Cartoon generation method and device, electronic equipment and storage medium
By acquiring and processing storyboard scripts to generate audio comics, the problem of low efficiency in traditional comic creation is solved, efficient automated creation and diversified expression are achieved, and the needs of users in the digital age are met.
Patent Information
- Application Number
- CN202411285892.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-13
- Publication Date
- 2025-10-10
- Estimated Expiration
- 2044-09-13
AI Technical Summary
Currently, comic creation relies on traditional hand-drawing, which has low efficiency and a single form of expression, making it difficult to meet the needs of users in the digital age for efficient creation and diversified experience.
By obtaining multiple target storyboards, electronic devices are used to generate target comic books and perform dubbing to form audio comics. This provides an automated creation process to replace manual hand-drawing, supports user input and automated generation, and combines a multimodal large model to adjust the painting and dubbing styles.
It improves the efficiency of comic creation, enriches the forms of expression, and meets users' needs for efficient creation and diversified experience.
Smart Images

Figure CN119295578B_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present disclosure relates to the technical field of computer, in particular to the technical field of artificial intelligence, large language model, natural language processing, and the like, and specifically relates to a comic generation method and device, electronic equipment and storage medium. BACKGROUND
[0002] Current comic creation mainly relies on traditional manual drawing technology, which is not only inefficient, but also has a single form, and it is difficult to meet the dual needs of efficient creation and diversified experience of users in the digital era. SUMMARY
[0003] The present disclosure provides a comic generation method, device, electronic equipment and storage medium.
[0004] According to a first aspect of the present disclosure, a comic generation method is provided, comprising:
[0005] obtaining a plurality of target shot scripts;
[0006] In response to a comic generation request processing operation, a comic generation request carrying a plurality of target shot scripts is sent to a first electronic device; wherein the first electronic device is used to generate a target comic book based on the plurality of target shot scripts carried in the comic generation request, and to dub the target comic book to obtain a first target animated comic;
[0007] receiving and playing the first target animated comic.
[0008] According to a second aspect of the present disclosure, a comic generation method is provided, comprising:
[0009] receiving a comic generation request carrying a plurality of target shot scripts;
[0010] generating a target comic book based on the plurality of target shot scripts carried in the comic generation request, and dubbing the target comic book to obtain a first target animated comic;
[0011] sending the first target animated comic to a second electronic device.
[0012] According to a third aspect of the present disclosure, a comic generation device is provided, comprising:
[0013] a script obtaining unit configured to obtain a plurality of target shot scripts;
[0014] The comic generation request sending unit is configured to send a comic generation request carrying a plurality of target shot scripts to the first electronic device in response to a comic generation request processing operation, wherein the first electronic device is configured to generate a target comic picture book based on the plurality of target shot scripts carried in the comic generation request, and perform dubbing on the target comic picture book to obtain a first target animated comic;
[0015] The first animated comic receiving unit is configured to receive and play the first target animated comic.
[0016] According to a fourth aspect of the present disclosure, a comic generation apparatus is provided, comprising:
[0017] The comic generation request receiving unit is configured to receive a comic generation request carrying a plurality of target shot scripts.
[0018] The comic generation unit is configured to generate a target comic picture book based on the plurality of target shot scripts carried in the comic generation request, and perform dubbing on the target comic picture book to obtain a first target animated comic.
[0019] The first animated comic sending unit is configured to send the first target animated comic to a second electronic device.
[0020] According to a fifth aspect of the present disclosure, an electronic device is provided, comprising:
[0021] at least one processor;
[0022] a memory connected with the at least one processor in communication;
[0023] The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method provided by the embodiments of the present disclosure.
[0024] According to a sixth aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to perform the method provided by the embodiments of the present disclosure.
[0025] According to a seventh aspect of the present disclosure, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the method provided by the embodiments of the present disclosure.
[0026] The present disclosure can improve the efficiency of comic creation, and enrich the forms of comic expression to meet the dual needs of users for efficient creation and diversified experience in the digital age.
[0027] It should be understood that the matters described in this section are not intended to identify key or essential features of the embodiments of the present disclosure, nor are they used to limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS
[0028] The accompanying drawings are used to better understand the present scheme and do not limit the present disclosure. Among them:
[0029] Figure 1 A flowchart of a comic generation method provided by an embodiment of the present disclosure;
[0030] Figure 2 A flowchart of obtaining a target comic theme provided by an embodiment of the present disclosure;
[0031] Figure 3 A schematic diagram of a theme setting interface corresponding to a target comic type provided by an embodiment of the present disclosure;
[0032] Figure 4 A flowchart of a first method for entering a theme setting interface corresponding to a target comic type provided by an embodiment of the present disclosure;
[0033] Figure 5 A flowchart of a second method for entering a theme setting interface corresponding to a target comic type provided by an embodiment of the present disclosure;
[0034] Figure 6 A flowchart of a first method for setting a target comic theme provided by an embodiment of the present disclosure;
[0035] Figure 7 A flowchart of a second method for setting a target comic theme provided by an embodiment of the present disclosure;
[0036] Figure 8 A flowchart of a method for generating a plurality of target comic scripts provided by an embodiment of the present disclosure;
[0037] Figure 9 A flowchart of a method for generating a first target comic provided by an embodiment of the present disclosure;
[0038] Figure 10 A flowchart of a method for receiving and playing a first target comic provided by an embodiment of the present disclosure;
[0039] Figure 11 An auxiliary diagram of a comic sharing mechanism provided by an embodiment of the present disclosure;
[0040] Figure 12 A flowchart of a comic generation method provided by an embodiment of the present disclosure;
[0041] Figure 13 A flowchart of an interaction process between a terminal device and a server provided by an embodiment of the present disclosure is shown in FIG. 1.
[0042] Figure 14 A scene diagram of a comic generation method provided by an embodiment of the present disclosure is shown in FIG. 2.
[0043] Figure 15 A schematic structural block diagram of a comic generation device provided by an embodiment of the present disclosure is shown in FIG. 3.
[0044] Figure 16 A schematic structural block diagram of a comic generation device provided by an embodiment of the present disclosure is shown in FIG. 3.
[0045] Figure 17 A schematic structural block diagram of an electronic device provided by an embodiment of the present disclosure is shown in FIG. 4. DETAILED DESCRIPTION
[0046] Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, which include various details of the embodiments of the present disclosure to help in understanding. These should be considered as merely exemplary. Therefore, those of ordinary skill in the art will recognize various changes and modifications of the embodiments described herein, without departing from the scope of the present disclosure. Also, for the sake of brevity and clarity, descriptions of well-known functions and constructions are omitted from the following description.
[0047] An embodiment of the present disclosure provides a comic generation method, which can be applied to a second electronic device. The second electronic device can be a terminal device. Here, the terminal device can be a conventional computer (desktop computer, notebook computer, etc.), a vehicle-mounted computer, a tablet computer, a smart phone, a personal digital processor, or other similar computing devices. In the following, an embodiment of the present disclosure will be described in detail with reference to the accompanying drawings. Figure 1 The comic generation method provided by an embodiment of the present disclosure is described below with reference to the flowchart shown in FIG. 1. It should be noted that although a logical order is shown in the flowchart, in some cases, the steps shown or described can be performed in other orders.
[0048] In step S101, a plurality of target shot scripts are obtained.
[0049] Each of the plurality of target shot scripts is used to describe a target shot picture in a first target comic to be generated, and the target shot picture can include character image, character action, character expression, background details, etc. Here, the character image can be a person, an animal, and other objects, etc.
[0050] In step S102, in response to a comic generation request processing operation, a comic generation request carrying the plurality of target shot scripts is sent to a first electronic device.
[0051] The comic generation request processing operation can be triggered by a user. The first electronic device can be configured to generate a target comic picture book based on a plurality of target shot scripts carried in the comic generation request, and perform dubbing on the target comic picture book to obtain a first target sound comic. Here, the target comic picture book can include a plurality of target shot pictures corresponding to the plurality of target shot scripts. Based on this, in the embodiment of the present disclosure, when dubbing the target comic picture book, each target shot picture in the plurality of target shot pictures can be taken as a picture to be dubbed, and the target shot script corresponding to the picture to be dubbed can be used to dub the picture to be dubbed.
[0052] In step S103, the first target sound comic is received and played.
[0053] By using the comic generation method provided in the embodiment of the present disclosure, the second electronic device can obtain a plurality of target shot scripts, and in response to a comic generation request processing operation, send a comic generation request carrying the plurality of target shot scripts to the first electronic device, so that the first electronic device generates a target comic picture book based on the plurality of target shot scripts carried in the comic generation request, and performs dubbing on the target comic picture book to obtain a first target sound comic. Thereafter, the second electronic device can receive and play the first target sound comic. In this way, not only the traditional manual drawing technology is replaced by an automatic comic creation process, thereby improving the comic creation efficiency, but also the sound element is integrated to enrich the comic expression form, so that the dual needs of efficient creation and diversified experience of users in the digital era can be met.
[0054] Further, in the embodiment of the present disclosure, for the plurality of target shot scripts, as a first optional implementation, they can be directly generated by user input, which makes the generation of the plurality of target shot scripts more flexible and controllable, so that the plurality of target shot scripts can be highly consistent with the user's expectation, thereby improving the user experience.
[0055] In the embodiment of the present disclosure, for the plurality of target shot scripts, as a second optional implementation, they can also be generated in a relatively automatic manner. Based on this, please refer to Figure 2 In the embodiment of the present disclosure, step S101, i.e., "obtaining a plurality of target shot scripts" can include:
[0056] In step S201-1, a target comic theme is obtained.
[0057] The target cartoon theme can be used to represent theme information of the first target animated comic to be generated. For example, the target cartoon theme can be "Magic Wand of Little Fairy - Actively Solve Difficulties"; for another example, the target cartoon theme can be "Ode to a Nightingale - Tang Dynasty Lao Ping Wang"; for yet another example, the target cartoon theme can be "Magic Wand of Little Fairy - Actively Solve Difficulties".
[0058] In an example, the step S201-1, i.e., "obtaining a target cartoon theme" can include:
[0059] In response to a cartoon type setting operation, displaying a theme setting interface corresponding to a target cartoon type;
[0060] In response to a cartoon theme setting operation triggered on the theme setting interface corresponding to the target cartoon type, obtaining the target cartoon theme.
[0061] The cartoon type setting operation can be triggered by a user; the target cartoon type can be any one of a plurality of candidate cartoon types (e.g., bedtime story, poetry enlightenment, safety education, character cultivation, emotion & relationship, and cognitive popularization).
[0062] Please refer to Figure 3 For example, the theme setting interface corresponding to the target cartoon type (e.g., safety education) can display, in addition to the target cartoon type, other candidate cartoon types (e.g., bedtime story, poetry enlightenment, character cultivation, emotion & relationship, and cognitive popularization) in addition to the target cartoon type among the plurality of candidate cartoon types, and the theme setting interface corresponding to the target cartoon type can also provide a theme editing window 301 for displaying the target cartoon theme and a first virtual button 302 for triggering a script acquisition request processing operation. The first virtual button 302 can be a "generate cartoon" button; in response to the script acquisition request processing operation, a script acquisition request carrying the target cartoon theme can be sent to the first electronic device.
[0063] Here, the plurality of candidate cartoon types can be determined by the first electronic device, and the first electronic device can determine the plurality of candidate cartoon types in the following way:
[0064] Obtaining a whole search word collection of an Internet search and discovery platform;
[0065] Selecting a target number of hot search words related to a cartoon search task from the whole search word collection;
[0066] Generating a plurality of candidate cartoon types based on the target number of hot search words.
[0067] The Internet search and discovery platform can include an Internet search engine platform, a social media platform, an online video sharing website, and the like. The target number can be set according to actual application requirements, for example, can be set to 20, and the embodiments of the present disclosure do not limit this.
[0068] After obtaining the target number of popular search terms, the target number of popular search terms can be processed through screening, deduplication, synonym merging, and the like, to generate a plurality of candidate comic types.
[0069] Further, in a specific example, the "in response to a comic type setting operation, displaying a theme setting interface corresponding to a target comic type" in step S201-1 can include:
[0070] In the case of entering the main interface of the comic generation webpage, in response to a comic type setting operation triggered on the main interface of the comic generation webpage, a target comic type is selected from a plurality of candidate comic types to enter a theme setting interface corresponding to the target comic type.
[0071] In actual implementation, the main interface of the comic generation webpage can be entered based on an original resource locator (Uniform Resource Locator, URL) (i.e., a URL pointing to the main interface of the comic generation webpage), and the bedtime story is selected as the target comic type by default. After entering the main interface of the comic generation webpage, a new target comic type can be selected from a plurality of candidate comic types in response to a comic type setting operation triggered on the main interface of the comic generation webpage to enter a theme setting interface corresponding to the new target comic type. The comic type setting operation can be a mouse click operation, a touch operation, a voice input operation, and the like, and the embodiments of the present disclosure do not limit this.
[0072] Please refer to Figure 4 , for example, the original URL can be https: / / xxxxxxxxxx, and based on the original URL, the bedtime story is selected as the target comic type by default in the main interface of the comic generation webpage. After entering the main interface of the comic generation webpage, a new target comic type (e.g., safety education) can be selected from a plurality of candidate comic types in response to a comic type setting operation triggered on the main interface of the comic generation webpage to enter a theme setting interface corresponding to the new target comic type.
[0073] In another specific example, the "in response to a comic type setting operation, displaying a theme setting interface corresponding to a target comic type" in step S201-1 can further include:
[0074] In response to the comic type setting operation, the original URL is modified to obtain a target URL, so as to enter a theme setting interface corresponding to the target comic type based on the target URL.
[0075] The comic type setting operation may be a keyboard input operation, a voice input operation, etc., and the embodiment of the present disclosure does not limit this.
[0076] Please combine Figure 5 For example, the original URL may be https: / / xxxxxxxxxx. In response to the comic type setting operation, the original URL is modified to obtain the target URL. The target URL may be https: / / xxxxxxxxxxkeyword=target comic type (e.g., safety education). Thereafter, the second electronic device may enter a theme setting interface corresponding to the target comic type based on the target URL.
[0077] That is, in the disclosed embodiment, the second electronic device can not only select a target comic type from multiple candidate comic types in response to a comic type setting operation triggered on the main interface of the comic generation webpage after entering the main interface of the comic generation webpage, thereby entering a theme setting interface corresponding to the target comic type, but can also modify the original URL (i.e., the URL pointing to the main interface of the comic generation webpage) in response to the comic type setting operation to obtain a target URL, and then enter the theme setting interface corresponding to the target comic type based on the target URL. In this way, a variety of methods for entering the theme setting interface corresponding to the target comic type can be provided to the user, allowing the user to flexibly select according to their needs, thereby improving the user experience.
[0078] Furthermore, in a specific example, the "obtaining a target comic theme in response to a comic theme setting operation triggered on a theme setting interface corresponding to the target comic type" in step S201-1 may include:
[0079] In response to a comic theme setting operation triggered on a theme setting interface corresponding to a target comic type, a target comic theme input in a theme editing window is obtained.
[0080] The comic theme setting operation may be a keyboard input operation, a voice input operation, etc., and the embodiment of the present disclosure does not limit this.
[0081] Please combine Figure 6For example, after entering the theme setting interface corresponding to the target comic type (e.g., safety education), the target comic theme input in the theme editing window can be obtained in response to a comic theme setting operation triggered on the theme setting interface corresponding to the target comic type. Here, the target comic theme is: help me create a comic, and the theme is: playing with fire is dangerous - cultivating children's fire safety awareness.
[0082] In another specific example, the "obtaining the target comic theme in response to a comic theme setting operation triggered on the theme setting interface corresponding to the target comic type" in step S201-1 can further include:
[0083] selecting the target comic theme from a plurality of candidate comic themes under the target comic type in response to a comic theme setting operation triggered on the theme setting interface corresponding to the target comic type.
[0084] As mentioned before, in addition to displaying the target comic type, the theme setting interface corresponding to the target comic type can also display other candidate comic types (e.g., bedtime story, poetry initiation, character cultivation, emotion & relationship, and cognitive popularization) in addition to the target comic type from a plurality of candidate comic types, while the theme setting interface corresponding to the target comic type can also provide a theme editing window for inputting the target comic theme, and a first virtual button for triggering a request processing operation. Under this premise, the theme editing window can also provide a second virtual button for triggering a theme window display operation. In response to the theme window display operation, a comic theme selection window can be displayed on the theme setting interface corresponding to the target comic type, and a plurality of candidate comic themes under the target comic type can be displayed in the comic theme selection window. In this way, the user can trigger a comic theme setting operation in the comic theme selection window to select the target comic theme from a plurality of candidate comic themes under the target comic type.
[0085] For example, the target comic type is bedtime story, and the plurality of candidate comic themes under the target comic type can include:
[0086] (1) The magic wand of the fairy girl - actively solve difficulties.
[0087] (2) The prince's deep forest adventure - search for courage & exploration of the unknown.
[0088] (3) The hare waiting for the tree - don't "get it without effort and don't know how to adapt".
[0089] ...
[0090] For example, the target comic type is poetry initiation, and the plurality of candidate comic themes under the target comic type can include:
[0091] (1) Ode to the Goose - Tang Lao Wang.
[0092] (2) Climb the Crane Pavilion - Tang Wang Zhi Huan.
[0093] (3) Out of the Pass - Tang Wang Changling.
[0094] …
[0095] For example, the target comic type is bedtime story, and the multiple candidate comic themes under the target comic type can include:
[0096] (1) The magic wand of the fairy - actively solve difficulties.
[0097] (2) The prince's deep forest adventure - search for courage & explore the unknown.
[0098] (3) Rabbit waiting for the tree - don't "get it without effort, don't know how to change."
[0099] …
[0100] For example, the target comic type is safety education, and the multiple candidate comic themes under the target comic type can include:
[0101] (1) Say no to "bullying" - cultivate children's awareness of anti-bullying.
[0102] (2) Playing with fire is dangerous - cultivate children's awareness of fire safety.
[0103] (3) Don't open the door to strangers - cultivate children's awareness of strangers.
[0104] …
[0105] For example, the target comic type is character cultivation, and the multiple candidate comic themes under the target comic type can include:
[0106] (1) Victory of the little rabbits - share and cooperation is the key to success.
[0107] (2) Frog at the bottom of the well - break the limitations of cognition and open your eyes.
[0108] (3) Foolish old man moving the mountain - perseverance and persistence.
[0109] …
[0110] For example, the target comic type is emotion & relationship, and the multiple candidate comic themes under the target comic type can include:
[0111] (1) Express anger reasonably - let children express emotions reasonably and actively solve difficulties.
[0112] (2) Calmly deal with challenges - let the child not panic when encountering problems and actively solve them calmly.
[0113] (3) Learn to say "no" - let the child understand to refuse others.
[0114] …
[0115] For example, the target comic type is cognitive popularization, and the multiple candidate comic themes under the target comic type can include:
[0116] (1) What is in the forest - understanding nature (forest animal popularization).
[0117] (2) What is in the ocean - understanding nature (ocean knowledge popularization).
[0118] (3) Their occupation - understanding human society (social occupation popularization).
[0119] …
[0120] Please combine Figure 7 , the theme setting interface corresponding to the target comic type (for example, safety education) can display, in addition to the target comic type, other candidate comic types (for example, bedtime story, poetry enlightenment, character cultivation, emotion & relationship and cognitive popularization) in addition to the target comic type. Among the multiple candidate comic types, the theme setting interface corresponding to the target comic type can also provide a theme editing window 701 for displaying the target comic theme, and a first virtual button 702 for triggering a request processing operation. Under this premise, the theme editing window 701 can also provide a second virtual button 701-1 for triggering a theme window display operation. The second virtual button 701-1 can be a "imitation story library (can be directly selected)" button; in response to the theme window display operation, a comic theme selection window 703 corresponding to the target comic type can be displayed, and multiple candidate comic themes under the target comic type can be displayed in the comic theme selection window 703. In this way, the user can trigger a comic theme setting operation in the comic theme selection window 703 to select a target comic theme from the multiple candidate comic themes under the target comic type. Specifically, the comic theme setting operation can be triggered by clicking the "go to use" button corresponding to the target comic theme, jumping back to the display page of the theme editing window 701, and displaying the target comic theme in the theme editing window 701. Here, the target comic theme is "playing with fire is dangerous" - cultivating children's fire safety awareness.
[0121] That is, in the embodiment of the disclosure, the second electronic device can not only obtain the target comic theme input in the theme editing window in response to the comic theme setting operation triggered on the theme setting interface corresponding to the target comic type, but also select the target comic theme from the plurality of candidate comic themes under the target comic type in response to the comic theme setting operation triggered on the theme setting interface corresponding to the target comic type. In this way, a diversified acquisition method for the target comic theme can be provided for the user, so that the user can flexibly select according to his own needs, thereby improving the user experience.
[0122] In the above manner, in the embodiment of the disclosure, the second electronic device can display the theme setting interface corresponding to the target comic type in response to the comic type setting operation, and obtain the target comic theme in response to the comic theme setting operation triggered on the theme setting interface corresponding to the target comic type. In this way, the user can not only continuously perform comic type setting and comic theme setting in the same setting process, thereby improving the comic creation efficiency, but also completely complete the comic type setting and comic theme setting according to his own needs, to ensure that the target comic type and the target comic theme are highly consistent with the user's expectations, thereby improving the user experience.
[0123] Step S201-2, in response to the script acquisition request processing operation, sends a script acquisition request carrying the target comic theme to the first electronic device.
[0124] The script acquisition request processing operation can be a mouse click operation, a touch operation, a voice input operation, etc., and the disclosure does not limit this. The first electronic device can be configured to generate a comic story based on the target comic theme carried in the script acquisition request, and split the comic story to obtain a plurality of initial split shot scripts. Here, the first electronic device can generate 10-20 initial split shot scripts by default.
[0125] In an example, the first electronic device can utilize a large language model to generate a comic story based on the target comic theme carried in the script acquisition request, and split the comic story to obtain a plurality of initial split shot scripts. The large language model can be a pre-trained neural network model that has general language knowledge, world knowledge, and professional knowledge in various fields, and is stored in the model in the form of parameters. Specifically, the large language model can be a Transformer architecture autoregressive generation model.
[0126] Further, in the embodiments of the present disclosure, the second electronic device can send a script acquisition request carrying the target comic type and the target comic theme to the first electronic device in response to the script acquisition request processing operation, so that the first electronic device generates a comic story based on the target comic type and the target comic theme carried in the script acquisition request, and splits the comic story to obtain a plurality of initial shot scripts, for example, so that the first electronic device uses a large language model to generate a comic story based on the target comic type and the target comic theme carried in the script acquisition request, and splits the comic story to obtain a plurality of initial shot scripts. In this way, the generated comic story can be improved to better meet the user's expectations, and the plurality of initial shot scripts can be improved to better meet the user's expectations, so as to further improve the user experience.
[0127] Step S201-3, receiving and displaying the plurality of initial shot scripts.
[0128] The plurality of initial shot scripts can be text information in a lightweight markup language (for example, Markdown format).
[0129] Step S201-4, obtaining a plurality of target shot scripts based on the plurality of initial shot scripts.
[0130] In an example, the plurality of initial shot scripts can be the plurality of target shot scripts.
[0131] In another example, the second electronic device can edit the plurality of initial shot scripts to obtain the plurality of target shot scripts in response to a shot script editing operation, so as to improve the plurality of target shot scripts to better meet the user's expectations, thereby improving the user experience. The shot script editing operation can be a keyboard input operation, a voice input operation, etc., which is not limited in the embodiments of the present disclosure; and the editing of the plurality of initial shot scripts can be an adding, deleting or modifying operation on the plurality of initial shot scripts.
[0132] Please refer to Figure 8 For example, the first electronic device splits the comic story "Little Rabbit Playing Fire" to obtain 14 initial shot scripts, which include:
[0133] 1. Little Rabbit jumps and plays in the forest.
[0134] 2. Jump sees a pile of fire in the distance, and curiously approaches it.
[0135] 3. Jump thinks that fire is interesting.
[0136] 4. It finds a small stick and tries to approach the fire.
[0137] 5. Suddenly, the stick is ignited, and jump is scared and throws it away.
[0138] 6. Jumping Jack jumped up in panic, but the fire grew bigger and bigger.
[0139] 7. Jumping Jack was scared, and he remembered what his mother had told him: playing with fire was dangerous.
[0140] 8. Jumping Jack helped find the animals in the forest to help put out the fire.
[0141] …
[0142] 13. Jumping Jack also became more sensible, and he played happily with the boys in the forest.
[0143] 14. They learned how to use fire safely and how to protect themselves.
[0144] After that, by clicking the "Edit Script" button and triggering the split script editing operation, editing of multiple initial split scripts is started, for example, the first initial split script "Rabbit Jumping Jack playing in the forest" is modified to "On a sunny morning, rabbit Jumping Jack plays in the forest", as a target split script; for another example, an initial split script "Every corner in the forest is full of laughter, and the animals live a happy life" is added as the 15th target split script. Finally, 15 target split scripts are obtained, which include:
[0145] 1. On a sunny morning, rabbit Jumping Jack plays in the forest.
[0146] 2. Jumping Jack sees a pile of fire in the distance, and he curiously approaches it.
[0147] 3. Jumping Jack thinks, what is fire? It looks so interesting.
[0148] 4. It finds a small stick and tries to approach the fire.
[0149] 5. Suddenly, the small stick is ignited, and Jumping Jack is scared and throws it away.
[0150] 6. Jumping Jack jumped up in panic, but the fire grew bigger and bigger.
[0151] 7. Jumping Jack was scared, and he remembered what his mother had told him: playing with fire was dangerous.
[0152] 8. Jumping Jack helped find the animals in the forest to help put out the fire.
[0153] …
[0154] 13. Jumping Jack also became more sensible, and he played happily with the boys in the forest.
[0155] 14. They learned how to use fire safely, and how to protect themselves.
[0156] 15. Every corner of the forest was full of laughter and joy, and the small animals lived a happy life.
[0157] After obtaining 15 target scripts, the comic generation request processing operation can be triggered by clicking the "generate comic" button, and the subsequent step S102, i.e., "in response to the comic generation request processing operation, the comic generation request carrying the multiple target scripts is sent to the first electronic device".
[0158] Through steps S201-1, S201-2, S201-3 and S201-4, in the embodiment of the disclosure, the second electronic device can obtain the target comic theme, and in response to the script acquisition request processing operation, the script acquisition request carrying the target comic theme is sent to the first electronic device, so that the first electronic device generates a comic story based on the target comic theme carried in the script acquisition request, and then splits the comic story to obtain multiple initial scripts. After that, the second electronic device can receive and display multiple initial scripts, and based on multiple initial scripts, multiple target scripts are obtained. That is, in the embodiment of the disclosure, in addition to being directly generated by user input, multiple target comic scripts can also be automatically generated through the interaction between the second electronic device and the first electronic device, thereby further improving the efficiency of comic creation.
[0159] In some optional embodiments, step S102, i.e., "in response to the comic generation request processing operation, the comic generation request carrying the multiple target scripts is sent to the first electronic device" can include:
[0160] determining a user preference style; wherein the user preference style includes at least one of a target drawing style and a target voice style;
[0161] generate a comic generation request carrying the multiple target scripts and the user preference style;
[0162] in response to the comic generation request processing operation, the comic generation request is sent to the first electronic device; wherein the first electronic device is configured to generate a target comic picture book based on the multiple target scripts and the user preference style carried in the comic generation request, and to voice the target comic picture book to obtain a first target comic.
[0163] The target drawing style can be any one of a plurality of candidate drawing styles (e.g., fresh cartoon, childlike illustration, and 3D cartoon); and the target voiceover style can be any one of a plurality of candidate voiceover styles (e.g., gentle sister, magnetic deep affection, warm commentary, and sweet lyricism).
[0164] In an example, the second electronic device can select a target drawing style from a plurality of candidate drawing styles in response to a drawing style selection operation, and select a target voiceover style from a plurality of candidate voiceover styles in response to a voiceover style selection operation. The drawing style selection operation and the voiceover style selection operation can be a mouse click operation, a touch operation, a voice input operation, etc., and the present disclosure does not limit the same.
[0165] After determining the user preference style, the second electronic device can generate a comic generation request carrying a plurality of target shot scripts and the user preference style, and send the comic generation request to the first electronic device in response to a comic generation request processing operation, so that the first electronic device generates a target comic book based on the plurality of target shot scripts and the user preference style carried in the comic generation request, and voices the target comic book to obtain a first target animated comic. The target comic book can be a Bdjson format comic book that has been subjected to Gaussian blur processing.
[0166] In an example, the first electronic device can utilize a multi-modal large model to generate a target comic book based on the plurality of target shot scripts and the user preferred style carried in the comic generation request, and to dub the target comic book after Gaussian blur processing to obtain a first target sound comic. For example, the first electronic device can utilize the multi-modal large model to understand the target drawing style in the plurality of target shot scripts and the user preferred style carried in the comic generation request, generate a to-be-adjusted comic book, and through understanding the plurality of target shot scripts, the user preferred style, and the relationship between elements (e.g., characters, animals, other objects, backgrounds) in the to-be-adjusted comic book, perform layout adjustment (e.g., size, color, and position adjustment of each element, as well as size, color, and position adjustment of subtitles), to generate a target comic book, and dub the target comic book based on the target dubbing style in the user preferred style to obtain a first target sound comic. The multi-modal large model can be a multi-modal model constructed by using a large language model, which can include an image encoder and a bridging component in addition to the large language model. The image encoder is connected to the large language model through the bridging component. Here, the image encoder is pre-trained and has a general image encoding function, which is used to encode the input target image to obtain an image encoding result; the bridging component is used to convert the image encoding result to a feature conversion result that can be understood by the large language model, i.e., the bridging component is used to align the visual feature space of the image encoder to the text feature space of the large language model.
[0167] Please refer to Figure 9 For example, the second electronic device can select a childlike illustration as the target drawing style from a plurality of candidate drawing styles (e.g., fresh cartoon, childlike illustration, and 3D cartoon) in response to a drawing style selection operation, and select a sweet and sentimental style as the target dubbing style from a plurality of candidate dubbing styles (e.g., gentle sister, magnetic deep affection, warm commentary, and sweet and sentimental) in response to a dubbing style selection operation. Thereafter, the second electronic device can generate a comic generation request carrying a plurality of target shot scripts and a user preferred style. The plurality of target shot scripts include:
[0168] 1. On a sunny morning, little rabbit jumps in the forest to play.
[0169] 2. Jump sees a pile of fire in the distance, and curiously approaches it.
[0170] 3. Jump thinks that fire is what? It looks so interesting.
[0171] 4. It finds a small stick and tries to approach the fire.
[0172] 5. Suddenly, the small stick is ignited, and jump is scared and throws it away.
[0173] 6. Tiao Tiao jumped up in panic, but the fire grew stronger and stronger.
[0174] 7. Tiaotiao was scared because he remembered what his mother had said: playing with fire is very dangerous.
[0175] 8. Tiaotiao asked the animals in the forest to help put out the fire.
[0176] …
[0177] 13. Tiaotiao also became more sensible, and played happily with the boys in the forest.
[0178] 14. They learned how to use fire safely and how to protect themselves.
[0179] 15. Every corner of the forest is filled with laughter and joy, and the little animals live a happy life.
[0180] After the second electronic device generates a comic generation request carrying multiple target storyboards and user preferred styles, it can trigger the comic generation request processing operation by clicking the "Generate Comic" button, and send the comic generation request to the first electronic device, so that the first electronic device uses the multimodal large model to generate a target comic picture book based on the multiple target storyboards carried in the comic generation request and the target painting style in the user preferred style, and dub the target comic picture book based on the target dubbing style in the user preferred style to obtain a first target audio comic.
[0181] Through the above method, in the embodiment of the present disclosure, the second electronic device can determine the user's preferred style (including at least one of a target drawing style and a target dubbing style), and generate a comic generation request carrying multiple target storyboards and the user's preferred style. Then, in response to the comic generation request processing operation, the second electronic device sends the comic generation request to the first electronic device, so that the first electronic device generates a target comic picture book based on the multiple target storyboards and the user's preferred style carried in the comic generation request, and dubs the target comic picture book to obtain a first target audio comic. In this way, it can ensure that the first target audio comic is highly consistent with the user's preferred style, thereby improving the user experience.
[0182] In some optional implementations, the comic generation request includes a comic drawing request and a comic dubbing request, and the comic drawing request carries multiple target storyboards. Based on this, in the disclosed embodiment, step S102, i.e., "responding to the comic generation request processing operation, sending the comic generation request carrying multiple target storyboards to the first electronic device," may also include:
[0183] In response to the comic drawing operation, a comic drawing request is sent to the first electronic device; wherein the first electronic device is configured to generate an initial comic picture book based on the plurality of target scripts carried in the comic generation request;
[0184] The initial comic picture book is received and displayed;
[0185] In the case where the confirmation operation for the initial comic picture book is detected, in response to the confirmation operation, a comic dubbing request is sent to the first electronic device; wherein the first electronic device is configured to respond to the comic dubbing request, take the initial comic picture book as a target comic picture book, dub the target comic picture book to obtain a first target comic.
[0186] The comic drawing operation and the confirmation operation can be a mouse click operation, a touch operation, a voice input operation, etc., and the embodiments of the present disclosure do not limit this.
[0187] In an example, the second electronic device can respond to the comic drawing operation, send a comic drawing request to the first electronic device, so that the first electronic device uses a multi-modal large model to generate an initial comic picture book based on the plurality of target scripts carried in the comic generation request. In a specific example, the first electronic device can use a multi-modal large model to generate an initial comic picture book based on the plurality of target scripts carried in the comic generation request and a target drawing style in the user preferred style. The target drawing style can be any one of a plurality of candidate drawing styles (e.g., fresh cartoon, childlike illustration, and 3D cartoon).
[0188] In an example, after the second electronic device receives and displays the initial comic picture book and detects the confirmation operation for the initial comic picture book, it can respond to the confirmation operation, send a comic dubbing request to the first electronic device, so that the first electronic device uses a multi-modal large model to take the initial comic picture book as a target comic picture book, dub the target comic picture book to obtain a first target comic. In a specific example, the first electronic device can use a multi-modal large model to take the initial comic picture book as a target comic picture book, and call a text-to-speech (TTS) function to dub the target comic picture book based on a target dubbing style in the user preferred style, to obtain a first target comic. The target dubbing style can be any one of a plurality of candidate dubbing styles (e.g., gentle sister, magnetic deep love, warm commentary, and sweet lyricism).
[0189] In addition, it should be noted that in the embodiment of the present disclosure, the second electronic device may also, upon detecting a negative operation for the initial comic book, send an initial comic redrawing request to the first electronic device in response to the negative operation, so that the first electronic device generates a new initial comic book based on the multiple target storyboards carried in the comic generation request in response to the initial comic redrawing request. Thereafter, the second electronic device may receive and display the new initial comic book, and upon detecting a confirmation operation for the new initial comic book, send a comic dubbing request to the first electronic device in response to the confirmation operation; wherein the first electronic device is configured to respond to the comic dubbing request and use the new initial comic book as the target comic book to dub the target comic book to obtain a first target audio comic.
[0190] Through the above method, in the embodiment of the present disclosure, the second electronic device can respond to the comic drawing operation and send a comic drawing request to the first electronic device, so that the first electronic device generates an initial comic drawing book based on the multiple target storyboards carried in the comic generation request. Thereafter, the second electronic device can receive and display the initial comic drawing book, and when a confirmation operation for the initial comic drawing book is detected, in response to the confirmation operation, send a comic dubbing request to the first electronic device, so that the first electronic device responds to the comic dubbing request and uses the initial comic drawing book as the target comic drawing book to dub the target comic drawing book to obtain a first target audio comic. In this way, it can be ensured that the first target audio comic is obtained by using the initial comic user confirmed by the user as the target comic drawing book and dubbing the target comic drawing book. Therefore, the first target audio comic meets the user's expectations and can improve the user experience.
[0191] In some optional implementations, step S103, i.e., "receiving and playing the first target audio comic," may:
[0192] polling the first electronic device to generate and display a user prompt message if it is determined that the first electronic device has generated a target comic picture book based on the multiple target storyboards carried in the comic generation request, and dubbed the target comic picture book to obtain a first target audio comic;
[0193] In response to the first comic play operation, a first target audio comic is received and played.
[0194] Among them, displaying the user prompt information can be a third virtual button displayed. Here, the third virtual button can be a "Play Comics" button. Based on this, in the embodiment of the present disclosure, the first comic playback operation can be triggered by clicking the third virtual button. In addition, in one example, after the second electronic device generates and displays the user prompt information, if the first comic playback operation is detected, a server-sent event (SSE) request can be sent to the first electronic device in response to the first comic playback operation, and the first target audio comic is received and played page by page.
[0195] For example, please combine Figure 10 The second electronic device can poll the first electronic device to generate and display user prompt information, that is, a third virtual button (for example, a "play comic" button) after determining that the first electronic device has generated a target comic picture book based on multiple target storyboards carried in the comic generation request, and dubbed the target comic picture book to obtain the first target audio comic. Thereafter, the first comic playback operation can be triggered by clicking the third virtual button to receive and play the first target audio comic.
[0196] Furthermore, it should be noted that in the disclosed embodiment, the first electronic device may also generate a target comic book based on the multiple target storyboards carried in the comic generation request, dub the target comic book, and after obtaining the first target audio comic, generate a text message prompt containing a prompt URL (i.e., a URL pointing to the playback page of the first target audio comic) and send the text message prompt to the user. In this way, the user can directly access the playback page of the first target audio comic based on the prompt URL.
[0197] Through the above method, in the disclosed embodiment, the second electronic device can poll the first electronic device to generate and display a user prompt message when it determines that the first electronic device has generated a target comic book based on the multiple target storyboards carried in the comic generation request, dubbed the target comic book, and obtained a first target audio comic. In response to the first comic playback operation, the second electronic device receives and plays the first target audio comic. On the one hand, because the comic generation process of "generating a target comic book based on the multiple target storyboards carried in the comic generation request, dubbing the target comic book, and obtaining the first target audio comic" takes several minutes (for example, 5 minutes), informing the user that the comic generation process has been completed through the user prompt message can reduce the user's subjective waiting time for the first target audio comic. On the other hand, the first target audio comic is received and played in response to the first comic playback operation only when the first comic playback operation is triggered, thereby avoiding waste of communication resources.
[0198] In some optional implementations, the comic generation method may further include:
[0199] Sending a work sharing request for a first target audio comic to a first electronic device;
[0200] The first electronic device is configured to store the first target audio comic in a shared comic library in response to the work sharing request. That is, in an embodiment of the present disclosure, the first electronic device may store the first target audio comic as a shareable comic in the shared comic library in response to the work sharing request. In one example, the first electronic device may categorize and store the first target audio comic based on its comic genre.
[0201] Based on this, in the embodiment of the present disclosure, the comic generation method may further include:
[0202] In response to the audio comic selection request processing operation, sending an audio comic selection request carrying comic identification information to the first electronic device; wherein the first electronic device is configured to select a second target audio comic from a shared comic library of the first electronic device based on the comic identification information carried in the audio comic selection request;
[0203] In response to the second comic play operation, a second target audio comic is received and played.
[0204] The comic identification information may be a comic serial number, a comic title, etc., which is not limited in the embodiment of the present disclosure.
[0205] In one example, after the second electronic device displays comic identification information (e.g., comic name) of multiple sharable comics provided by the shared comic library in response to the inventory viewing operation, it can respond to the audio comic selection request processing operation and send an audio comic selection request carrying comic identification information to the first electronic device, so that the first electronic device selects the second target audio comic from the shared comic library of the first electronic device based on the comic identification information carried in the audio comic selection request. Thereafter, the second electronic device can receive and play the second target audio comic in response to the second comic playback operation. For example, in response to the second comic playback operation, an SSE request can be sent to the first electronic device to receive and play the second target audio comic page by page.
[0206] Among them, the inventory viewing operation and the audio comic selection request processing operation can be a mouse click operation, a touch operation, a voice input operation, etc., and the embodiment of the present disclosure does not limit this.
[0207] Please combine Figure 11For example, in addition to displaying the target comic type (e.g., safety education), the theme setting interface corresponding to the target comic type (e.g., bedtime story, poetry enlightenment, character cultivation, emotion & relationship, and cognitive popular science) can also display other candidate comic types (e.g., bedtime story, poetry enlightenment, character cultivation, emotion & relationship, and cognitive popular science) in the theme setting interface, and the theme setting interface corresponding to the target comic type can also provide a theme editing window 1101 for displaying the target comic theme, a first virtual button 1102 for triggering a request processing operation, and a shared comic storage window 1103. The shared comic storage window 1103 displays part of the shareable comics in the shared comic library (e.g., a shareable comic with comic identification information of a cat sleeping well, a shareable comic with comic identification information of a tiger seeking a master, etc.). Clicking any shareable comic in the part of the shareable comics can trigger a storage viewing operation to enter a shared comic library synchronization window 1104.
[0208] Thereafter, the second target comic (e.g., a shareable comic with comic identification information of saying no to bullying) under any comic type in the shared comic library synchronization window 1104 can be clicked to trigger a voice comic selection request processing operation, and a voice comic selection request carrying comic identification information (here, comic identification information of the second target voice comic) can be sent to the first electronic device to enable the first electronic device to select the second target voice comic from the shared comic library of the first electronic device based on the comic identification information carried in the voice comic selection request. Thereafter, the second electronic device can receive and play the second target voice comic in response to a second comic playing operation.
[0209] In the above manner, in the embodiments of the present disclosure, the second electronic device can send a work sharing request for the first target voice comic to the first electronic device to enable the first electronic device to store the first target voice comic in the shared comic library in response to the work sharing request. Based on this, in the examples of the present disclosure, the second electronic device can also send a voice comic selection request carrying comic identification information to the first electronic device in response to a voice comic selection request processing operation to enable the first electronic device to select a second target voice comic from the shared comic library of the first electronic device based on the comic identification information carried in the voice comic selection request. Thereafter, the second electronic device can receive and play the second target voice comic in response to a second comic playing operation. In this way, the comic sharing mechanism can provide the user with a generated and rich shareable comic, thereby meeting the user's more efficient and diversified comic playing needs.
[0210] The embodiments of the present disclosure also provide a comic generation method, which can be applied to a first electronic device. The first electronic device can be a server. In the following, the comic generation method will be described in combination with the first electronic device. Figure 12The flowchart shown in the figure illustrates a comic book generation method provided by an embodiment of the present disclosure. It should be noted that although the flowchart shows a logical order, in some cases, the steps shown or described can also be performed in other orders.
[0211] Step S1201: Receive a comic generation request carrying multiple target storyboards.
[0212] Each of the multiple target storyboards is used to describe a target storyboard screen in the first target audio comic to be generated, and the target storyboard screen may include character images, character actions, character expressions, background details, etc. Here, the character images may be people, animals, and other objects.
[0213] Step S1202: Generate a target comic book based on the multiple target storyboards carried in the comic generation request, and dub the target comic book to obtain a first target audio comic.
[0214] The target comic book may include multiple target storyboards corresponding to multiple target storyboard scripts. Based on this, in the disclosed embodiment, when dubbing the target comic book, each of the multiple target storyboards can be used as a picture to be dubbed, and the target storyboard script corresponding to the picture to be dubbed can be used to dub the picture to be dubbed.
[0215] Step S1202: Send the first target audio comic to the second electronic device.
[0216] Using the comic generation method provided by the embodiment of the present disclosure, a first electronic device can receive a comic generation request carrying multiple target storyboards, and based on the multiple target storyboards carried in the comic generation request, generate a target comic picture book, dub the target comic picture book, and obtain a first target audio comic. The first target audio comic is then sent to a second electronic device so that the second electronic device receives and plays the first target audio comic. In this way, not only does the automated comic creation process replace traditional manual hand-drawing techniques, thereby improving comic creation efficiency, but the incorporation of sound elements also enriches the comic expression form. Therefore, it can meet the dual needs of users in the digital age for efficient creation and diversified experience.
[0217] In some optional implementations, the comic generation method may further include:
[0218] Receive a script acquisition request carrying a target comic theme;
[0219] Generate a comic story based on the target comic theme carried in the script acquisition request;
[0220] Split the comic story to obtain a plurality of initial shot scripts;
[0221] Send the plurality of initial shot scripts to a second electronic device; wherein the second electronic device is configured to receive and display the plurality of initial shot scripts, and obtain a plurality of target shot scripts based on the plurality of initial shot scripts.
[0222] The target comic theme can be used to represent the theme information of the first target animated comic to be generated. For example, the target comic theme can be "Magic Wand of Little Fairy - Actively Solve Difficulties"; for another example, the target comic theme can be "Ode to the Goose - Tang Don Luobin Wang"; for yet another example, the target comic theme can be "Magic Wand of Little Fairy - Actively Solve Difficulties".
[0223] Here, the target comic theme can be obtained by the second electronic device, and the second electronic device can obtain the target comic theme in the following way:
[0224] In response to a comic type setting operation, display a theme setting interface corresponding to the target comic type;
[0225] In response to a comic theme setting operation triggered on the theme setting interface corresponding to the target comic type, obtain the target comic theme.
[0226] In an example, "in response to a comic type setting operation, display a theme setting interface corresponding to the target comic type" can include:
[0227] In the case of having entered the main interface of the comic generation webpage, in response to a comic type setting operation triggered on the main interface of the comic generation webpage, select the target comic type from a plurality of candidate comic types to enter the theme setting interface corresponding to the target comic type;
[0228] Alternatively, in response to a comic type setting operation, modify the original URL to obtain a target URL, so as to enter the theme setting interface corresponding to the target comic type based on the target URL.
[0229] In an example, "in response to a comic theme setting operation triggered on the theme setting interface corresponding to the target comic type, obtain the target comic theme" can include:
[0230] In response to a comic theme setting operation triggered on the theme setting interface corresponding to the target comic type, obtain the target comic theme input in the theme editing window;
[0231] Alternatively, in response to a comic theme setting operation triggered on the theme setting interface corresponding to the target comic type, select the target comic theme from a plurality of candidate comic themes under the target comic type.
[0232] Afterwards, the second electronic device can send a script obtaining request carrying the target comic theme to the first electronic device in response to the script obtaining request processing operation. Afterwards, the first electronic device can generate a comic story based on the target comic theme carried in the script obtaining request, split the comic story to obtain a plurality of initial shot scripts, and send the plurality of initial shot scripts to the second electronic device, so that the second electronic device receives and displays the plurality of initial shot scripts, and obtains a plurality of target shot scripts based on the plurality of initial shot scripts. In an example, the first electronic device can utilize a large language model to generate a comic story based on the target comic theme carried in the script obtaining request, split the comic story to obtain a plurality of initial shot scripts, and send the plurality of initial shot scripts to the second electronic device, so that the second electronic device receives and displays the plurality of initial shot scripts, and obtains a plurality of target shot scripts based on the plurality of initial shot scripts. The plurality of initial shot scripts can be text information in a lightweight markup language (for example, Markdown format).
[0233] In the above manner, in the embodiment of the disclosure, the first electronic device receives a script obtaining request carrying a target comic theme, generates a comic story based on the target comic theme carried in the script obtaining request, splits the comic story to obtain a plurality of initial shot scripts, and sends the plurality of initial shot scripts to the second electronic device, so that the second electronic device receives and displays the plurality of initial shot scripts, and obtains a plurality of target shot scripts based on the plurality of initial shot scripts. That is, in the embodiment of the disclosure, the plurality of target comic scripts can be automatically generated through the interaction between the second electronic device and the first electronic device, thereby further improving the comic creation efficiency.
[0234] Further, in the embodiment of the disclosure, the script obtaining request also carries a target comic type. Based on this, in the embodiment of the disclosure, "generating a comic story based on the target comic theme carried in the script obtaining request" can include:
[0235] generating a comic story based on the target comic type and the target comic theme carried in the script obtaining request.
[0236] In an example, the first electronic device can utilize a large language model to generate a comic story based on the target comic type and the target comic theme carried in the script obtaining request. Afterwards, the first electronic device splits the comic story to obtain a plurality of initial shot scripts. In this way, the generated comic story can be improved to better meet the user's expectations, and the plurality of initial shot scripts can be improved to better meet the user's expectations, thereby further improving the user experience.
[0237] In some optional implementations, the comic generation request also carries a user preferred style, and the user preferred style includes at least one of a target drawing style and a target dubbing style. Based on this, in the disclosed embodiment, step S1202, i.e., "generating a target comic book based on the multiple target storyboards carried in the comic generation request, and dubbing the target comic book to obtain a first target audio comic," may include:
[0238] Based on the multiple target storyboards and user preferred styles carried in the comic generation request, a target comic picture book is generated, and the target comic picture book is dubbed to obtain a first target audio comic.
[0239] In one example, the first electronic device can use a multimodal large model to generate a target comic picture book based on multiple target storyboards and user preferred styles carried in the comic generation request, and dub the target comic picture book after Gaussian blur processing to obtain a first target audio comic. For example, the first electronic device can use a multimodal large model to understand the multiple target storyboards and the target painting style in the user preferred style carried in the comic generation request, generate a comic picture book to be adjusted, and by understanding the multiple target storyboards, the user preferred style, and the relationship between the elements (e.g., characters, animals, other objects, background) in the comic picture book to be adjusted, perform typesetting adjustments (e.g., size, color, position adjustment of each element, and subtitle size, subtitle color, subtitle position adjustment) to generate a target comic picture book, and dub the target comic picture book based on the target dubbing style in the user preferred style to obtain a first target audio comic.
[0240] Through the above approach, in the disclosed embodiment, the first electronic device can generate a target comic book based on the multiple target storyboards and the user's preferred style carried in the comic book generation request, and then dub the target comic book to obtain a first target audio comic. This ensures that the first target audio comic is highly compatible with the user's preferred style, thereby improving the user experience.
[0241] In some optional implementations, the comic generation request includes a comic drawing request and a comic dubbing request, and the comic drawing request carries the multiple target storyboards. Based on this, in the disclosed embodiment, step S1202, i.e., "generating a target comic book based on the multiple target storyboards carried in the comic generation request, and dubbing the target comic book to obtain a first target audio comic," may also include:
[0242] Generate an initial comic book based on multiple target storyboards carried in the comic generation request;
[0243] send the initial comic book to a second electronic device; wherein the second electronic device is configured to receive and display the initial comic book;
[0244] In a case where the second electronic device receives and displays the initial comic book, and detects a confirmation operation for the initial comic book, and sends a comic dubbing request to the first electronic device in response to the confirmation operation, the first electronic device generates a first target comic dubbing by dubbing the initial comic book as a target comic book in response to the comic dubbing request.
[0245] In an example, the first electronic device can generate the initial comic book based on the plurality of target shot scripts carried in the comic generation request by using the multi-modal large model. In a specific example, the first electronic device can generate the initial comic book based on the plurality of target shot scripts carried in the comic generation request and a target drawing style in the user preference style by using the multi-modal large model. The target drawing style can be any one of a plurality of candidate drawing styles (e.g., fresh cartoon, childlike illustration, and 3D cartoon).
[0246] In an example, after the second electronic device receives and displays the initial comic book, and detects a confirmation operation for the initial comic book, and sends a comic dubbing request to the first electronic device in response to the confirmation operation, the first electronic device can generate a first target comic dubbing by dubbing the initial comic book as a target comic book by using the multi-modal large model. In a specific example, the first electronic device can generate a first target comic dubbing by dubbing the initial comic book as a target comic book and invoking a TTS function based on a target dubbing style in the user preference style by using the multi-modal large model. The target dubbing style can be any one of a plurality of candidate dubbing styles (e.g., gentle sister, magnetic deep affection, warm commentary, and sweet lyricism).
[0247] In addition, it should be noted that in the embodiments of the present disclosure, the second electronic device can also send an initial comic redrawing request to the first electronic device in response to a negative operation for the initial comic book after detecting the negative operation. After receiving the initial comic redrawing request, the first electronic device can generate a new initial comic book based on the plurality of target shot scripts carried in the comic generation request in response to the initial comic redrawing request. Thereafter, the second electronic device can receive and display the new initial comic book, and send a comic dubbing request to the first electronic device in response to a confirmation operation for the new initial comic book in a case where the confirmation operation is detected. In this way, the first electronic device can generate a first target comic dubbing by dubbing the new initial comic book as a target comic book in response to the comic dubbing request.
[0248] By the above manner, in the embodiment of the disclosure, the first electronic device can generate an initial comic book based on the plurality of target shot scripts carried in the comic generation request, and send the initial comic book to the second electronic device; wherein the second electronic device is configured to receive and display the initial comic book, and in the case that the second electronic device detects a confirmation operation for the initial comic book and sends a comic dubbing request to the first electronic device in response to the confirmation operation, the second electronic device is configured to, in response to the comic dubbing request, take the initial comic book as a target comic book, dub the target comic book to obtain a first target sound comic. In this way, it can be ensured that the first target sound comic is obtained by taking the initial comic book confirmed by the user as the target comic book and dubbing the target comic book, and therefore the first target sound comic meets the user's expectation, which can improve the user experience.
[0249] In some optional embodiments, the comic generation method can further include:
[0250] In the case that the second electronic device sends a work sharing request for the first target sound comic, the first target sound comic is stored in the shared comic library in response to the work sharing request.
[0251] In an example, the first electronic device can classify and store the first target sound comic based on the type of the comic to which the first target sound comic belongs.
[0252] Based on this, in the embodiment of the disclosure, the comic generation method can further include:
[0253] Receiving a sound comic selection request carrying comic identification information;
[0254] Selecting a second target sound comic from the shared comic library of the first electronic device based on the comic identification information carried in the sound comic selection request;
[0255] Sending the second target sound comic to the second electronic device.
[0256] The comic identification information can be a comic serial number, a comic name, etc., which is not limited in the embodiment of the disclosure.
[0257] Through the above manner, in the embodiment of the disclosure, the first electronic device can store the first target comic in the shared comic library in response to the work sharing request in a case that the first electronic device receives the work sharing request for the first target comic sent by the second electronic device. Based on this, in the example of the disclosure, the first electronic device can also receive a comic selection request carrying comic identification information, and select a second target comic from the shared comic library of the first electronic device based on the comic identification information carried in the comic selection request, and send the second target comic to the second electronic device. In this way, through the comic sharing mechanism, the user can be provided with a generated and rich shareable comic, thereby meeting the user's more efficient and diversified comic playing needs.
[0258] In the following, the above-mentioned embodiments of the disclosure will be described in detail in combination with Figure 13 In the embodiment of the disclosure, the second electronic device and the first electronic device are introduced in an interactive process involved in the execution of the comic generation method.
[0259] (1) The second electronic device obtains a comic theme.
[0260] (2) The second electronic device sends a script acquisition request carrying a target comic type and a target comic theme to the first electronic device in response to a script acquisition request processing operation.
[0261] (3) The first electronic device generates a comic story based on the target comic type and the target comic theme carried in the script acquisition request, splits the comic story, obtains a plurality of initial split scripts, and sends the plurality of initial split scripts to the second electronic device.
[0262] (4) The second electronic device edits the plurality of initial split scripts to obtain a plurality of target split scripts in response to a split script editing operation.
[0263] (5) The second electronic device determines a user preference style, generates a comic generation request carrying the plurality of target split scripts and the user preference style, and sends the comic generation request to the first electronic device in response to a comic generation request processing operation.
[0264] (6) The first electronic device generates a target comic book based on the plurality of target split scripts and the user preference style carried in the comic generation request, and performs dubbing on the target comic book to obtain a first target comic.
[0265] (7) The second electronic device polls the first electronic device to generate and display user prompt information in a case that the first electronic device has generated a target comic book based on the plurality of target split scripts carried in the comic generation request, and performed dubbing on the target comic book to obtain a first target comic.
[0266] (8) The second electronic device receives and plays the first target comic in response to the first comic playing operation.
[0267] Please refer to Figure 14 A scene schematic diagram of a comic generation method provided by the embodiment of the present disclosure.
[0268] As described above, the comic generation method provided by the embodiment of the present disclosure is applied to an electronic device. The electronic device can be a second electronic device or a first electronic device. Here, the second electronic device can be a terminal device, for example, a conventional computer (desktop computer, notebook computer, etc.), a vehicle-mounted computer, a tablet computer, a smart phone, a personal digital processor or other similar computing device; and the first electronic device can be a server.
[0269] When the electronic device is the second electronic device, it is used for:
[0270] obtaining a plurality of target shot scripts;
[0271] sending a comic generation request carrying the plurality of target shot scripts to the first electronic device in response to a comic generation request processing operation; wherein the first electronic device is configured to generate a target comic book based on the plurality of target shot scripts carried in the comic generation request, and to dub the target comic book to obtain a first target comic;
[0272] receiving and playing the first target comic.
[0273] When the electronic device is the first electronic device, it is used for:
[0274] receiving a comic generation request carrying a plurality of target shot scripts;
[0275] generating a target comic book based on the plurality of target shot scripts carried in the comic generation request, and dubbing the target comic book to obtain a first target comic;
[0276] sending the first target comic to the second electronic device.
[0277] It should be noted that in the embodiment of the present disclosure, Figure 14 The scene schematic diagram shown is only schematic and not limiting, and those skilled in the art can make various obvious changes and / or replacements based on Figure 14 Examples, and the technical solutions obtained still belong to the disclosure range of the embodiment of the present disclosure.
[0278] To better implement the comic generation method applied to the second electronic device, the disclosure embodiment further provides a comic generation device which can be integrated in the second electronic device. Wherein, the second electronic device can be a terminal device, for example, a conventional computer (desktop computer, notebook computer, etc.), a vehicle-mounted computer, a tablet computer, a smart phone, a personal digital processor or other similar computing device. Hereinafter, a comic generation device 1500 provided by the disclosure embodiment will be described in conjunction with the schematic structural block diagram shown in FIG. 15. Figure 15 The comic generation device 1500 provided by the disclosure embodiment is described in conjunction with the schematic structural block diagram shown in FIG. 15.
[0279] The comic generation device 1500 comprises:
[0280] A script acquisition unit 1501 is configured to acquire a plurality of target shot scripts.
[0281] A comic generation request sending unit 1502 is configured to, in response to a comic generation request processing operation, send a comic generation request carrying the plurality of target shot scripts to a first electronic device; wherein the first electronic device is configured to generate a target comic picture book based on the plurality of target shot scripts carried in the comic generation request, and perform dubbing on the target comic picture book to obtain a first target anime.
[0282] A first anime receiving unit 1503 is configured to receive and play the first target anime.
[0283] In some optional embodiments, the script acquisition unit 1501 is configured to:
[0284] Acquire a target comic theme.
[0285] In response to a script acquisition request processing operation, send a script acquisition request carrying the target comic theme to the first electronic device; wherein the first electronic device is configured to generate a comic story based on the target comic theme carried in the script acquisition request, and split the comic story to obtain a plurality of initial shot scripts.
[0286] Receive and display the plurality of initial shot scripts.
[0287] Obtain the plurality of target shot scripts based on the plurality of initial shot scripts.
[0288] In some optional embodiments, the script acquisition unit 1501 is configured to:
[0289] In response to a comic type setting operation, display a theme setting interface corresponding to a target comic type.
[0290] In response to a comic theme setting operation triggered on the theme setting interface corresponding to the target comic type, obtain the target comic theme.
[0291] In some optional embodiments, the script obtaining unit 1501 is configured to:
[0292] In a case where the main interface of the comic generation webpage has been entered, in response to a comic type setting operation triggered on the main interface of the comic generation webpage, a target comic type is selected from a plurality of candidate comic types to enter a theme setting interface corresponding to the target comic type;
[0293] Alternatively, in response to the comic type setting operation, an original URL is modified to obtain a target URL, so as to enter the theme setting interface corresponding to the target comic type based on the target URL; wherein the original URL points to the main interface of the comic generation webpage.
[0294] In some optional embodiments, the script obtaining unit 1501 is configured to:
[0295] In response to a comic theme setting operation triggered on the theme setting interface corresponding to the target comic type, a target comic theme input in the theme editing window is obtained;
[0296] Alternatively, in response to the comic theme setting operation triggered on the theme setting interface corresponding to the target comic type, a target comic theme is selected from a plurality of candidate comic themes under the target comic type.
[0297] In some optional embodiments, the script obtaining unit 1501 is configured to:
[0298] In response to a script obtaining request processing operation, a script obtaining request carrying the target comic type and the target comic theme is sent to a first electronic device; wherein the first electronic device is configured to generate a comic story based on the target comic type and the target comic theme carried in the script obtaining request, and split the comic story to obtain a plurality of initial shot scripts.
[0299] In some optional embodiments, the script obtaining unit 1501 is configured to:
[0300] In response to a shot script editing operation, the plurality of initial shot scripts are edited to obtain a plurality of target shot scripts.
[0301] In some optional embodiments, the comic generation request sending unit 1502 is configured to:
[0302] Determine a user preference style; wherein the user preference style includes at least one of a target drawing style and a target dubbing style;
[0303] Generate a comic generation request carrying the plurality of target shot scripts and the user preference style;
[0304] In response to the comic generation request processing operation, the comic generation request is sent to the first electronic device; wherein the first electronic device is configured to generate a target comic picture book based on the plurality of target scripts and the user preferred style carried in the comic generation request, and perform dubbing on the target comic picture book to obtain a first target animated comic.
[0305] In some optional embodiments, the comic generation request comprises a comic drawing request and a comic dubbing request, and the comic drawing request carries the plurality of target scripts; the comic generation request sending unit 1502 is configured to:
[0306] In response to the comic drawing operation, the comic drawing request is sent to the first electronic device; wherein the first electronic device is configured to generate an initial comic picture book based on the plurality of target scripts carried in the comic generation request;
[0307] The initial comic picture book is received and displayed;
[0308] In the case where the confirmation operation for the initial comic picture book is detected, in response to the confirmation operation, the comic dubbing request is sent to the first electronic device; wherein the first electronic device is configured to, in response to the comic dubbing request, take the initial comic picture book as a target comic picture book to perform dubbing on the target comic picture book to obtain a first target animated comic.
[0309] In some optional embodiments, the first animated comic receiving unit 1503 is configured to:
[0310] The first electronic device is polled to generate and display a user prompt information in the case where it is determined that the first electronic device has generated a target comic picture book based on the plurality of target scripts carried in the comic generation request, and performed dubbing on the target comic picture book to obtain a first target animated comic.
[0311] In response to the first comic playing operation, the first target animated comic is received and played.
[0312] In some optional embodiments, the comic generation apparatus 1500 further comprises a work sharing request sending unit configured to:
[0313] The work sharing request for the first target animated comic is sent to the first electronic device; wherein the first electronic device is configured to, in response to the work sharing request, store the first target animated comic in a shared comic library.
[0314] In some optional embodiments, the comic generation apparatus 1500 further comprises:
[0315] an audio comic selection request sending unit, configured to, in response to the audio comic selection request processing operation, send an audio comic selection request carrying comic identification information to the first electronic device; wherein the first electronic device is configured to select a second target audio comic from a shared comic library of the first electronic device based on the comic identification information carried in the audio comic selection request;
[0316] The second audio comic receiving unit is configured to receive and play a second target audio comic in response to a second comic playing operation.
[0317] For the description of the specific functions and examples of each unit of the comic generation device 1500 in the embodiment of the present disclosure, please refer to the relevant description of the corresponding steps in the aforementioned embodiment of the comic generation method applied to the service device, and will not be repeated here.
[0318] In order to better implement the comic generation method applied to the first electronic device, the embodiment of the present disclosure also provides a comic generation device, which can be integrated into the first electronic device. The first electronic device can be a server. Figure 16 The schematic structural block diagram shown is used to illustrate a comic generation device 1600 provided in the disclosed embodiment.
[0319] The comic generation device 1600 includes:
[0320] A comic generation request receiving unit 1601 is configured to receive a comic generation request carrying multiple target storyboards;
[0321] The comic generation unit 1602 is configured to generate a target comic book based on the multiple target storyboards carried in the comic generation request, and dub the target comic book to obtain a first target audio comic.
[0322] The first audio comic sending unit 1603 is configured to send the first target audio comic to the second electronic device.
[0323] In some optional implementations, the comic generation device 1600 further includes:
[0324] A script acquisition request receiving unit, configured to receive a script acquisition request carrying a target comic theme;
[0325] A comic story generating unit, configured to generate a comic story based on a target comic theme carried in a script acquisition request;
[0326] An initial storyboard script acquisition unit is used to split the comic story into multiple initial storyboard scripts;
[0327] The target storyboard acquisition unit is used to send multiple initial storyboards to the second electronic device; wherein the second electronic device is used to receive and display the multiple initial storyboards, and obtain multiple target storyboards based on the multiple initial storyboards.
[0328] In some optional implementations, the script acquisition request further carries a target comic genre; the comic story generation unit is configured to:
[0329] Generate a comic story based on the target comic genre and target comic theme carried in the script acquisition request.
[0330] In some optional implementations, the comic generation request further carries a user preferred style, and the user preferred style includes at least one of a target drawing style and a target dubbing style; the comic generation unit 1602 is configured to:
[0331] Based on the multiple target storyboards and user preferred styles carried in the comic generation request, a target comic picture book is generated, and the target comic picture book is dubbed to obtain a first target audio comic.
[0332] In some optional implementations, the comic generation request includes a comic drawing request and a comic dubbing request, and the comic drawing request carries multiple target storyboards; the comic generation unit 1602 is configured to:
[0333] Generate an initial comic book based on multiple target storyboards carried in the comic generation request;
[0334] Sending the initial comic book to a second electronic device; wherein the second electronic device is configured to receive and display the initial comic book;
[0335] When the second electronic device detects a confirmation operation for the initial comic picture book and sends a comic dubbing request to the first electronic device in response to the confirmation operation, the initial comic picture book is used as the target comic picture book in response to the comic dubbing request to dub the target comic picture book to obtain a first target audio comic.
[0336] In some optional implementations, the comic generation device 1600 further includes a shared comic library expansion unit, configured to:
[0337] When a work sharing request for the first target audio comic is received from the second electronic device, the first target audio comic is stored in a shared comic library in response to the work sharing request.
[0338] In some optional implementations, the comic generation device 1600 further includes:
[0339] An audio comic selection request receiving unit, configured to receive an audio comic selection request carrying comic identification information;
[0340] an audio comic selection unit, configured to select a second target audio comic from a shared comic library of the first electronic device based on the comic identification information carried in the audio comic selection request;
[0341] The second audio comic sending unit is configured to send the second target audio comic to the second electronic device.
[0342] For the description of specific functions and examples of each unit of the comic generation device 1600 in the embodiment of the present disclosure, reference can be made to the description of corresponding steps in the aforementioned embodiment of the comic generation method applied to the second electronic device, and will not be repeated here.
[0343] In the technical solutions disclosed herein, the acquisition, storage, and application of user personal information involved comply with the provisions of relevant laws and regulations and do not violate public order and good morals.
[0344] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium, and a computer program product.
[0345] Figure 17 A schematic block diagram of an example electronic device 1700 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are provided as examples only and are not intended to limit the implementation of the present disclosure described and / or claimed herein.
[0346] like Figure 17 As shown, device 1700 includes a computing unit 1701, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 1702 or a computer program loaded from a storage unit 1708 into a random access memory (RAM) 1703. Various programs and data required for the operation of device 1700 can also be stored in RAM 1703. Computing unit 1701, ROM 1702, and RAM 1703 are connected to each other via a bus 1704. An input / output (I / O) interface 1705 is also connected to bus 1704.
[0347] A number of the components in the device 1700 are connected to the I / O interface 1705, including: an input unit 1706, e.g., a keyboard, a mouse, etc.; an output unit 1707, e.g., various types of displays, speakers, etc.; a storage unit 1708, e.g., a magnetic disk, a magneto-optical disk, etc.; and a communication unit 1709, e.g., a network card, a modem, a wireless communication transceiver, etc. The communication unit 1709 allows the device 1700 to exchange information / data with other devices over a computer network, such as the Internet, and / or various telecommunication networks.
[0348] The computing unit 1701 can be various general and / or special purpose processing components with processing and computing capabilities. Some examples of the computing unit 1701 include, but are not limited to, a CPU, a Graphics Processing Unit (GPU), various special-purpose Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Process (DSP), and any appropriate processor, controller, microcontroller, etc. The computing unit 1701 performs various methods and processes described above, e.g., the comic generation method. For example, in some embodiments, the comic generation method can be implemented as a computer software program, which is tangibly contained in a machine-readable medium, e.g., the storage unit 1708. In some embodiments, part or all of the computer program can be loaded and / or installed on the device 1700 via the ROM 1702 and / or the communication unit 1709. When the computer program is loaded to the RAM 1703 and executed by the computing unit 1701, one or more steps in the comic generation method described above can be performed. Alternatively, in other embodiments, the computing unit 1701 can be configured as the comic generation method by any other appropriate means, e.g., by means of firmware.
[0349] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.
[0350] The program code for implementing the method of the present disclosure can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device so that when the program code is executed by the processor or controller, the functions / operations specified in the flow chart and / or block diagram are implemented. The program code can be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.
[0351] In the context of this disclosure, a machine-readable medium can be a tangible medium that contains or stores a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include but is not limited to an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the machine-readable storage medium would include a linearly-programmed electronic storage, a portable computer diskette, a hard disk, a RAM, a ROM, an erasable programmable read-only memory (EPROM) or flash memory, an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
[0352] To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having a display device (e.g., a Cathode Ray Tube (CRT) monitor or a Liquid Crystal Display (LCD)) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.
[0353] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a Local Area Network (LAN), a Wide Area Network (WAN), and the Internet.
[0354] The computer system can include clients and servers. This relationship can be
[0355] The embodiments of the present disclosure further provide a non-transitory computer readable storage medium storing computer instructions, wherein the computer instructions are used to make the computer execute the method for generating a comic.
[0356] The embodiments of the present disclosure further provide a computer program product, comprising a computer program which, when executed by a processor, implements the method for generating a comic.
[0357] It should be understood that the various forms of flow shown above can be used to reorder, add or delete steps. For example, the steps described in the present disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in the present disclosure can be achieved, which is not limited herein. In addition, in the present disclosure, relationship terms such as "first", "second", "third" and the like are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between the entities or operations. In addition, in the present disclosure, "a plurality of" can be understood as at least two.
[0358] The above detailed description does not constitute a limitation on the protection scope of the present disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent replacements and improvements made within the principles of the present disclosure should be included in the protection scope of the present disclosure.
Claims
1. A comic generation method, comprising: Get multiple target storyboards; In response to the comic generation request processing operation, a comic generation request carrying the multiple target storyboards is sent to a first electronic device; wherein the first electronic device is configured to generate a target comic picture book based on the multiple target storyboards carried in the comic generation request, and dub the target comic picture book to obtain a first target audio comic; receiving and playing the first target audio comic; Wherein, obtaining multiple target storyboards includes: In response to a comic type setting operation, a theme setting interface corresponding to a target comic type is displayed; in response to a comic theme setting operation triggered on the theme setting interface corresponding to the target comic type, a target comic theme is obtained; wherein the target comic type is determined from a plurality of candidate comic types; the plurality of candidate comic types are obtained by: obtaining a comprehensive search term collection of an Internet search and discovery platform; selecting a target number of popular search terms related to the comic search task from the comprehensive search term collection; and obtaining the plurality of candidate comic types based on the target number of popular search terms; In response to the script acquisition request processing operation, a script acquisition request carrying the target comic theme is sent to the first electronic device; wherein the first electronic device is configured to generate a comic story based on the target comic theme carried in the script acquisition request, and split the comic story to obtain a plurality of initial storyboard scripts; receiving and displaying the plurality of initial storyboards; Based on the multiple initial storyboards, the multiple target storyboards are obtained.
2. The method according to claim 1, wherein The method of displaying a theme setting interface corresponding to a target comic type in response to a comic type setting operation includes: In a case where the main interface of the comic generation webpage has been entered, in response to the comic type setting operation triggered on the main interface of the comic generation webpage, selecting the target comic type from a plurality of candidate comic types to enter a theme setting interface corresponding to the target comic type; Alternatively, in response to the comic type setting operation, the original resource locator is modified to obtain a target resource locator, so as to enter a theme setting interface corresponding to the target comic type based on the target resource locator; wherein the original resource locator points to the main interface of the comic generation webpage.
3. The method according to claim 1, wherein The step of obtaining the target comic theme in response to a comic theme setting operation triggered on a theme setting interface corresponding to the target comic type includes: In response to the comic theme setting operation triggered on the theme setting interface corresponding to the target comic type, obtaining the target comic theme input in the theme editing window; Alternatively, in response to the comic theme setting operation being triggered on a theme setting interface corresponding to the target comic type, the target comic theme is selected from a plurality of candidate comic themes under the target comic type.
4. The method according to claim 1, wherein The step of sending the script acquisition request carrying the target comic theme to the first electronic device in response to the script acquisition request processing operation includes: In response to the script acquisition request processing operation, a script acquisition request carrying the target comic type and the target comic theme is sent to the first electronic device; wherein the first electronic device is used to generate the comic story based on the target comic type and the target comic theme carried in the script acquisition request, and split the comic story to obtain the multiple initial storyboard scripts.
5. The method according to claim 1, wherein The step of obtaining the plurality of target storyboards based on the plurality of initial storyboards comprises: In response to the storyboard editing operation, the multiple initial storyboards are edited to obtain the multiple target storyboards.
6. The method according to any one of claims 1 to 5, wherein The step of sending the comic generation request carrying the plurality of target storyboards to the first electronic device in response to the comic generation request processing operation includes: Determining a user preferred style; wherein the user preferred style includes at least one of a target painting style and a target dubbing style; generating the comic generation request carrying the plurality of target storyboards and the user preferred style; In response to the comic generation request processing operation, the comic generation request is sent to the first electronic device; wherein the first electronic device is used to generate the target comic picture book based on the multiple target storyboards carried in the comic generation request and the user preferred style, and dub the target comic picture book to obtain the first target audio comic.
7. The method according to any one of claims 1 to 5, wherein The comic generation request includes a comic drawing request and a comic dubbing request, and the comic drawing request carries the multiple target storyboards; and in response to the comic generation request processing operation, sending the comic generation request carrying the multiple target storyboards to the first electronic device includes: In response to the comic drawing operation, sending the comic drawing request to the first electronic device; wherein the first electronic device is configured to generate an initial comic drawing book based on the multiple target storyboards carried in the comic drawing request; Receiving and displaying the initial comic book; When a confirmation operation for the initial comic picture book is detected, a comic dubbing request is sent to the first electronic device in response to the confirmation operation; wherein the first electronic device is used to respond to the comic dubbing request, use the initial comic picture book as the target comic picture book, and dub the target comic picture book to obtain the first target audio comic.
8. The method according to any one of claims 1 to 5, wherein The receiving and playing the first target audio comic includes: polling the first electronic device to generate and display a user prompt message if it is determined that the first electronic device has generated the target comic picture book based on the multiple target storyboards carried in the comic generation request and dubbed the target comic picture book to obtain the first target audio comic; In response to the first comic play operation, the first target audio comic is received and played.
9. The method according to claim 1, further comprising: A work sharing request for the first target audio comic is sent to the first electronic device; wherein the first electronic device is configured to store the first target audio comic in a shared comic library in response to the work sharing request.
10. The method according to claim 1 or 9, further comprising: In response to the audio comic selection request processing operation, sending an audio comic selection request carrying comic identification information to a first electronic device; wherein the first electronic device is configured to select a second target audio comic from a shared comic library of the first electronic device based on the comic identification information carried in the audio comic selection request; In response to the second comic play operation, the second target audio comic is received and played.
11. A comic generation method comprising: receiving a comic generation request carrying multiple target storyboards; Generate a target comic book based on the multiple target storyboards carried in the comic generation request, and dub the target comic book to obtain a first target audio comic; sending the first target audio comic to a second electronic device; The method further comprises: Receive a script acquisition request carrying a target comic type and a target comic theme; wherein the target comic type is acquired by: the second electronic device acquiring a comprehensive search term collection from an Internet search and discovery platform; selecting a target number of popular search terms related to the comic search task from the comprehensive search term collection; obtaining a plurality of candidate comic types based on the target number of popular search terms; and determining the target comic type from the plurality of candidate comic types. Generate a comic story based on the target comic genre and the target comic theme carried in the script acquisition request; Splitting the comic story to obtain multiple initial storyboards; The multiple initial storyboards are sent to the second electronic device; wherein the second electronic device is used to receive and display the multiple initial storyboards, and obtain the multiple target storyboards based on the multiple initial storyboards.
12. The method according to claim 11, wherein The comic generation request further carries a user preferred style, and the user preferred style includes at least one of a target drawing style and a target dubbing style; generating a target comic picture book based on the multiple target storyboards carried in the comic generation request, and dubbing the target comic picture book to obtain a first target audio comic, including: Based on the multiple target storyboards carried in the comic generation request and the user preferred style, the target comic picture book is generated, and the target comic picture book is dubbed to obtain the first target audio comic.
13. The method according to claim 11 or 12, wherein: The comic generation request includes a comic drawing request and a comic dubbing request, and the comic drawing request carries the multiple target storyboards; generating a target comic picture book based on the multiple target storyboards carried in the comic generation request, and dubbing the target comic picture book to obtain a first target audio comic, including: generating an initial comic book based on the multiple target storyboards carried in the comic drawing request; Sending the initial comic book to the second electronic device; wherein the second electronic device is used to receive and display the initial comic book; Upon receiving a comic dubbing request sent by the second electronic device to the first electronic device after detecting a confirmation operation for the initial comic picture book and responding to the confirmation operation, the first target audio comic is obtained by taking the initial comic picture book as the target comic picture book and dubbing the target comic picture book in response to the comic dubbing request.
14. The method according to claim 11, further comprising: When a work sharing request for the first target audio comic is received from the second electronic device, the first target audio comic is stored in a shared comic library in response to the work sharing request.
15. The method according to claim 14, further comprising: receiving an audio comic selection request carrying comic identification information; Selecting a second target audio comic from a shared comic library of the first electronic device based on the comic identification information carried in the audio comic selection request; The second target audio comic is sent to the second electronic device.
16. A comic generation device, comprising: A script acquisition unit, used for acquiring multiple target storyboard scripts; a comic generation request sending unit, configured to, in response to the comic generation request processing operation, send a comic generation request carrying the multiple target storyboards to a first electronic device; wherein the first electronic device is configured to generate a target comic picture book based on the multiple target storyboards carried in the comic generation request, and dub the target comic picture book to obtain a first target audio comic; a first audio comic receiving unit, configured to receive and play the first target audio comic; The script acquisition unit is specifically used to: In response to a comic type setting operation, a theme setting interface corresponding to a target comic type is displayed; in response to a comic theme setting operation triggered on the theme setting interface corresponding to the target comic type, a target comic theme is obtained; wherein the target comic type is determined from a plurality of candidate comic types; the plurality of candidate comic types are obtained by: obtaining a comprehensive search term collection of an Internet search and discovery platform; selecting a target number of popular search terms related to the comic search task from the comprehensive search term collection; and obtaining the plurality of candidate comic types based on the target number of popular search terms; In response to the script acquisition request processing operation, a script acquisition request carrying the target comic theme is sent to the first electronic device; wherein the first electronic device is configured to generate a comic story based on the target comic theme carried in the script acquisition request, and split the comic story to obtain a plurality of initial storyboard scripts; receiving and displaying the plurality of initial storyboards; Based on the multiple initial storyboards, the multiple target storyboards are obtained.
17. A comic generation device, comprising: A script acquisition request receiving unit is configured to receive a script acquisition request carrying a target comic type and a target comic theme; wherein the target comic type is acquired by: the second electronic device acquiring a comprehensive search term collection from an Internet search and discovery platform; selecting a target number of popular search terms related to the comic search task from the comprehensive search term collection; obtaining a plurality of candidate comic types based on the target number of popular search terms; and determining the target comic type from the plurality of candidate comic types. A comic story generating unit, configured to generate a comic story based on the target comic genre and the target comic theme carried in the script acquisition request; An initial storyboard script acquisition unit, configured to split the comic story into multiple initial storyboard scripts; a target storyboard acquiring unit, configured to send the plurality of initial storyboards to the second electronic device; wherein the second electronic device is configured to receive and display the plurality of initial storyboards, and to acquire the plurality of target storyboards based on the plurality of initial storyboards; A comic generation request receiving unit, configured to receive a comic generation request carrying a plurality of target storyboards; a comic generating unit, configured to generate a target comic picture book based on the multiple target storyboards carried in the comic generation request, and dub the target comic picture book to obtain a first target audio comic; The first audio comic sending unit is configured to send the first target audio comic to a second electronic device.
18. An electronic device comprising: at least one processor; a memory communicatively coupled to the at least one processor; The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 15.
19. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to enable the computer to execute the method according to any one of claims 1 to 15.
20. A computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements the method according to any one of claims 1 to 15.