Method, apparatus, device, storage medium and program product for media content generation

Abstract

The application provides a method, device, equipment, storage medium and program product for media content generation. The method comprises: receiving a first operation, the first operation indicating content generation under a first setting system, the first setting system comprising one or more preset narrative elements; presenting narrative information, the narrative information describing an event occurring under the first setting system; and based on a second operation, presenting first media content, the first media content being generated based on the narrative information.

Description

Technical Field

[0001] The examples in this article generally relate to the field of computer science, and in particular to methods, apparatuses, devices, storage media, and program products for the generation of media content. Background Technology

[0002] With the rapid development of content generation technology, users' demand for creative content generation based on specific styles or narrative systems is growing. However, for ordinary users, quickly generating high-quality media content based on specific narrative systems still faces difficulties in terms of high technical barriers and operational complexity. Summary of the Invention

[0003] In a first aspect, this paper provides a method for generating media content. The method includes: receiving a first operation, the first operation instructing content generation under a first set system, the first set system including one or more preset narrative elements; presenting narrative information describing events occurring under the first set system; and, based on a second operation, presenting first media content generated based on the narrative information.

[0004] In a second aspect of this document, a media content generation apparatus is provided. The apparatus includes: a receiving module configured to receive a first operation, the first operation instructing content generation under a first preset system, the first preset system including one or more preset narrative elements; a first presentation module configured to present narrative information describing events occurring under the first preset system; and a second presentation module configured to present first media content based on the second operation, the first media content being generated based on the narrative information.

[0005] In a third aspect of this document, an electronic device is provided. The electronic device includes: at least one processing unit; and at least one memory coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, the instructions causing the electronic device to perform the method of the first aspect when executed by the at least one processing unit.

[0006] In a fourth aspect of this document, a computer-readable storage medium is provided. The computer-readable storage medium stores computer-executable instructions that can be executed by a processor to implement the method of the first aspect.

[0007] In a fifth aspect of this document, a computer program product is provided. The computer program product is tangibly stored in a computer storage medium and includes computer-executable instructions that, when executed by a device, cause the device to perform the method of the first aspect.

[0008] In this way, by generating content within a pre-defined framework, the operational threshold for users to create media content based on a specific narrative system can be lowered, thereby improving the efficiency of content generation.

[0009] It should be understood that the content described in this section is not intended to limit the key or important features of the examples in this article, nor is it intended to restrict the scope of the solution. Other features will become readily apparent from the following description. Attached Figure Description

[0010] The above and other features, advantages, and aspects of the various examples herein will become more apparent when taken in conjunction with the accompanying drawings and the following detailed description. In the accompanying drawings, the same or similar reference numerals denote the same or similar elements, wherein: Figure 1 A schematic diagram of the example environment is shown; Figures 2A to 2F The diagram illustrates sample interfaces for media content generation in several scenarios. Figure 3 The diagram illustrates the interactive and backend processing flow for media content generation in several scenarios. Figure 4 Flowcharts illustrating methods for media content generation in several scenarios are shown; Figure 5 Block diagrams of apparatuses for media content generation in several scenarios are shown; and Figure 6 A block diagram of an electronic device capable of implementing multiple illustrative scenarios is shown. Detailed Implementation

[0011] The examples in this document will now be described in more detail with reference to the accompanying drawings. While some examples are shown in the drawings, it should be understood that solutions can be implemented in various forms and should not be construed as limited to the examples presented herein. Rather, these examples are provided to provide a more thorough and complete understanding of the solutions. It should be understood that the drawings and examples in this document are for illustrative purposes only and are not intended to limit the scope of protection of the solutions.

[0012] It should be noted that the headings of any section / subsection provided herein are not restrictive. Various examples are described throughout this document, and examples of any type may be included under any section / subsection. Furthermore, examples described in any section / subsection may be combined in any way with any other examples described in the same section / subsection and / or different sections / subsections.

[0013] In the description of the examples in this document, the term "including" and similar terms should be understood as open inclusion, i.e., "including but not limited to". The term "based on" should be understood as "at least partially based on". The term "an example" or "the example" should be understood as "at least one example". The term "some examples" should be understood as "at least some examples". Other explicit and implicit definitions may also be included below. The terms "first", "second", etc., may refer to different or the same objects. Other explicit and implicit definitions may also be included below.

[0014] The examples in this document may involve user data, data acquisition, and / or use. All of these aspects comply with relevant laws, regulations, and rules. In the examples, all data collection, acquisition, processing, manipulation, forwarding, and use are conducted with the user's knowledge and confirmation. Accordingly, when implementing each example, the type, scope of use, and usage scenarios of any data or information that may be involved should be communicated to the user and their authorization obtained through appropriate means, in accordance with relevant laws and regulations. The specific methods of notification and / or authorization can vary depending on the actual situation and application scenario; the scope of the solution is not limited in this regard.

[0015] In this manual and the sample solutions, any processing of personal information will be conducted only under legal grounds (such as obtaining the consent of the data subject or being necessary for the performance of a contract) and will only be carried out within the scope stipulated or agreed upon. A user's refusal to process personal information beyond what is necessary for basic functions will not affect the user's use of basic functions.

[0016] The term "setting system" as used in this article refers to a set of predefined narrative-related settings, which may include, but are not limited to, one or more elements such as narrative background, narrative participants, narrative logic, visual style, and content style. The setting system can be extracted and constructed based on existing media content (such as videos, animations, etc.), or it can be pre-configured by the creator or the system.

[0017] The term "narrative element" as used in this article refers to the basic building blocks that constitute the setting system. It may include, but is not limited to, one or more of the following: narrative background (e.g., historical context, social state, etc.), narrative participants (e.g., characters, character relationships, character attributes, etc.), and narrative logic (e.g., main storyline, plot development, etc.).

[0018] The term "narrative information" as used in this article refers to information describing events that occur within a specific setting, which may include, but is not limited to, story outlines, story scripts, character behavior descriptions, and scene descriptions. Narrative information can be automatically generated by the system based on the setting, or it can be generated by combining user-inputted custom content.

[0019] As used in this article, "media content" refers to content presented in visual and / or auditory forms, which may include, but is not limited to, video, animation, and image sequences. Media content can be generated based on the visual style of narrative information and setting.

[0020] The term "entry element" as used in this article refers to an interactive element used by users to select and enter a specific setting system, which may include, but is not limited to, triggerable interface elements such as cards, buttons, and icons.

[0021] As mentioned above, with the rapid development of artificial intelligence and multimedia content generation technologies, users' demand for creative content generation based on specific styles or narrative systems is growing. In some scenarios, users want to create entirely new stories that conform to the existing narrative system of media content (such as specific historical backgrounds, character settings, visual styles, etc.) and generate these stories as media content such as videos. However, traditional content creation methods usually require users to have professional video production skills and to manually complete all stages from story conception to video production, which presents a high technical threshold and operational complexity for ordinary users.

[0022] A media content generation scheme is proposed. According to this scheme, an electronic device can receive an instruction to perform a first operation of content generation under a first preset system, wherein the first preset system includes one or more preset narrative elements. The electronic device can present narrative information describing events occurring under the first preset system. Furthermore, the electronic device can, based on a second operation instructing content generation based on the narrative information, present first media content generated based on the narrative information.

[0023] Through the above solution, users can quickly generate narrative information and media content that conform to a preset setting system, reducing the number of steps required from narrative conception to media content generation. Since the narrative elements in the setting system are pre-loaded and injected into the generation model as constraints for content generation, the server does not need to re-parse and reconstruct the complete narrative context for each generation request, thereby reducing server computational overhead and bandwidth consumption for transmitting narrative context data in edge-cloud communication.

[0024] The following describes various examples of this scheme in further detail with reference to the accompanying drawings.

[0025] Figure 1 A schematic diagram of example environment 100 is shown. (e.g.) Figure 1 As shown, example environment 100 may include electronic device 110.

[0026] In this example environment 100, electronic device 110 may run an application 120 that supports media content generation. Application 120 may be any suitable type of application for media content generation, including but not limited to video creation applications, short drama production applications, or other suitable applications. User 140 may interact with application 120 via electronic device 110 and / or its attached devices.

[0027] exist Figure 1 In environment 100, if application 120 is active, electronic device 110 can present interface 150 for supporting media content generation through application 120. In some cases, electronic device 110 communicates with server 130 to provide services to application 120.

[0028] Electronic device 110 can be any type of mobile terminal, fixed terminal, or portable terminal, including mobile phones, desktop computers, laptop computers, notebook computers, netbook computers, tablet computers, media computers, multimedia tablets, handheld computers, portable gaming terminals, VR / AR devices, personal communication system (PCS) devices, personal navigation devices, personal digital assistants (PDAs), audio / video players, digital cameras / camcorders, positioning devices, television receivers, radio receivers, e-book devices, gaming devices, or any combination thereof, including accessories and peripherals of these devices or any combination thereof. In some cases, electronic device 110 may also support any type of user-facing interface (such as "wearable" circuitry).

[0029] Server 130 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks, and big data and artificial intelligence platforms. Server 130 may include, for example, computing systems / servers such as mainframes, edge computing nodes, computing devices in a cloud environment, etc. Server 130 can provide backend services for applications 120 in electronic devices 110 that support media content generation.

[0030] A communication connection can be established between server 130 and electronic device 110. This communication connection can be established via wired or wireless means. The communication connection can include, but is not limited to, Bluetooth, mobile network, Universal Serial Bus (USB), and Wireless Fidelity (WiFi) connections. In some cases, server 130 and electronic device 110 can exchange signaling information through their communication connection.

[0031] It should be understood that the structure and function of the various elements in environment 100 are described for illustrative purposes only and do not imply any limitation on the scope of the scheme.

[0032] The examples described herein can be implemented on electronic device 110. It should be noted that the operations described relative to electronic device 110 can be performed by a related application 120 running on electronic device 110. The interface described relative to electronic device 110 can be provided by application 120; for example, electronic device 110 presents the corresponding interface by running application 120. Furthermore, some operations described relative to electronic device 110 may require the assistance of server 130 to complete.

[0033] The following description of the example will continue with reference to the accompanying drawings.

[0034] Figure 2A A schematic diagram of an interface 200A for media content generation is shown, based on several scenarios. See below for reference. Figure 2A To describe the process of media content generation.

[0035] like Figure 2AAs shown, on interface 200A, electronic device 110 presents multiple entry elements 202, 203, 204, 205, 206, and 207. In some embodiments, entry elements 202 to 207 may correspond to different setting systems. For example, a setting system can refer to a set of overall narrative settings used to constrain and guide the generation of narrative information (also known as a story), which may include, but is not limited to, one or more of the following elements: world location, historical background, storyline, visual style, narrative rules, character types, character attributes, character relationships, character responsibilities, and character abilities. The setting system can be used to limit the narrative space and narrative logic of the narrative information, so that the story outline, story script, character behavior, scene description, and / or media content generated under the setting system can conform to the overall setting of the setting system. For example, under the setting system of a magical world, narrative information can be generated around mages, magical abilities, magical rules, and corresponding character relationships. Similarly, under the setting system of an animal group, narrative information can be generated around different animal species, habitats, group rules, character responsibilities, group relationships, and survival challenges. Therefore, users can randomly generate new stories while keeping the basic settings of the system unchanged, or adjust narrative elements such as characters, character relationships, endings, and event progression through custom inputs, thereby generating new narrative information and media content that matches the system settings. This will be described in detail below.

[0036] exist Figure 2A In the example, entry element 202 can correspond to the first setting system (e.g., the same as setting system A), and entry elements 203 to 207 can each correspond to other different setting systems. Each entry element can include an icon and a text label to display the name and identifier of the corresponding setting system to the user. In some cases, entry elements 203 to 207 can correspond to other types of content creation methods, and are not limited to content generation based on a setting system.

[0037] In some cases, electronic device 110 may present interface 200A (also referred to as a second interface), which includes one or more entry elements 202 to 207, each corresponding to one or more setting systems. In some cases, electronic device 110 may receive an entry trigger operation (also referred to as a fourth operation) triggered on a first entry element (e.g., entry element 202) of the one or more entry elements. The first entry element may correspond to a first setting system. In response to this entry trigger operation, electronic device 110 may present another interface (also referred to as a first interface, e.g., ...). Figure 2B The interface shown is 200B.

[0038] In this way, users can access the corresponding settings page with a single trigger operation on the entry element, reducing the number of steps required for users to select and navigate between different settings systems. Since the settings system information corresponding to the entry element can be pre-loaded into the client cache when the user browses the interface 200A, the client does not need to request the basic settings system data from the server again when the user performs the trigger operation. This reduces the number of data requests and bandwidth usage in end-to-end cloud communication, while also shortening the response latency from the user's trigger operation to the presentation of the first interface.

[0039] Figure 2B A schematic diagram of an interface 200B for media content generation is shown, based on several scenarios. See below for reference. Figure 2B This describes the process of content generation under the first set system.

[0040] like Figure 2B As shown, on interface 200B, electronic device 110 can display a description area 212 and description information 214, a first element 216 and a second element 218. Description area 212 can be used to display the name and icon of the first setting system. Description area 212 can also display keywords of the first setting system. Description information 214 is used to display one or more preset narrative elements in the first setting system, such as a textual description of the narrative background, narrative participants, and narrative logic of the setting system.

[0041] In some cases, as described above, the electronic device 110 may present an interface 200B as an example of a first interface. The interface 200B may include descriptive information 214 and at least one element (e.g., a first element 216 and a second element 218). The descriptive information 214 may be used to display one or more pre-defined narrative elements in a first setting system. At least one element may correspond to at least one generation mode. As used herein, the term "generation mode" refers to a type of mode used to determine how narrative information is generated, which may include, but is not limited to, a mode that is randomly generated without additional information, a mode generated based on user-defined input, and a mode generated by adjusting narrative elements.

[0042] Electronic device 110 can receive a story generation trigger operation (also called a first operation) on a first interface, which is triggered on one of at least one element. Figure 2B As an example, a user can trigger a story generation operation by triggering either the first element 216 or the second element 218.

[0043] In this way, users can intuitively understand the narrative elements of the setting system and select the generation mode within a single interface, reducing the number of interface jumps between understanding the setting system and selecting the generation mode. Because the descriptive information and generation mode elements are presented centrally on the same interface, the client only needs to load one screen to complete both the setting system display and generation mode selection functions, eliminating the need to load separate pages for each. This reduces the client's page rendering overhead and the number of interface loads and updates.

[0044] In some cases, at least one generation mode may include at least one of a first generation mode, a second generation mode, and a third generation mode. The first generation mode may correspond to content generation without additional information. The second generation mode may correspond to user-defined content generation. The third generation mode may correspond to content generation by adjusting at least one of one or more narrative elements. Figure 2B As an example, the first element 216 can correspond to the first generation pattern, and the second element 218 can correspond to the second generation pattern.

[0045] In this way, users can flexibly choose from multiple generation modes according to their creative intentions, reducing the number of steps required for exploring different creative paths. Since the backend generation pipelines corresponding to different generation modes can be pre-configured and cached, the server can directly call the corresponding generation pipeline based on the generation mode selected by the user, without having to dynamically build the generation pipeline for each request, thereby reducing the server's computational overhead and the initialization latency of the generation pipeline.

[0046] In some cases, narrative information can be related to the generation mode indicated by the story generation trigger operation. For example, when the story generation trigger operation indicates the first generation mode, the narrative information can be randomly generated entirely based on the first setting system. For example, when the story generation trigger operation indicates the second generation mode, the narrative information can be generated by combining user-defined input and the first setting system. For example, when the story generation trigger operation indicates the third generation mode, the narrative information can be generated based on narrative elements adjusted by the user.

[0047] In this way, the way narrative information is generated can be adapted to the generation mode selected by the user, and the user does not need to specify the generation strategy of narrative information separately.

[0048] In some scenarios, in response to a story generation trigger operation instruction to generate content without additional information (i.e., the first generation mode), the electronic device 110 can present narrative information generated based on a first set system (e.g., randomly generated). In this generation mode, the server 130 can inject narrative elements from the first set system as constraints into prompts in a large language model. The large language model then randomly generates narrative information based on these narrative elements and returns it to the electronic device 110 for presentation in a streaming manner. The following section combines... Figure 2C Let's have a discussion.

[0049] Figure 2C A schematic diagram of an interface 200C for media content generation is shown, based on several scenarios. For example... Figure 2C As shown, on interface 200C, electronic device 110 presents description information 214, a first element 216, a second element 218, a narrative information area 220, and a submission element 222. The narrative information area 220 can be used to present narrative information (i.e., story content) generated based on a first setting system. The submission element 222 can be used to receive a content generation operation (also known as a second operation) that instructs the generation of media content based on the narrative information.

[0050] In this way, users can obtain narrative information that conforms to the set system without entering any additional information, reducing the number of steps required for users to go from entering the set system to obtaining the narrative information. Since the narrative information is returned in a streaming manner, the electronic device 110 can start rendering and presenting as soon as it receives part of the narrative information, without waiting for the complete narrative information to be generated. This shortens the user's perceived first byte time and reduces the main thread blocking time caused by the client waiting for a complete response.

[0051] In some cases, electronic device 110 can also receive a narrative update operation (also known as a third operation) that instructs the updating of narrative information. For example, a user can modify the generated narrative information or trigger a regeneration operation. In response to the narrative update operation, electronic device 110 can present the updated narrative information. The primary media content can be generated based on the updated narrative information. For example, such as... Figure 2C As shown, users can edit or trigger regeneration of the content in the narrative information area 220 in the interface 200C to obtain updated narrative information.

[0052] In this way, users can iteratively adjust narrative information without leaving the current interface, reducing the number of interface jumps between modifying narrative information and viewing the modification results.

[0053] Figure 2D A schematic diagram of an interface 200D for media content generation is shown, based on several scenarios. See below for reference. Figure 2D To describe the process of generating user-defined content.

[0054] like Figure 2D As shown, on interface 200D, electronic device 110 presents a description area 212, description information 214, a first element 216, a second element 218, a first input area 224, and a generation element 226. The first input area 224 is a text input area presented in response to a user's triggering operation on the second element 218, used to receive story ideas or synopsis information input by the user. The generation element 226 is used to trigger the generation of narrative information based on user input and a first set system.

[0055] In some cases, in response to a story generation trigger action instruction to generate user-defined content (i.e., a second generation mode), the electronic device 110 may present a first input area 224. For example... Figure 2D As shown, the first input area 224 may contain prompt text (e.g., prompting the user to describe a story idea) to guide the user in inputting the story idea. The electronic device 110 may receive input (also referred to as the first input) in the first input area 224 to summarize narrative information. In response to the first input, the electronic device 110 may present narrative information that conforms to the first setting system and the first input. For example, in response to the user inputting a story idea and triggering the generation element 226, the electronic device 110 may present narrative information that conforms to the first setting system and the first input.

[0056] In this way, users can obtain complete narrative information that conforms to the set system and incorporates their own ideas with just a short text input, reducing the number of steps between inputting an idea and obtaining a complete story. Since users only need to input a story outline rather than the complete story text, the amount of user input data transmitted from the client to the server is small. The server can generate complete narrative information based on the narrative elements of the set system and the user's outline, without requiring multiple rounds of user interaction to refine the story details, thereby reducing the number of interaction rounds between the client and cloud and the communication bandwidth consumption.

[0057] In some scenarios, in response to a story generation trigger action instructing content generation by adjusting at least one of one or more narrative elements (i.e., a third generation mode), the electronic device 110 may present a second input area. The second input area may be an input field for receiving user instructions on how to adjust the narrative elements. The electronic device 110 may receive a second input in the second input area, indicating an adjustment to at least one of the one or more narrative elements. For example, a user may input instructions to change characters, change the relationship between characters, or change the ending. In response to the second input, the electronic device 110 may present narrative information having at least one adjusted narrative element.

[0058] In this way, users can make targeted adjustments to specific narrative elements while retaining the core framework of the setting system, reducing the number of steps required for users to rethink the entire story in order to modify some narrative elements.

[0059] In some cases, the visual style of the primary media content can correspond to the visual style of the secondary media content, and the primary setting system is generated based on the secondary media content. For example, the secondary media content can be a high-quality video with a specific visual style, and the narrative elements and visual style parameters of the primary setting system can be extracted and constructed based on this secondary media content. Therefore, the primary media content generated based on the primary setting system will inherit the visual style of the secondary media content; for example, the color tone, rendering style, and character design style will remain consistent with the secondary media content.

[0060] In this way, user-generated media content can automatically inherit the visual style of the original high-quality content, without requiring users to manually specify or adjust visual style parameters. Since the visual style parameters are pre-extracted and stored as part of the configuration system, the video generation model can directly load the pre-stored style parameters when rendering video frames, eliminating the need to re-execute the style extraction and analysis calculation process with each generation request. This reduces server computational overhead and overall video generation latency.

[0061] Figure 2E A schematic diagram of an interface 200E (also known as a third interface) for media content generation is shown, depending on certain scenarios.

[0062] like Figure 2E As shown, on interface 200E, electronic device 110 displays a preview area 228, a playback control 229, a summary information area 230, and a start-up control (also called a first control) 232. The preview area 228 can be used to display preview information of the first media content (e.g., a preview of the first few seconds of a video). The playback control 229 can be used by the user to trigger playback of the generated preview content. The summary information area 230 displays summary information, which can be used to summarize the narrative information. The start-up control 232 can be used to trigger the complete generation of the first media content.

[0063] In some cases, in response to a second operation (e.g., a user triggering submission element 222 in interface 200C), electronic device 110 may present at least one of summary information and preview information in interface 200E. For example... Figure 2E As shown, summary information area 230 presents summary information for outlining the narrative information, and preview area 228 presents preview information for showing a portion of the primary media content (such as a preview of the first few seconds of a video).

[0064] In this way, users can preview a summary of the narrative information and a preview of the media content before triggering the generation of the full media content, reducing the number of times users need to regenerate the entire content if they are not satisfied with the generated result. Since the preview information only shows a part of the media content, the server only needs to render a small number of video frames to provide the preview. Compared with generating the full video, the computational overhead and rendering time of the preview rendering are significantly reduced, thereby reducing the server's computing resource consumption and the bandwidth consumption for transmitting preview data between the edge and the cloud.

[0065] Figure 2F A schematic diagram of an interface 200F for media content generation is shown, depending on certain scenarios.

[0066] like Figure 2F As shown, on interface 200F, electronic device 110 displays a progress information area 234, a generation progress details area 236, and a prompt message 238. Progress information area 234 displays the name of the current generation stage and the overall progress percentage. Generation progress details area 236 displays multiple sub-progress items, each corresponding to a different generation stage of the first media content, such as analyzing the story script, generating visual styles, rendering video frames, and synthesizing sound effects and background music. Prompt message 238 displays the estimated generation time and notification methods upon completion.

[0067] In some cases, in response to an operation on the start control 232 in interface 200E, electronic device 110 can display progress information (such as...). Figure 2F The progress information area 234 and the generation progress details area 236 in the interface 200F shown are used to display the generation process of the first media content. This progress information may include multiple sub-progress items, each corresponding to a different generation stage of the first media content. Upon completion of the generation process, the electronic device 110 can display the first media content.

[0068] In this way, users can understand the progress of each stage of media content generation in real time, reducing the number of times users need to repeatedly query or refresh the page due to uncertainty about the generation status while waiting. Since the progress information is presented in a phased form, the status updates of each stage can be implemented through lightweight status callbacks. The client only needs to receive and render the status change information, without polling the server to obtain complete generation status data, thereby reducing the number of client polling requests and the server query load, while also reducing the bandwidth consumption of end-to-end cloud communication.

[0069] Figure 3 A schematic diagram of the interactive and backend processing flow 300 for media content generation is shown, depending on several scenarios. For example... Figure 3As shown in the diagram, process 300 illustrates the collaboration process between the user interaction layer and the backend technology layer.

[0070] At the user interaction layer, process 300 includes stages such as homepage browsing 302, clicking cards 304, story creation 306, story submission 308, preview 310, one-click shooting 312, and waiting 314. At the backend technology layer, process 300 includes stages such as system setting loading 316, story generation 318, formatting 320, preview rendering 322, video generation 324, and returning 326.

[0071] During the homepage browsing phase 302, the electronic device 110 presents multiple entry elements on interface 200A. During the card clicking phase 304, in response to the user's triggering action on the entry element, the electronic device 110 navigates to the corresponding settings system page (interface 200B). At the backend technology layer, during the settings system loading phase 316, the settings library of the settings system is loaded, including constraint information such as narrative elements and prompts, and injected into the content generation model.

[0072] In the story creation stage 306, users can choose to randomly generate a story or input a custom story idea, and electronic device 110 waits for the result. At the backend technical layer, the story generation stage 318 generates a story outline based on the constraints of the set system and outputs it back to electronic device 110 in a streaming manner. In the story submission stage 308, the user confirms the story content and submits it to the backend. At the backend technical layer, the formatting stage 320 performs content security verification and structured output on the submitted story script, generating a structured script.

[0073] In Preview stage 310, electronic device 110 plays a preview animation and performs a countdown preview. In the backend technology layer, Preview Rendering stage 322 generates animation frames, combines scene elements, and outputs a short preview animation. In One-Click Shooting stage 312, the user triggers the first control to initiate video generation. In the backend technology layer, Video Generation stage 324 performs complete video rendering and generation. In Waiting stage 314, electronic device 110 displays the generation progress and waits to receive the final video. In the backend technology layer, Return stage 326 returns the generated video to electronic device 110.

[0074] In some cases, the aforementioned media content generation process can be executed independently by electronic device 110. For example, electronic device 110 can locally load narrative elements of a set system, generate narrative information using a locally deployed language model, and render and generate first media content using a locally deployed video generation model. The term "video generation model" as used herein refers to a model capable of automatically generating video frame sequences based on text descriptions or structured scripts, which may include, but is not limited to, video generation models based on diffusion models, video generation models based on generative adversarial networks, etc.

[0075] In some cases, the aforementioned media content generation process can be executed independently by server 130. For example, server 130 can load narrative elements of a predefined system, generate narrative information using a large language model deployed on the server side, render and generate first media content using a video generation model deployed on the server side, and transmit the generated first media content to electronic device 110 for presentation.

[0076] In some cases, the aforementioned media content generation process can be jointly executed by electronic device 110 and server 130. For example, electronic device 110 can be responsible for presenting the user interface and receiving user operations, and transmitting user operations and related parameters to server 130. Server 130 can be responsible for loading the configuration system, generating narrative information, verifying content, and rendering and generating media content, and returning the generation results to electronic device 110 for presentation.

[0077] Figure 4 A flowchart of an example process 400 for media content generation under certain circumstances is shown. Process 400 can be implemented at electronic device 110. See below for reference. Figure 4 To describe process 400.

[0078] like Figure 4 As shown, in box 410, electronic device 110 receives a first operation, which instructs content generation under a first setting system. The first setting system includes one or more preset narrative elements. Its interactive presentation can be found above. Figures 2A to 2B The example described.

[0079] In frame 420, electronic device 110 presents narrative information, which describes events that occur within the first established framework. Its interactive presentation can be found above. Figure 2D The example described.

[0080] In box 430, electronic device 110, based on a second operation, presents first media content, which is generated based on narrative information. Its interactive presentation can be found above. Figures 2E to 2F The example described.

[0081] In this way, users can complete the entire process from narrative information generation to media content generation with fewer steps based on a preset system, reducing the number of steps and interface jumps required during content creation. Since the narrative elements in the preset system are pre-loaded and serve as constraints for content generation, the server does not need to re-parse and reconstruct the narrative context for each request, thus reducing server computational overhead.

[0082] In some scenarios, the electronic device 110 can present a first interface, which includes descriptive information and at least one element. The descriptive information is used to display one or more narrative elements, and the at least one element corresponds to at least one generation mode. The device can also receive a first operation on the first interface, which is triggered by one of the at least one elements. Specific interactive presentations can be found above. Figure 2B The example described illustrates this. In this way, users can intuitively understand the settings system and select the generation mode within a single interface, reducing the number of interface jumps.

[0083] In some scenarios, at least one generation mode may include at least one of the following: a first generation mode, corresponding to content generation without additional information; a second generation mode, corresponding to user-defined content generation; and a third generation mode, corresponding to content generation by adjusting at least one of one or more narrative elements. Specific interactive presentations can be found above. Figure 2B The example described illustrates this approach. In this way, users can flexibly choose from multiple generation modes, reducing exploration steps. Since the backend generation pipelines corresponding to different generation modes can be pre-configured, the server can directly call the corresponding generation pipeline, reducing computational overhead and initialization latency.

[0084] In some cases, narrative information can be related to the generation pattern of the first action instruction. For specific interactive presentation details, please refer to the above text. Figures 2B to 2D The example described illustrates how narrative information can be automatically adapted to the user-selected generation mode. Since the mapping between generation modes and generation strategies can be determined locally on the client side, the number of end-to-cloud negotiation rounds and the amount of communication data are reduced.

[0085] In some cases, the electronic device 110 can generate content and present narrative information in response to a first operational instruction without additional information. This narrative information is generated based on a first predefined system. For specific interactive presentation details, please refer to the above. Figure 2C The example described illustrates this. In this way, users can obtain narrative information without entering additional information, reducing the number of steps required. Because the narrative information is returned in a streaming manner, electronic devices can begin rendering as soon as they receive partial information, shortening the first byte time and reducing the client's main thread blocking time.

[0086] In some cases, the electronic device 110 can also receive a third operation instructing the updating of narrative information; and present the updated narrative information, wherein the first media content is generated based on the updated narrative information. Specific interactive presentations can be found above. Figure 2C The example described illustrates this. In this way, users can iteratively adjust narrative information in place, reducing the number of interface transitions.

[0087] In some scenarios, the electronic device 110 can generate user-defined content in response to a first operation instruction, present a first input area, receive first input in the first input area, and present narrative information in response to the first input, the narrative information conforming to a first setting system and the first input. Specific interactive presentations can be found above. Figure 2D The example described illustrates how this approach allows users to obtain creatively integrated narrative information with minimal input, reducing the number of steps required.

[0088] In some scenarios, electronic device 110 may generate content by adjusting narrative elements in response to a first operation instruction, present a second input area, receive second input in the second input area, and, in response to the second input, present narrative information having adjusted narrative elements. Specific interactive presentations can be found above. Figure 2B The example described illustrates this. In this way, users can selectively adjust narrative elements while preserving the core framework, reducing the number of steps required. Since unadjusted narrative elements can reuse cached data, server computational overhead and the amount of data transferred are reduced.

[0089] In some scenarios, the electronic device 110 can present a second interface, which includes one or more entry elements; receive a fourth operation triggered by a first entry element; and, in response to the fourth operation, present the first interface. Specific interactive presentation details can be found above. Figure 2A The example described illustrates this. In this way, users can access the settings page with a single trigger, reducing navigation steps. Since the settings information can be pre-loaded, there's no need to request the server again upon triggering, reducing the number of data requests and response latency for end-to-cloud communication.

[0090] In some cases, electronic device 110 may respond to a second operation by presenting at least one of summary information and preview information on a third interface. Specific interactive presentation can be found above. Figure 2E The example described illustrates this. In this way, users can preview the effect before triggering full generation, reducing the number of regeneration operations. Since the preview only renders a small number of video frames, rendering overhead is significantly reduced, lowering server computing resource consumption and cloud-edge transmission bandwidth usage.

[0091] In some scenarios, the electronic device 110 can respond to an operation on the first control by displaying progress information, which includes multiple sub-progress items corresponding to different generation stages; and respond to the completion of the generation process by displaying the first media content. For specific interactive presentation details, please refer to the above. Figure 2F The example described illustrates this. In this way, users can track the generation progress in real time, reducing the need for repeated refreshes.

[0092] In some cases, the visual style of the first media content can correspond to the visual style of the second media content, and the first setting system is generated based on the second media content. In this way, the generated media content automatically inherits the visual style of the original content. Since the visual style parameters have been pre-extracted and stored, the video generation model can directly load the pre-stored style parameters, reducing server computational overhead and video generation latency.

[0093] A corresponding apparatus for implementing the above methods or processes is also provided.

[0094] Figure 5 A block diagram of a media content generation apparatus 500 under several scenarios is shown. Apparatus 500 can be implemented as or included in electronic device 110. The various modules / components in apparatus 500 can be implemented by hardware, software, firmware, or any combination thereof.

[0095] like Figure 5 As shown, the device 500 includes a receiving module 510 configured to receive a first operation, the first operation instructing content generation under a first setting system, the first setting system including one or more preset narrative elements; a first presentation module 520 configured to present narrative information describing events occurring under the first setting system; and a second presentation module 530 configured to present first media content based on a second operation, the first media content being generated based on the narrative information.

[0096] In some cases, the receiving module 510 may also be configured to present a first interface, the first interface including descriptive information and at least one element, the descriptive information being used to display one or more narrative elements, the at least one element corresponding to at least one generation mode; and to receive a first operation on the first interface, the first operation being triggered on one of the at least one elements.

[0097] In some cases, at least one generation mode may include at least one of the following: a first generation mode, corresponding to content generation without additional information; a second generation mode, corresponding to user-defined content generation; and a third generation mode, corresponding to content generation by adjusting at least one of one or more narrative elements.

[0098] In some cases, narrative information can be related to the generation pattern of the first operational instruction.

[0099] In some cases, the first presentation module 520 may also be configured to generate content and present narrative information without additional information in response to a first operation instruction. The narrative information is generated based on a first setting system.

[0100] In some cases, the receiving module 510 may also be configured to receive a third operation that indicates updating the narrative information; and the first presentation module 520 may also be configured to present the updated narrative information, wherein the first media content is generated based on the updated narrative information.

[0101] In some cases, the first presentation module 520 may also be configured to generate user-defined content in response to a first operation instruction and present a first input area; the receiving module 510 may also be configured to receive a first input in the first input area, the first input being used to summarize narrative information; and the first presentation module 520 may also be configured to present narrative information in response to the first input, the narrative information conforming to a first setting system and the first input.

[0102] In some cases, the first presentation module 520 may also be configured to generate content by adjusting narrative elements in response to a first operation instruction, and present a second input area; the receiving module 510 may also be configured to receive a second input in the second input area, the second input indicating adjustment of narrative elements; and the first presentation module 520 may also be configured to present narrative information having adjusted narrative elements in response to the second input.

[0103] In some cases, the first presentation module 520 may also be configured to present a second interface, which includes one or more entry elements; the receiving module 510 may also be configured to receive a fourth operation triggered by the first entry element; and the first presentation module 520 may also be configured to present the first interface in response to the fourth operation.

[0104] In some cases, the second presentation module 530 may also be configured to, in response to the second operation, present at least one of summary information and preview information in a third interface, wherein the summary information is used to summarize the narrative information and the preview information is used to display a portion of the first media content.

[0105] In some cases, the second presentation module 530 can also be configured to present progress information in response to an operation on the first control, the progress information including multiple sub-progress items corresponding to different generation stages; and to present the first media content in response to the end of the generation process.

[0106] In some cases, the visual style of the first media content can correspond to the visual style of the second media content, and the first setting system is generated based on the second media content.

[0107] The modules included in device 500 can be implemented in various ways, including software, hardware, firmware, or any combination thereof. In some cases, one or more modules can be implemented using software and / or firmware, such as machine-executable instructions stored on a storage medium. In addition to or as an alternative to machine-executable instructions, some or all of the units in device 500 can be implemented at least partially by one or more hardware logic components. By way of example and not limitation, exemplary types of hardware logic components that can be used include field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard parts (ASSPs), systems on a chip (SOCs), complex programmable logic devices (CPLDs), and so on.

[0108] Figure 6 A block diagram of an electronic device 600 in which one or more examples may be implemented is shown. It should be understood that... Figure 6 The electronic device 600 shown is merely exemplary and should not be construed as limiting the functionality and scope of the examples described herein. Figure 6 The illustrated electronic device 600 can be used to implement the electronic device 110 discussed above.

[0109] like Figure 6 As shown, electronic device 600 is in the form of a general-purpose electronic device. Components of electronic device 600 may include, but are not limited to, one or more processing units or processors 610, memory 620, storage device 630, one or more communication units 640, one or more input devices 650, and one or more output devices 660. Processor 610 may be a physical or virtual processor and is capable of performing various processes according to programs stored in memory 620. In a multiprocessor system, multiple processors execute computer-executable instructions in parallel to improve the parallel processing capability of electronic device 600.

[0110] Electronic device 600 typically includes multiple computer storage media. Such media can be any accessible media that is accessible to electronic device 600, including but not limited to volatile and non-volatile media, removable and non-removable media. Memory 620 can be volatile memory (e.g., registers, cache, random access memory (RAM)), non-volatile memory (e.g., read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof). Storage device 630 can be removable or non-removable media and can include machine-readable media, such as flash drives, disks, or any other media that can be used to store information and / or data and can be accessed within electronic device 600.

[0111] Electronic device 600 may further include additional removable / non-removable, volatile / non-volatile storage media. Although not explicitly stated... Figure 6 As shown, disk drives for reading from or writing to removable, non-volatile disks (e.g., "floppy disks") and optical disk drives for reading from or writing to removable, non-volatile optical disks can be provided. In these cases, each drive can be connected to a bus (not shown) via one or more data media interfaces. Memory 620 may include computer program product 625 having one or more program modules configured to perform various methods or actions of various examples.

[0112] The communication unit 640 enables communication with other electronic devices via a communication medium. Additionally, the functionality of the components of the electronic device 600 can be implemented using a single computing cluster or multiple computing machines capable of communicating via communication connections. Therefore, the electronic device 600 can operate in a networked environment using logical connections to one or more other servers, networked personal computers, or another network node.

[0113] Input device 650 can be one or more input devices, such as a mouse, keyboard, trackball, etc. Output device 660 can be one or more output devices, such as a monitor, speaker, printer, etc. Electronic device 600 can also communicate with one or more external devices (not shown) via communication unit 640 as needed. These external devices include storage devices, display devices, etc., and can communicate with one or more devices that enable user interaction with electronic device 600, or with any device that enables electronic device 600 to communicate with one or more other electronic devices (e.g., network card, modem, etc.). Such communication can be performed via an input / output (I / O) interface (not shown).

[0114] A computer-readable storage medium is provided that stores computer-executable instructions thereon, wherein the computer-executable instructions are executed by a processor to implement the methods described above. A computer program product is also provided, which is tangibly stored on a non-transitory computer-readable medium and includes computer-executable instructions, which are executed by a processor to implement the methods described above.

[0115] The flowcharts and / or block diagrams of the methods, apparatus, devices, and computer program products referred to herein describe various aspects. It should be understood that each block of the flowcharts and / or block diagrams, as well as combinations of blocks in the flowcharts and / or block diagrams, can be implemented by computer-readable program instructions.

[0116] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processor of the computer or other programmable data processing apparatus, they create means for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner; thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0117] Computer-readable program instructions can be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions that execute on the computer, other programmable data processing apparatus, or other device to perform the functions / actions specified in one or more boxes of a flowchart and / or block diagram.

[0118] The flowcharts and block diagrams in the accompanying figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products under various scenarios. In this respect, each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction, which contains one or more executable instructions for implementing the specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than those shown in the figures. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0119] Various examples have been described above. The foregoing descriptions are exemplary and not exhaustive, nor are they limited to the disclosed implementations. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described implementations. The terminology used herein is chosen to best explain the principles, practical applications, or improvements to technology in the market, or to enable others skilled in the art to understand the various implementations disclosed herein.

Claims

1. A method for generating media content, comprising: Receive a first operation, the first operation instructing content generation under a first setting system, the first setting system including one or more preset narrative elements; Presenting narrative information, which describes events that occur under the first set system; as well as Based on the second operation, first media content is presented, which is generated based on the narrative information.

2. The method of claim 1, wherein receiving the first operation comprises: A first interface is presented, which includes descriptive information and at least one element. The descriptive information is used to display the one or more narrative elements, and the at least one element corresponds to at least one generation mode. as well as The first operation is received on the first interface, and the first operation is triggered on one of the at least one elements.

3. The method of claim 2, wherein the at least one generation mode comprises at least one of the following: The first generation mode corresponds to content generation without any additional information; The second generation mode corresponds to generating user-defined content; as well as The third generation mode corresponds to content generation by adjusting at least one of the one or more narrative elements.

4. The method of claim 1, wherein the narrative information is related to the generation mode of the first operation instruction.

5. The method of claim 4, wherein presenting the narrative information comprises: In response to the first operation instruction, content is generated without additional information, and the narrative information is presented, which is generated based on the first setting system.

6. The method of claim 5, further comprising: Receive a third operation, the third operation instructing the updating of the narrative information; as well as The updated narrative information is presented, wherein the first media content is generated based on the updated narrative information.

7. The method of claim 4, wherein presenting the narrative information comprises: In response to the first operation instruction, user-defined content is generated, and the first input area is presented; A first input is received in the first input area, the first input being used to summarize the narrative information; as well as In response to the first input, the narrative information is presented, which conforms to the first setting system and the first input.

8. The method of claim 4, wherein presenting the narrative information comprises: In response to the first operation instruction, content generation is performed by adjusting at least one of the one or more narrative elements, and a second input area is presented; A second input is received in the second input area, the second input indicating an adjustment to at least one of the one or more narrative elements; as well as In response to the second input, the narrative information is presented, the narrative information having the at least one adjusted narrative element.

9. The method according to claim 2, further comprising: A second interface is presented, which includes one or more entry elements, each of which corresponds to one or more setting systems, and the one or more setting systems include the first setting system. Receive a fourth operation, which is triggered on a first entry element among the one or more entry elements, and the first entry element corresponds to the first set system; as well as In response to the fourth operation, the first interface is displayed.

10. The method according to claim 1, further comprising: In response to the second operation, at least one of summary information and preview information is presented in a third interface, the summary information being used to summarize the narrative information and the preview information being used to display a portion of the first media content.

11. The method of claim 10, wherein the third interface further includes a first control, and presenting the first media content includes: In response to the operation of the first control, progress information is presented. The progress information is used to display the generation process of the first media content. The progress information includes multiple sub-progress items, which correspond to different generation stages of the first media content. as well as Upon completion of the generation process, the first media content is presented.

12. A media content generation device, comprising: The receiving module is configured to receive a first operation, the first operation instructing content generation under a first setting system, the first setting system including one or more preset narrative elements; The first presentation module is configured to present narrative information, which describes events that occur under the first set system. as well as The second presentation module is configured to present first media content based on a second operation, wherein the first media content is generated based on the narrative information.

13. An electronic device, comprising: At least one processing unit; as well as At least one memory, coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, which, when executed by the at least one processing unit, cause the electronic device to perform the method according to any one of claims 1 to 11.

14. A computer-readable storage medium having a computer program stored thereon, the computer program being executable by a processor to implement the method according to any one of claims 1 to 11.

15. A computer program product tangibly stored in a computer storage medium and comprising computer-executable instructions that, when executed by a device, cause the device to perform the method according to any one of claims 1 to 11.

Images