displayed.

[0143] Thus, the target video can be generated by shooting according to the aforementioned shooting setting information and shooting material information.

[0144] In the generated target video, character dialogues can be played through speech synthesis, or the voice dialogues input by the user can be converted into text through speech-to-text technology and displayed in the target video, further meeting user needs and improving video shooting effects.

[0145] In the above scheme, the video shooting background, shooting characters and other shooting material information are generated by the input shooting summary information and the selected video style, and different props can be used for shooting, thereby improving the shooting efficiency and the video shooting effect, meeting user needs and enhancing the user experience.

[0146] After step 204, step 207 or step 208 and / or step 209 or step 210 or step 211 and / or step 212 or step 213 may be executed. The execution order of steps 204-213 may be determined according to actual conditions. FIG. 2 is only an example.

[0147] FIG8 is a schematic diagram of the structure of a video generation device provided by an embodiment of the present disclosure. The device can be implemented by software and / or hardware and can generally be integrated into an electronic device. As shown in FIG8 , the device includes:

[0148] A display module 301 is configured to display a shooting editing interface in response to the input video style and shooting summary information, wherein the shooting editing interface includes: at least one shooting scene, and shooting material information corresponding to the shooting scene, wherein the shooting material information matches the video style and the shooting summary information and is used to indicate multimedia information required for the shooting scene during shooting;

[0149] A first acquisition module 302 is configured to acquire shooting setting information corresponding to the at least one shooting scene;

[0150] The generating module 303 is configured to generate a target video by performing shooting based on the shooting setting information and the shooting material information corresponding to the at least one shooting scene in response to a shooting trigger operation on the shooting editing interface.

[0151] Optionally, the device further comprises:

[0152] a second acquisition module, configured to acquire at least one shooting scene based on the scene processing instruction and the video style feedback, and shooting material information corresponding to the shooting scene;

[0153] The scene processing instruction is generated based on the shooting summary information and preset shooting scene elements.

[0154] Optionally, the shooting material information includes: environment description information and character dialogue information, wherein:

[0155] The environment description information and the character dialogue information are extracted from the original text information by parsing the scene processing instructions based on a first model that matches the video style.

[0156] Optionally, the shooting material information also includes: shooting background, where:

[0157] The shooting background is generated by processing the environment description information based on a second model that matches the video style, wherein the shooting background includes: an image background or a video background.

[0158] Optionally, the shooting material information also includes: character props, where:

[0159] The character props are generated by processing the character description information extracted from the original text information based on a second model that matches the video style.

[0160] Optionally, the beat display module is specifically used to:

[0161] In response to a selection operation of a target shooting scene from the at least one shooting scene, displaying target environment description information and target character dialogue information corresponding to the target shooting scene in a first area of ​​the shooting editing interface, wherein a shooting duration of the target shooting scene is determined based on a length of the target character dialogue information; and

[0162] A target shooting background corresponding to the target scene is displayed in a second area of ​​the shooting editing interface, wherein the target shooting background matches the environment description information.

[0163] Optionally, the device further includes:

[0164] An updating module, configured to update and display, in the second area, a target shooting background matching the modified target environment description information in response to a modification and update operation on the target environment description information;

[0165] and / or,

[0166] The updating module is further configured to update the shooting duration of the target shooting scene based on the length of the modified target character dialogue information in response to a modification and update operation on the target character dialogue information.

[0167] Optionally, displaying a character indication area on the target shooting background further includes:

[0168] In response to a triggering operation on a character setting control in the shooting editing interface, acquiring character feature information corresponding to the character indication area;

[0169] A target character is determined according to the character feature information, and the target character is associated with the character indication area and displayed during shooting.

[0170] Optionally, the device further comprises:

[0171] an adding module, configured to add a new shooting scene and shooting material information corresponding to the new shooting scene to the shooting editing interface in response to a scene adding operation; and / or

[0172] The deleting module is configured to delete the target shooting scene and target shooting material information corresponding to the target shooting scene in the shooting editing interface in response to a deletion operation on the target shooting scene in the at least one shooting scene.

[0173] Optionally, the shooting setting information includes: a continuous mode and an interval mode, and the generating module 303 is configured to:

[0174] In response to setting the continuous mode for multiple shooting scenes, automatically switching to the next shooting scene after the shooting time of the current shooting scene is reached based on the shooting material information of the current shooting scene, and continuing shooting based on the shooting material information of the next shooting scene;

[0175] or,

[0176] In response to setting the interval mode for multiple shooting scenes, shooting is stopped after the shooting time of the current shooting scene is reached based on the shooting material information of the current shooting scene, and the next shooting scene is jumped to based on the switching instruction of the next shooting scene, and shooting is continued based on the shooting material information of the next shooting scene.

[0177] Optionally, the shooting setting information includes: a character prop mode, and the generating module 303 is specifically configured to:

[0178] In response to setting the target character to a partial prop mode, rendering the partial props and the target character during shooting; or

[0179] In response to setting the target character to the all-props mode, the target character is subjected to matting technology during filming, and the matting result and all the props are rendered; or

[0180] In response to setting the target character to the virtual prop mode, the virtual prop is controlled and processed according to the skeletal motion information of the reference character during shooting.

[0181] Optionally, the shooting setting information includes: a person mode and an empty shot mode, and the generating module 303 is specifically configured to:

[0182] In response to setting the target shooting scene to the person mode, the background picture or background video corresponding to the target shooting scene is set as the background during shooting, and the person in the camera is placed in the foreground; or

[0183] In response to setting the target shooting scene to the empty shot mode, the background picture or background video corresponding to the target shooting scene is set as the foreground during shooting, and the person in the camera is hidden in the shooting scene.

[0184] The video generation device provided in the embodiments of the present disclosure can execute the video generation method provided in any embodiment of the present disclosure, and has the corresponding functional modules and beneficial effects of the execution method.

[0185] An embodiment of the present disclosure further provides a computer program product, including a computer program / instruction, which, when executed by a processor, implements the video generation method provided by any embodiment of the present disclosure.

[0186] FIG8 is a schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure. Specific reference will be made below to FIG8 , which shows a schematic diagram of the structure of an electronic device 400 suitable for implementing an embodiment of the present disclosure. The electronic device 400 in the embodiment of the present disclosure may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (e.g., vehicle-mounted navigation terminals), and the like, as well as fixed terminals such as digital TVs, desktop computers, and the like. The electronic device shown in FIG8 is merely an example and should not impose any limitations on the functions and scope of use of the embodiments of the present disclosure.

[0187] As shown in Figure 8, the electronic device 400 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 401, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 402 or a program loaded from a storage device 408 into a random access memory (RAM) 403. Various programs and data required for the operation of the electronic device 400 are also stored in the RAM 403. The processing device 401, the ROM 402, and the RAM 403 are connected to each other via a bus 404. An input / output (I / O) interface 405 is also connected to the bus 404.

[0188] Typically, the following devices may be connected to the I / O interface 405: an input device 406 including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 407 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 408 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 409. The communication device 409 may allow the electronic device 400 to communicate with other devices wirelessly or by wire to exchange data. Although FIG8 shows the electronic device 400 with various devices, it should be understood that not all of the devices shown are required to be implemented or present. More or fewer devices may alternatively be implemented or present.

[0189] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program includes program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network via the communication device 409, or installed from the storage device 408, or installed from the ROM 402. When the computer program is executed by the processing device 401, the above-mentioned functions defined in the video generation method of the embodiment of the present disclosure are performed.

[0190] It should be noted that the computer-readable medium mentioned above in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or component, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, device, or component. In the present disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted using any suitable medium, including but not limited to wires, optical cables, RF (radio frequency), etc., or any suitable combination thereof.

[0191] In some embodiments, the client and server can communicate using any currently known or later developed network protocol, such as HTTP (Hypertext Transfer Protocol), and can be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or later developed network.

[0192] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0193] The above-mentioned computer-readable medium carries one or more programs. When the above-mentioned one or more programs are executed by the electronic device, the electronic device: receives the user's information display trigger operation during the playback of the video; obtains at least two target information associated with the video; displays the first target information among the at least two target information in the information display area of ​​the playback page of the video, wherein the size of the information display area is smaller than the size of the playback page; receives the user's first switching trigger operation, and switches the first target information displayed in the information display area to the second target information among the at least two target information.

[0194] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages, or a combination thereof, including, but not limited to, object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on the remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0195] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or a part of code, and the module, program segment, or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of the boxes in the block diagram and / or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0196] The units involved in the embodiments described in this disclosure may be implemented in software or hardware, wherein the name of a unit does not necessarily limit the unit itself.

[0197] The functions described above herein may be performed, at least in part, by one or more hardware logic components. For example, and without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chip (SOCs), complex programmable logic devices (CPLDs), and the like.

[0198] In the context of the present disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in conjunction with an instruction execution system, device or equipment. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium can include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0199] According to one or more embodiments of the present disclosure, the present disclosure provides an electronic device, including:

[0200] processor;

[0201] a memory for storing instructions executable by the processor;

[0202] The processor is configured to read the executable instructions from the memory and execute the instructions to implement any one of the video generation methods provided in the present disclosure.

[0203] According to one or more embodiments of the present disclosure, the present disclosure provides a computer-readable storage medium, wherein the storage medium stores a computer program, and the computer program is used to execute any one of the video generation methods provided by the present disclosure.

[0204] The above description is merely a preferred embodiment of the present disclosure and an illustration of the technical principles employed. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by the specific combination of the above-mentioned technical features, but also includes other technical solutions formed by any combination of the above-mentioned technical features or their equivalents without departing from the above-mentioned disclosed concepts. For example, a technical solution formed by replacing the above-mentioned features with (but not limited to) technical features with similar functions disclosed in this disclosure.

[0205] In addition, although each operation is described in a specific order, this should not be understood as requiring these operations to be performed in the specific order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details have been included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

[0206] Although the subject matter has been described in language specific to structural features and / or methodological logical acts, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are merely example forms of implementing the claims.

Claims

1. A video generation method, wherein: The method comprises: In response to the input video style and shooting summary information, displaying a shooting editing interface, wherein the shooting editing interface includes: at least one shooting scene, and shooting material information corresponding to the shooting scene, wherein the shooting material information matches the video style and the shooting summary information and is used to indicate multimedia information required for the shooting scene when shooting; Acquire shooting setting information corresponding to the at least one shooting scene; In response to a shooting trigger operation on the shooting editing interface, shooting is performed based on the shooting setting information and the shooting material information corresponding to the at least one shooting scene to generate a target video.

2. The method according to claim 1, wherein: The method further comprises: Acquire at least one shooting scene based on the scene processing instruction and the video style feedback, and shooting material information corresponding to the shooting scene; The scene processing instruction is generated based on the shooting summary information and preset shooting scene elements.

3. The method according to claim 2, wherein: The shooting material information includes: environment description information and character dialogue information, wherein: The environment description information and the character dialogue information are extracted from the original text information by parsing the scene processing instructions to obtain original text information based on a first model that matches the video style.

4. The method according to claim 3, wherein: The shooting material information also includes: shooting background, where: The shooting background is generated by processing the environment description information based on a second model that matches the video style, wherein the shooting background includes: an image background or a video background.

5. The method according to claim 3, wherein: The shooting material information also includes: character props, among which, The character props are generated by processing the character description information extracted from the original text information based on a second model that matches the video style.

6. The method according to claim 1, wherein: The shooting material information corresponding to the shooting scene displayed on the shooting editing interface includes: In response to a selection operation of a target shooting scene in the at least one shooting scene, displaying target environment description information and target character dialogue information corresponding to the target shooting scene in a first area in the shooting editing interface, wherein the shooting duration of the target shooting scene is determined based on the length of the target character dialogue information; and The second area in the shooting editing interface displays a target shooting background corresponding to the target scene. In the embodiment, the target shooting background matches the environment description information.

7. The method according to claim 6, wherein: The method further comprises: In response to a modification and update operation on the target environment description information, updating and displaying a target shooting background matching the modified target environment description information in the second area; and / or, In response to the modification and update operation on the target character dialogue information, the shooting duration of the target shooting scene is updated based on the length of the modified target character dialogue information.

8. The method according to claim 6, wherein: Displaying a role indication area on the target shooting background also includes: In response to a triggering operation on a role setting control in the shooting editing interface, acquiring role characteristic information set corresponding to the role indication area; The target character is determined according to the character feature information, and the target character is associated with the character indication area and displayed during shooting.

9. The method according to claim 1, wherein: The method further comprises: In response to the scene adding operation, adding a new shooting scene and shooting material information corresponding to the new shooting scene to the shooting editing interface; and / or, In response to a deletion operation on a target shooting scene in the at least one shooting scene, the target shooting scene and target shooting material information corresponding to the target shooting scene are deleted in the shooting editing interface.

10. The method according to claim 1, wherein: The shooting setting information includes: a continuous mode and an interval mode, and the shooting based on the shooting setting information corresponding to the at least one shooting scene and the shooting material information includes: In response to setting the plurality of shooting scenes to the continuous mode, automatically switching to the next shooting scene after the shooting time of the current shooting scene is reached based on the shooting material information of the current shooting scene, and continuing shooting based on the shooting material information of the next shooting scene; or, In response to setting multiple shooting scenes to the interval mode, shooting is stopped after the shooting time of the current shooting scene is reached based on the shooting material information of the current shooting scene, and the next shooting scene is jumped to based on the switching instruction of the next shooting scene, and shooting is continued based on the shooting material information of the next shooting scene.

11. The method according to claim 1, wherein: The shooting setting information includes: a character prop mode, and the shooting based on the shooting setting information corresponding to the at least one shooting scene and the shooting material information includes: In response to setting the target character to a partial prop mode, rendering the partial props and the target character during shooting; or, In response to setting the target character to the all-props mode, the target character is subjected to the matte technique during shooting. Processing, rendering the matting result and all the props; or, In response to setting the target character to the virtual prop mode, the virtual prop is controlled and processed according to the skeletal movement information of the reference character during shooting.

12. The method according to claim 1, wherein: The shooting setting information includes: a person mode and an empty shot mode, and the shooting based on the shooting setting information corresponding to the at least one shooting scene and the shooting material information includes: In response to setting the target shooting scene to the person mode, when shooting, the background picture or background video corresponding to the target shooting scene is set as the background, and the person in the camera is placed in the foreground; or In response to setting the target shooting scene to the empty shot mode, the background picture or background video corresponding to the target shooting scene is set as the foreground during shooting, and the person in the camera is hidden in the shooting scene.

13. A video generating device, comprising: A display module is used to display a shooting editing interface in response to the input video style and shooting summary information, wherein the shooting editing interface includes: at least one shooting scene, and shooting material information corresponding to the shooting scene, wherein the shooting material information matches the video style and the shooting summary information, and is used to indicate the multimedia information required for the shooting scene when shooting; A first acquisition module, used to acquire shooting setting information corresponding to the at least one shooting scene; A generation module is used to respond to a shooting trigger operation on the shooting editing interface, shoot based on the shooting setting information corresponding to the at least one shooting scene and the shooting material information to generate a target video.

14. An electronic device, wherein: The electronic device comprises: processor; a memory for storing instructions executable by the processor; The processor is used to read the executable instructions from the memory and execute the instructions to implement the video generation method described in any one of claims 1-12.

15. A computer-readable storage medium, wherein: The storage medium stores a computer program, and the computer program is used to execute the video generation method described in any one of claims 1 to 12.

Images