Video generation method and system, computer equipment and storage medium
By using After Effects video template library and Stable Diffusion image generation model in financial marketing, combined with AI and template production, the problems of high cost, inflexible methods and lack of targeted video generation in the existing technology are solved, and efficient Personalized video generation meets the diverse needs of financial marketing.
Patent Information
- Application Number
- CN202411101747.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-12
- Publication Date
- 2024-12-06
AI Technical Summary
The existing video generation methods have high costs, insufficient flexibility, and lack of targetedness in financial marketing, which is difficult to meet the marketing needs of diversified financial products.
By receiving the selection instructions of the target user, selecting the video template and the original material, and using the preset material generation model to generate the target material, replacing the material in the video template, and generating the corresponding target video. In the specific implementation, the After Effects video template library and Stable Diffusion image generation model are used, combined with AI and template production, and video generation is achieved.
It reduces the cost of video production, shortens production time, improves the personalization and flexibility of videos, can quickly respond to market changes, enriches video materials, and meets the diversified needs of financial marketing.
Smart Images

Figure CN119094852A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of information processing technology, and in particular to a video generation method, system, computer equipment and non-volatile computer-readable storage medium. Background Art
[0002] At present, with the rapid development of mobile Internet, the financial industry is facing unprecedented market opportunities and challenges. Under the background of digital transformation, financial companies are paying more and more attention to brand promotion and product marketing through short video platforms. Short videos have become the new favorite of financial marketing due to their fast transmission speed, wide coverage and high user stickiness. However, the existing short video generation scheme has some shortcomings, which greatly limits the efficiency and effectiveness of financial marketing; the shortcomings are as follows:
[0003] 1. Templated production: Traditional templated short video production usually involves fixed templates, which limits the personalization and innovation of the video; templated videos often lack pertinence and appeal, and are difficult to meet the diverse marketing needs of financial products;
[0004] 2. Real-life shooting and production: Although real-life shooting can provide a sense of reality, it is costly, has a long production cycle, and has high requirements for venues, actors, and shooting equipment. In addition, real-life shooting has limited ability to quickly respond to market changes;
[0005] 3. Animation production: Although animated videos can provide more creative space, animation production also faces the problem of high cost and high professional skills requirements; animators need to invest a lot of time to design and produce animations, which is not conducive to financial companies to quickly launch marketing activities.
[0006] That is, the video generation method in the prior art has the problems of high cost, inflexibility, and lack of specificity.
[0007] Therefore, the existing technology still needs to be improved and developed. Summary of the invention
[0008] In view of the above-mentioned deficiencies in the prior art, the object of the present invention is to provide a video generation method, system, computer device and non-volatile computer-readable storage medium that can be used in financial technology or other related fields, aiming to solve the problems of high cost, inflexible method and lack of specificity in the video generation method in the prior art.
[0009] In order to achieve the above object, the present invention adopts the following technical solutions:
[0010] A video generation method, comprising:
[0011] receiving a first selection instruction from a target user, and selecting a target video template from a preset video template library according to the first selection instruction;
[0012] receiving a second selection instruction from the target user, and selecting an original material to be replaced from the target video template according to the second selection instruction;
[0013] Inputting the original material into a preset material generation model to generate corresponding target material;
[0014] The original material in the target video template is replaced with the target material to generate a corresponding target video.
[0015] In a further technical solution, the video generation method, wherein the receiving of a first selection instruction of a target user and selecting a target video template from a preset video template library according to the first selection instruction, comprises:
[0016] Pre-build video template library based on target video software;
[0017] A first selection instruction of a target user is received, and a target video template is selected from the video template library according to the first selection instruction.
[0018] In a further technical solution, the video generation method, wherein the step of inputting the original material into a preset material generation model to generate corresponding target material, comprises:
[0019] Pre-build material generation model;
[0020] The original material is input into the material generation model to generate corresponding target material.
[0021] In a further technical solution, the video generation method, wherein the receiving the second selection instruction of the target user, selecting the original material to be replaced in the target video template according to the second selection instruction,
[0022] The original material includes text and / or pictures.
[0023] In a further technical solution, in the video generation method, when the original material is text, the material generation model is a text generation model;
[0024] When the original material is a picture, the material generation model is a picture generation model.
[0025] In a further technical solution, in the video generation method, the image generation model is Stable Diffusion.
[0026] In a further technical solution, the video generation method, wherein the video template library is pre-built based on the target video software,
[0027] Wherein, the target video software is After Effects.
[0028] A video generation system, comprising:
[0029] A first selection module, configured to receive a first selection instruction from a target user, and select a target video template from a preset video template library according to the first selection instruction;
[0030] A second selection module, configured to receive a second selection instruction from the target user, and select an original material to be replaced from the target video template according to the second selection instruction;
[0031] A first generation module, used for inputting the original material into a preset material generation model to generate corresponding target material;
[0032] The second generating module is used to replace the original material in the target video template with the target material to generate a corresponding target video.
[0033] A computer device, wherein the computer device comprises at least one processor; and
[0034] a memory communicatively connected to the at least one processor; wherein,
[0035] The memory stores a computer program that can be executed by the at least one processor. When the computer program is executed by the at least one processor, any of the above-mentioned video generation methods can be implemented.
[0036] A non-volatile computer-readable storage medium stores a computer program, wherein the computer program, when executed by at least one processor, can implement any of the above-mentioned video generation methods.
[0037] Compared with the prior art, the present invention provides a video generation method, system, computer device and non-volatile computer-readable storage medium, wherein the method comprises: receiving a first selection instruction of a target user, and selecting a target video template from a preset video template library according to the first selection instruction; receiving a second selection instruction of the target user, and selecting the original material to be replaced from the target video template according to the second selection instruction; inputting the original material into a preset material generation model to generate a corresponding target material; replacing the original material in the target video template with the target material to generate a corresponding target video. In this way, the method of the present invention can solve the problems of high cost, inflexible method and lack of pertinence in the video generation method in the prior art. BRIEF DESCRIPTION OF THE DRAWINGS
[0038] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0039] Figure 1 A schematic flow chart of a video generation method provided by an embodiment of the present invention.
[0040] Figure 2 A schematic diagram of functional modules of a video generation system provided by an embodiment of the present invention.
[0041] Figure 3 A schematic diagram of the hardware structure of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION
[0042] In order to make the purpose, technical solution and effect of the present invention clearer and more specific, the present invention is further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.
[0043] In the description of the present invention, the terms "include", "including", "have", "contain", etc. are all open terms, which mean including but not limited to. The descriptions with reference to the terms "one embodiment", "a specific embodiment", "some embodiments", "for example", etc. mean that the specific features, structures or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures or characteristics described may be combined in a suitable manner in any one or more embodiments or examples. The order of steps involved in each embodiment is used to schematically illustrate the implementation of the present application, and the order of steps therein is not limited and can be appropriately adjusted as needed.
[0044] Various non-limiting embodiments of the present invention are described in detail below in conjunction with the accompanying drawings.
[0045] At present, with the rapid development of mobile Internet, the financial industry is facing unprecedented market opportunities and challenges. Under the background of digital transformation, financial companies are paying more and more attention to brand promotion and product marketing through short video platforms. Short videos have become the new favorite of financial marketing due to their fast transmission speed, wide coverage and high user stickiness. However, the existing short video generation scheme has some shortcomings, which greatly limits the efficiency and effectiveness of financial marketing; the shortcomings are as follows:
[0046] 1. Templated production: Traditional templated short video production usually involves fixed templates, which limits the personalization and innovation of the video; templated videos often lack pertinence and appeal, and are difficult to meet the diverse marketing needs of financial products;
[0047] 2. Real-life shooting and production: Although real-life shooting can provide a sense of reality, it is costly, has a long production cycle, and has high requirements for venues, actors, and shooting equipment. In addition, real-life shooting has limited ability to quickly respond to market changes;
[0048] 3. Animation production: Although animated videos can provide more creative space, animation production also faces the problem of high cost and high professional skills requirements; animators need to invest a lot of time to design and produce animations, which is not conducive to financial companies to quickly launch marketing activities.
[0049] That is, the video generation method in the prior art has the problems of high cost, inflexibility, and lack of specificity.
[0050] To solve the above problems, see Figure 1 The embodiment of the present invention provides a video generation method, wherein the method comprises the steps of:
[0051] S100, receiving a first selection instruction from a target user, and selecting a target video template from a preset video template library according to the first selection instruction;
[0052] S200, receiving a second selection instruction from the target user, and selecting an original material to be replaced from the target video template according to the second selection instruction;
[0053] S300, inputting the original material into a preset material generation model to generate corresponding target material;
[0054] S400: Replace the original material in the target video template with the target material to generate a corresponding target video.
[0055] Furthermore, the video generation method, wherein the step S100, receiving a first selection instruction of a target user, and selecting a target video template from a preset video template library according to the first selection instruction, comprises:
[0056] Pre-build video template library based on target video software;
[0057] A first selection instruction of a target user is received, and a target video template is selected from the video template library according to the first selection instruction.
[0058] Furthermore, in the video generation method, the video template library is pre-built based on the target video software,
[0059] Wherein, the target video software is After Effects.
[0060] In specific implementation, in this embodiment, based on the target video software, a video template library is pre-built; a first selection instruction of a target user is received, and a target video template is selected from the video template library according to the first selection instruction; wherein the target video software is After Effects (i.e., Adobe After Effects);
[0061] The specific implementation process is as follows:
[0062] 1) Design and creation of video templates
[0063] Use After Effects' professional animation and visual effects tools to design a series of video templates (i.e., video template libraries); these video templates include pre-designed animation paths, special effects, text styles, color schemes, and replaceable placeholders;
[0064] 2) Saving and managing video templates
[0065] Save the designed video template as an After Effects project file (.AEP format) and store it in a specified folder on the computer or server; to facilitate user retrieval, you can classify the video template by type, theme or usage scenario, and establish a corresponding directory structure;
[0066] 3) Implementation of the user interface
[0067] Develop a user interface, which can be a stand-alone application or integrated into the system corresponding to the video generation method, to display an overview of the video template library and allow users to browse, search, and preview templates; the user interface should provide intuitive navigation and filtering tools to help users quickly find the templates they need;
[0068] 4) Receive user instructions
[0069] Receive the first selection instruction of the target user through the user interface; the target user can select the target video template they want by clicking on the previewed template, entering a keyword to search, or using classification filtering;
[0070] receiving a first selection instruction of a target user, and selecting a target video template from the video template library according to the first selection instruction;
[0071] 5) Video template selection and loading
[0072] When the target user selects a template (i.e., a target video template), the system (the system corresponding to the video generation method) receives a corresponding instruction (a first selection instruction) and calls a corresponding After Effects project file from a storage location; then, the template is loaded into the After Effects software, ready for the next step of personalized editing or direct output;
[0073] 6) Personalized editing and output
[0074] Users can perform personalized editing on the selected template (i.e. the target video template) in After Effects, such as changing text content, replacing the material in the placeholder, adjusting animation effects, etc. After editing, preview and confirm the video;
[0075] Once the user is satisfied, the video can be output in different formats and resolutions as needed, and then rendered and exported for further use or sharing;
[0076] Through the above process, the whole process from the construction of the video template library to the user's selection of the target video template is realized, aiming to provide users with a simple and efficient video production experience; that is, the above process fully utilizes the powerful functions of After Effects, and through the combination of the user interface and the system, provides users with an efficient and convenient video template selection and editing process;
[0077] Among them, AE (After Effects) video template is a video template made with Adobe software, which can provide users with various pre-made video effects and special effects, saving users a lot of time and energy, allowing users to quickly make high-quality videos; the advantage of AE video template is that it can provide users with high-quality and cool video special effects without the need for professional video production skills; AE video template has a wide range of applicability and can be used in various video production scenarios, such as film and television production, marketing and promotion, etc.
[0078] Furthermore, in the video generation method, in step S200, a second selection instruction of the target user is received, and the original material to be replaced is selected from the target video template according to the second selection instruction.
[0079] The original material includes text and / or pictures.
[0080] Furthermore, in the video generation method, the step S300 of inputting the original material into a preset material generation model to generate corresponding target material includes:
[0081] Pre-build material generation model;
[0082] The original material is input into the material generation model to generate corresponding target material.
[0083] Furthermore, in the video generation method, when the original material is text, the material generation model is a text generation model;
[0084] When the original material is a picture, the material generation model is a picture generation model.
[0085] Furthermore, in the video generation method, the image generation model is Stable Diffusion.
[0086] In specific implementation, in this embodiment, a second selection instruction of the target user is received, and the original material to be replaced is selected from the target video template according to the second selection instruction, wherein the original material includes text and / or picture; a material generation model is pre-built; the original material is input into the material generation model to generate the corresponding target material; when the original material is text, the material generation model is a text generation model; when the original material is a picture, the material generation model is a picture generation model; the picture generation model is Stable Diffusion;
[0087] The specific implementation process is as follows:
[0088] 1) User selection and instruction reception
[0089] Open the target video template in After Effects; receive second selection instructions from the target user through the user interface, and the instructions indicate the original materials to be replaced, including texts and / or pictures;
[0090] 2) Original material identification and selection
[0091] According to the user's second selection instruction, the original material to be replaced is identified and selected in the target video template of After Effects; if the original material is text, the text layer is selected; if the original material is a picture, the layer containing the picture is selected;
[0092] 3) Selection of material generation model
[0093] Based on the type of raw material selected, decide which pre-built material generation model to use; if the material is text, use a text generation model (such as GPT, BERT, etc.) to generate new text content; if the material is an image, use Stable Diffusion as an image generation model to generate new images;
[0094] Among them, Stable Diffusion is an AI painting generation tool;
[0095] 4) Generation of target materials
[0096] For text materials, new text content is output through the text generation model based on business needs or content provided by users;
[0097] For image materials, provide descriptive text prompts to Stable Diffusion according to business needs or user requirements, and generate new images based on these prompts. Of course, when the generated new images have various backgrounds, you can use PS or SAM models to cut out the required parts of the images to obtain PNG images with transparent backgrounds.
[0098] Through the above process, the process from receiving user instructions to selecting original materials and generating corresponding target materials is realized, providing a content basis for the subsequent generation of target videos.
[0099] Further, in the video generation method, in step S400, the original material in the target video template is replaced with the target material to generate a corresponding target video;
[0100] In specific implementation, in this embodiment, the original material in the target video template is replaced with the target material to generate a corresponding target video; wherein the specific implementation process is roughly as follows:
[0101] 1) Target material preparation
[0102] Make sure the target material has been generated and prepared; if the original material is text, make sure the text generation model has produced new text content; if the original material is an image, make sure the Stable Diffusion model has generated a new image based on the prompt;
[0103] 2) Open the video editing software
[0104] Start After Effects and open the target video template file; this file contains the original video project that needs to replace the material;
[0105] 3) Locate and replace the material
[0106] In After Effects, find the original material that needs to be replaced in the target video template; if the original material is text, select the corresponding text layer; if the original material is a picture, select the layer containing the material;
[0107] Import the newly generated target material into After Effects and place it into the corresponding text layer or layers to replace the original material;
[0108] 4) Adjust and sync with animation
[0109] Make any necessary adjustments to the newly replaced target assets to ensure they are visually consistent with other elements of the target video template; this may include adjusting size, position, color, and animation effects to ensure the new assets are naturally synced with the animations and transitions in the template;
[0110] 5) Review and final rendering
[0111] After the replacement is completed, carefully review the generated target video to ensure that all new materials are correctly integrated into the video and that the overall video is smooth and meets the expected effect;
[0112] Once the user is satisfied, set appropriate video output parameters, such as resolution, bit rate, and format, and then render the video; after rendering is complete, export the final video file;
[0113] 6) Output and Sharing
[0114] Save the exported video file to a designated location and share it with the target audience through appropriate channels, such as uploading to a video sharing platform, embedding on a website, or posting on social media;
[0115] Through the above process, a complete video generation workflow is formed from the identification of original materials, the generation of target materials, to the editing, review and output of the final target video.
[0116] It can be seen from the above method embodiments that the video generation method provided by the present invention at least includes: receiving a first selection instruction of a target user, and selecting a target video template from a preset video template library according to the first selection instruction; receiving a second selection instruction of the target user, and selecting an original material to be replaced from the target video template according to the second selection instruction; inputting the original material into a preset material generation model to generate a corresponding target material; replacing the original material in the target video template with the target material to generate a corresponding target video; and so on. In this way, the method of the present invention can solve the problems of high cost, inflexible method, and lack of pertinence in the video generation method in the prior art.
[0117] Specifically, the video generation method provided in the embodiment of the present invention creatively combines AE video templates and Stable Diffusion image generation. Stable Diffusion is only responsible for generating image materials, while coherent animations are generated through AE templates. In this way, marketing short videos can be quickly generated based on AE templates, and the materials can be greatly enriched.
[0118] The video generation method provided by the embodiment of the present invention combines AI and template production, which can not only greatly save costs and shorten production time, but also greatly enrich the materials for video production; it has at least the following beneficial technical effects:
[0119] 1) The video is made through AE template, so the video will not have the disadvantage of being incoherent. At the same time, the template can be made once and reused multiple times, which is flexible and can reduce costs;
[0120] 2) Based on user needs, Stable Diffusion can be used to generate background images, LOGOs and other materials in a targeted manner, which can not only enrich the image materials, but also quickly generate the target video and shorten the video production time.
[0121] It should be understood that, although the present application provides method operation steps as described in the embodiments or flowcharts, more or less operation steps may be included based on conventional or non-creative labor, and these operation steps are not necessarily performed in sequence according to the embodiment or flowchart. The order of steps listed in the embodiment or flowchart is only one way of executing the order of many steps, and does not represent the only execution order. It should be noted that there is not necessarily a certain order between the above steps. A person of ordinary skill in the art can understand from the description of the embodiment of the present invention that in different embodiments, the above steps may have different execution orders, that is, they may be executed in parallel, or they may be executed in exchange, etc. Moreover, at least a part of the steps in the embodiment or flowchart may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but may be executed at different times, and the execution order of these sub-steps or stages is not necessarily performed in sequence, but may be executed in turn, alternately or synchronously with other steps or at least a part of the sub-steps or stages of other steps.
[0122] Based on the above method embodiment, please refer to Figure 2 Another embodiment of the present invention further provides a video generation system, wherein the system comprises:
[0123] A first selection module 11 is used to receive a first selection instruction from a target user, and select a target video template from a preset video template library according to the first selection instruction;
[0124] A second selection module 12 is used to receive a second selection instruction from the target user, and select the original material to be replaced in the target video template according to the second selection instruction;
[0125] The first generating module 13 is used to input the original material into a preset material generating model to generate corresponding target material;
[0126] The second generating module 14 is used to replace the original material in the target video template with the target material to generate a corresponding target video.
[0127] Furthermore, the video generation system, wherein the receiving of the first selection instruction of the target user and selecting the target video template from a preset video template library according to the first selection instruction, comprises:
[0128] Pre-build video template library based on target video software;
[0129] A first selection instruction of a target user is received, and a target video template is selected from the video template library according to the first selection instruction.
[0130] Furthermore, in the video generation system, the video template library is pre-built based on the target video software.
[0131] Wherein, the target video software is After Effects.
[0132] In specific implementation, in this embodiment, based on the target video software, a video template library is pre-built; a first selection instruction of a target user is received, and a target video template is selected from the video template library according to the first selection instruction; wherein the target video software is After Effects (i.e., Adobe After Effects);
[0133] The specific implementation process is as follows:
[0134] 1) Design and creation of video templates
[0135] Use After Effects' professional animation and visual effects tools to design a series of video templates (i.e., video template libraries); these video templates include pre-designed animation paths, special effects, text styles, color schemes, and replaceable placeholders;
[0136] 2) Saving and managing video templates
[0137] Save the designed video template as an After Effects project file (.AEP format) and store it in a specified folder on the computer or server; to facilitate user retrieval, you can classify the video template by type, theme or usage scenario, and establish a corresponding directory structure;
[0138] 3) Implementation of the user interface
[0139] Develop a user interface, which can be a stand-alone application or integrated into the video generation system, to display an overview of the video template library and allow users to browse, search, and preview templates; the user interface should provide intuitive navigation and filtering tools to help users quickly find the templates they need;
[0140] 4) Receive user instructions
[0141] Receive the first selection instruction of the target user through the user interface; the target user can select the target video template they want by clicking on the previewed template, entering a keyword to search, or using classification filtering;
[0142] receiving a first selection instruction of a target user, and selecting a target video template from the video template library according to the first selection instruction;
[0143] 5) Video template selection and loading
[0144] When the target user selects a template (i.e., the target video template), the system will receive the corresponding instruction (the first selection instruction) and call the corresponding After Effects project file from the storage location; then, the template is loaded into the After Effects software, ready for the next step of personalized editing or direct output;
[0145] 6) Personalized editing and output
[0146] Users can perform personalized editing on the selected template (i.e. the target video template) in After Effects, such as changing text content, replacing the material in the placeholder, adjusting animation effects, etc. After editing, preview and confirm the video;
[0147] Once the user is satisfied, the video can be output in different formats and resolutions as needed, and then rendered and exported for further use or sharing;
[0148] Through the above process, the whole process from the construction of the video template library to the user's selection of the target video template is realized, aiming to provide users with a simple and efficient video production experience; that is, the above process fully utilizes the powerful functions of After Effects, and through the combination of the user interface and the system, provides users with an efficient and convenient video template selection and editing process;
[0149] Among them, AE (After Effects) video template is a video template made with Adobe software, which can provide users with various pre-made video effects and special effects, saving users a lot of time and energy, allowing users to quickly make high-quality videos; the advantage of AE video template is that it can provide users with high-quality and cool video special effects without the need for professional video production skills; AE video template has a wide range of applicability and can be used in various video production scenarios, such as film and television production, marketing and promotion, etc.
[0150] Furthermore, the video generation system, wherein the receiving of the second selection instruction of the target user, selects the original material to be replaced in the target video template according to the second selection instruction,
[0151] The original material includes text and / or pictures.
[0152] Furthermore, in the video generation system, the step of inputting the original material into a preset material generation model to generate corresponding target material comprises:
[0153] Pre-build material generation model;
[0154] The original material is input into the material generation model to generate corresponding target material.
[0155] Furthermore, in the video generation system, when the original material is text, the material generation model is a text generation model;
[0156] When the original material is a picture, the material generation model is a picture generation model.
[0157] Furthermore, in the video generation system, the image generation model is Stable Diffusion.
[0158] In specific implementation, in this embodiment, a second selection instruction of the target user is received, and the original material to be replaced is selected from the target video template according to the second selection instruction, wherein the original material includes text and / or picture; a material generation model is pre-built; the original material is input into the material generation model to generate the corresponding target material; when the original material is text, the material generation model is a text generation model; when the original material is a picture, the material generation model is a picture generation model; the picture generation model is Stable Diffusion;
[0159] The specific implementation process is as follows:
[0160] 1) User selection and instruction reception
[0161] Open the target video template in After Effects; receive second selection instructions from the target user through the user interface, and the instructions indicate the original materials to be replaced, including texts and / or pictures;
[0162] 2) Original material identification and selection
[0163] According to the user's second selection instruction, the original material to be replaced is identified and selected in the target video template of After Effects; if the original material is text, the text layer is selected; if the original material is a picture, the layer containing the picture is selected;
[0164] 3) Selection of material generation model
[0165] Based on the type of raw material selected, decide which pre-built material generation model to use; if the material is text, use a text generation model (such as GPT, BERT, etc.) to generate new text content; if the material is an image, use Stable Diffusion as an image generation model to generate new images;
[0166] Among them, Stable Diffusion is an AI painting generation tool;
[0167] 4) Generation of target materials
[0168] For text materials, new text content is output through the text generation model based on business needs or content provided by users;
[0169] For image materials, provide descriptive text prompts to Stable Diffusion according to business needs or user requirements, and generate new images based on these prompts. Of course, when the generated new images have various backgrounds, you can use PS or SAM models to cut out the required parts of the images to obtain PNG images with transparent backgrounds.
[0170] Through the above process, the process from receiving user instructions to selecting original materials and generating corresponding target materials is realized, providing a content basis for the subsequent generation of target videos.
[0171] Furthermore, in the video generation system, the original material in the target video template is replaced with the target material to generate a corresponding target video;
[0172] In specific implementation, in this embodiment, the original material in the target video template is replaced with the target material to generate a corresponding target video; wherein the specific implementation process is roughly as follows:
[0173] 1) Target material preparation
[0174] Make sure the target material has been generated and prepared; if the original material is text, make sure the text generation model has produced new text content; if the original material is an image, make sure the Stable Diffusion model has generated a new image based on the prompt;
[0175] 2) Open the video editing software
[0176] Start After Effects and open the target video template file; this file contains the original video project that needs to replace the material;
[0177] 3) Locate and replace the material
[0178] In After Effects, find the original material that needs to be replaced in the target video template; if the original material is text, select the corresponding text layer; if the original material is a picture, select the layer containing the material;
[0179] Import the newly generated target material into After Effects and place it into the corresponding text layer or layers to replace the original material;
[0180] 4) Adjust and sync with animation
[0181] Make any necessary adjustments to the newly replaced target assets to ensure they are visually consistent with other elements of the target video template; this may include adjusting size, position, color, and animation effects to ensure the new assets are naturally synced with the animations and transitions in the template;
[0182] 5) Review and final rendering
[0183] After the replacement is completed, carefully review the generated target video to ensure that all new materials are correctly integrated into the video and that the overall video is smooth and meets the expected effect;
[0184] Once the user is satisfied, set appropriate video output parameters, such as resolution, bit rate, and format, and then render the video; after rendering is complete, export the final video file;
[0185] 6) Output and Sharing
[0186] Save the exported video file to a designated location and share it with the target audience through appropriate channels, such as uploading to a video sharing platform, embedding on a website, or posting on social media;
[0187] Through the above process, a complete video generation workflow is formed from the identification of original materials, the generation of target materials, to the editing, review and output of the final target video.
[0188] As can be seen from the above system embodiments, the video generation system provided by the present invention at least includes: receiving a first selection instruction of a target user, and selecting a target video template from a preset video template library according to the first selection instruction; receiving a second selection instruction of the target user, and selecting an original material to be replaced from the target video template according to the second selection instruction; inputting the original material into a preset material generation model to generate a corresponding target material; replacing the original material in the target video template with the target material to generate a corresponding target video; and so on. In this way, the system of the present invention can solve the problems of high cost, inflexible method, and lack of pertinence in the video generation system in the prior art.
[0189] Specifically, the video generation system provided by the embodiment of the present invention creatively combines AE video templates and Stable Diffusion image generation. Stable Diffusion is only responsible for generating image materials, while coherent animations are generated through AE templates. In this way, marketing short videos can be quickly generated based on AE templates, and the materials can be greatly enriched.
[0190] The video generation system provided by the embodiment of the present invention combines AI and template production, which can not only save a lot of costs and shorten production time, but also greatly enrich the materials for video production; it has at least the following beneficial technical effects:
[0191] 1) The video is made through AE template, so the video will not have the disadvantage of being incoherent. At the same time, the template can be made once and reused multiple times, which is flexible and can reduce costs;
[0192] 2) Based on user needs, Stable Diffusion can be used to generate background images, LOGOs and other materials in a targeted manner, which can not only enrich the image materials, but also quickly generate the target video and shorten the video production time.
[0193] Based on the above method embodiment, please refer to Figure 3 Another embodiment of the present invention further provides a computer device, wherein the computer device 10 includes:
[0194] memory 120 and one or more processors 110, Figure 3 A processor 110 is used as an example for description. The processor 110 and the memory 120 may be connected via a communication bus or other means. Figure 3 The example of connection via a communication bus is taken as an example.
[0195] The processor 110 is used to complete various control logics of the computer device 10. It can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), a single-chip microcomputer, an ARM (Acorn RISC Machine) or other programmable logic device, a discrete gate or transistor logic, a discrete hardware component, or any combination of these components. In addition, the processor 110 can also be any traditional processor, microprocessor or state machine. The processor 110 can also be implemented as a combination of computing devices, for example, a combination of a DSP and a microprocessor, a plurality of microprocessors, one or more microprocessors combined with a DSP, or any other such configuration.
[0196] The memory 120 is a non-volatile computer-readable storage medium that can be used to store non-volatile software programs, non-volatile computer executable programs and modules, such as the computer program corresponding to the video generation method in the embodiment of the present invention. The processor 110 executes various functional applications and data processing of the computer device 10 by running the non-volatile software programs, instructions and units stored in the memory 120, that is, the video generation method in the above method embodiment is implemented.
[0197] The memory 120 may include a program storage area and a data storage area, wherein the program storage area may store an application required for operating the device or at least one function; the data storage area may store data created according to the use of the computer device 10, etc. In addition, the memory 120 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some embodiments, the memory 120 may optionally include a memory remotely arranged relative to the processor 110, and these remote memories may be connected to the computer device 10 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.
[0198] One or more units are stored in the memory 120, and when executed by one or more processors 110, a video generation method as in any of the above method embodiments can be implemented, for example, the video generation method described above can be implemented. Figure 1 The method comprises steps S100 to S400.
[0199] It can be seen from the above computer device embodiments that the computer device provided by the present invention can at least achieve: receiving a first selection instruction from a target user, and selecting a target video template from a preset video template library according to the first selection instruction; receiving a second selection instruction from the target user, and selecting an original material to be replaced from the target video template according to the second selection instruction; inputting the original material into a preset material generation model to generate a corresponding target material; replacing the original material in the target video template with the target material to generate a corresponding target video; etc. In this way, the computer device of the present invention can solve the problems of high cost, inflexible method, and lack of pertinence in the video generation device in the prior art.
[0200] Specifically, the computer device provided by the embodiment of the present invention creatively combines AE video templates and StableDiffusion image generation. Stable Diffusion is only responsible for generating image materials, while coherent animations are generated through AE templates. In this way, marketing short videos can be quickly generated based on AE templates, and the materials can be greatly enriched.
[0201] The computer device provided by the embodiment of the present invention, combined with AI and template production, can not only greatly save costs and shorten production time, but also greatly enrich the materials for video production; it has at least the following beneficial technical effects:
[0202] 1) The video is made through AE template, so the video will not have the disadvantage of being incoherent. At the same time, the template can be made once and reused multiple times, which is flexible and can reduce costs;
[0203] 2) Based on user needs, Stable Diffusion can be used to generate background images, LOGOs and other materials in a targeted manner, which can not only enrich the image materials, but also quickly generate the target video and shorten the video production time.
[0204] Those skilled in the art will understand that Figure 3 The hardware structure diagram shown in the figure is only a schematic diagram of a partial structure related to the solution of the present invention, and does not constitute a limitation on the computer device to which the solution of the present invention is applied. The specific computer device may include more components than those shown in the figure, or combine certain components, or have a different arrangement of components.
[0205] Based on the above method embodiments, another embodiment of the present invention further provides a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium stores a computer program, and when the computer program is executed by at least one processor, the video generation method in any of the above method embodiments can be implemented, for example, the video generation method described above can be implemented. Figure 1The method comprises steps S100 to S400.
[0206] As an example, the non-volatile storage medium can include a read-only memory (ROM), a programmable ROM (PROM), an electrically programmable ROM (EPROM), an electrically erasable ROM (EEPROM), or a flash memory. Volatile memory can include a random access memory (RAM) as an external cache memory. By way of illustration and not limitation, RAM can be obtained in many forms such as synchronous RAM (SRAM), dynamic RAM, (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), Synch link DRAM (SLDRAM), and direct Rambus RAM (DRRAM). The disclosed memory components or memories of the operating environment described herein are intended to include one or more of these and / or any other suitable types of memory.
[0207] Based on the above method embodiments, another embodiment of the present invention further provides a computer program product, the computer program product includes a computer program stored on a non-volatile computer-readable storage medium, the computer program includes program instructions, when the program instructions are executed by a processor, the video generation method in any of the above method embodiments can be implemented, for example, the above described Figure 1 The method comprises steps S100 to S400.
[0208] The embodiments described above are merely illustrative, in which the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0209] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a general hardware platform, and of course can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the relevant technology can be embodied in the form of a software product, and the computer software product can exist in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods of each embodiment or some parts of the embodiment.
[0210] Conditional language such as "can," "can," "might," or "may," unless specifically stated otherwise or otherwise understood within the context as used, is generally intended to convey, among other things, that a particular embodiment can include (while other embodiments do not) a particular feature, element, and / or operation. Thus, such conditional language is also generally intended to imply that a feature, element, and / or operation is required for one or more embodiments anyway or that one or more embodiments must include logic for determining, with or without input or prompting, whether such features, elements, and / or operations are included or will be performed in any particular embodiment.
[0211] What has been described herein, in this specification and in the accompanying drawings includes examples that can provide a method, system, computer device, and non-volatile computer-readable storage medium for video generation. Of course, it is not possible to describe every conceivable combination of elements and / or methods for the purpose of describing the various features of the present disclosure, but it can be recognized that many other combinations and permutations of the disclosed features are possible. Therefore, it is obvious that various modifications can be made to the present disclosure without departing from the scope or spirit of the present disclosure, but all these various modifications should belong to the scope of protection of the claims attached to the present invention. In addition, or in an alternative, other embodiments of the present disclosure may be obvious from consideration of the present specification and the accompanying drawings and from the practice of the present disclosure as presented herein. It is intended that the examples proposed in the present specification and the accompanying drawings are considered to be illustrative and not restrictive in all respects. Although specific terms are used herein, they are used in a general and descriptive sense and are not used for limiting purposes.
Claims
1. A video generation method, characterized in that: include: receiving a first selection instruction from a target user, and selecting a target video template from a preset video template library according to the first selection instruction; receiving a second selection instruction from the target user, and selecting an original material to be replaced from the target video template according to the second selection instruction; Inputting the original material into a preset material generation model to generate corresponding target material; The original material in the target video template is replaced with the target material to generate a corresponding target video.
2. The video generation method according to claim 1, characterized in that: The receiving a first selection instruction of a target user and selecting a target video template from a preset video template library according to the first selection instruction includes: Pre-build video template library based on target video software; A first selection instruction of a target user is received, and a target video template is selected from the video template library according to the first selection instruction.
3. The video generation method according to claim 2, characterized in that: The step of inputting the original material into a preset material generation model to generate corresponding target material includes: Pre-build material generation model; The original material is input into the material generation model to generate corresponding target material.
4. The video generation method according to claim 3, characterized in that: In the step of receiving a second selection instruction from the target user and selecting the original material to be replaced from the target video template according to the second selection instruction, The original material includes text and / or pictures.
5. The video generation method according to claim 4, characterized in that: When the original material is text, the material generation model is a text generation model; When the original material is a picture, the material generation model is a picture generation model.
6. The video generation method according to claim 5, characterized in that: The image generation model is StableDiffusion.
7. The video generation method according to any one of claims 2 to 6, characterized in that: The target video software is based on which a video template library is pre-built. Wherein, the target video software is After Effects.
8. A video generation system, characterized in that: include: A first selection module, configured to receive a first selection instruction from a target user, and select a target video template from a preset video template library according to the first selection instruction; A second selection module, configured to receive a second selection instruction from the target user, and select an original material to be replaced from the target video template according to the second selection instruction; A first generation module, used for inputting the original material into a preset material generation model to generate corresponding target material; The second generating module is used to replace the original material in the target video template with the target material to generate a corresponding target video.
9. A computer device, characterized in that: The computer device comprises at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor. When the computer program is executed by the at least one processor, the video generation method according to any one of claims 1 to 7 can be implemented.
10. A non-volatile computer-readable storage medium, characterized in that: The non-volatile computer-readable storage medium stores a computer program, and when the computer program is executed by at least one processor, the video generation method according to any one of claims 1 to 7 can be implemented.
