Comic generation method, device, electronic device and storage medium

Abstract

The present disclosure provides a comic generation method, device, electronic device and storage medium, which relate to the field of artificial intelligence, specifically to technical fields such as NLP, large models, LLM, and deep learning. The specific implementation scheme is as follows: obtaining and displaying multiple storyboards; wherein the storyboards are obtained by splitting the story information associated with the target comic to be generated; in response to the confirmation operation of the multiple storyboards, sending a target comic style adapted to the target comic to the server; wherein the target comic style is used by the server to combine the multiple storyboards, determine the object characteristics, and obtain at least one character image that matches the object characteristics; receiving and displaying the character image sent by the server, and sending a target image determined based on the character image to the server; wherein the target image is used by the server to combine the multiple storyboards and the target comic style to generate the target comic; receiving and displaying the target comic sent by the server.

Description

Technical Field

[0001] The present disclosure relates to the field of AI (Artificial Intelligence), specifically to technical fields such as NLP (Natural Language Processing), large models, LLM (Large Language Model), and deep learning, and especially to comic generation methods, devices, electronic devices, and storage media. Background Art

[0002] With the rapid development of mobile internet technology, reading on electronic devices is becoming increasingly popular, and e-comics have become increasingly accepted as part of the reading experience. E-comics are electronic versions of paper comics, and readers can browse them in the same way as they would on paper. Summary of the Invention

[0003] The present disclosure provides a method, apparatus, electronic device, and storage medium for generating comics.

[0004] According to a first aspect of the present disclosure, a comic generation method is provided, comprising:

[0005] Acquire and display a plurality of storyboards; wherein the storyboards are obtained by splitting story information associated with a target comic to be generated;

[0006] In response to a confirmation operation on the plurality of storyboards, a target comic style adapted to the target comic is sent to a server; wherein the target comic style is used by the server to determine object features by combining the plurality of storyboards and to obtain at least one character image matching the object features;

[0007] receiving and displaying the character image sent by the server, and sending a target image determined based on the character image to the server; wherein the target image is used by the server to generate the target comic by combining the multiple storyboards and the target comic style;

[0008] Receive and display the target comic sent by the server.

[0009] According to a second aspect of the present disclosure, another comic generation method is provided, comprising:

[0010] Acquire story information associated with a target comic to be generated, and split the story information to obtain multiple storyboards;

[0011] Sending the plurality of storyboards to a client, and receiving a target comic style sent by the client in response to a confirmation operation on the plurality of storyboards;

[0012] Determining at least one object feature according to the plurality of storyboards and the target comic style, and acquiring a character image matching the object feature;

[0013] sending the character image to the client, and receiving a target image sent by the client; wherein the target image is determined based on the character image;

[0014] Based on the character image, the multiple storyboards and the target comic style, the target comic is generated and sent to the client.

[0015] According to a third aspect of the present disclosure, there is provided a comic generation device, comprising:

[0016] An acquisition and display module is used to acquire and display a plurality of storyboards; wherein the storyboards are obtained by splitting the story information associated with the target comic to be generated;

[0017] a sending module configured to send a target comic style adapted to the target comic to a server in response to a confirmation operation on the plurality of storyboards; wherein the target comic style is used by the server to determine object features based on the plurality of storyboards and to obtain at least one character image matching the object features;

[0018] A receiving and displaying module, configured to receive and display the character image sent by the server;

[0019] The sending module is further configured to send a target image determined based on the character image to the server; wherein the target image is used by the server to generate the target comic by combining the multiple storyboards and the target comic style;

[0020] The receiving and displaying module is further configured to receive and display the target comic sent by the server.

[0021] According to a fourth aspect of the present disclosure, another comic generation device is provided, comprising:

[0022] An acquisition and splitting module is used to acquire story information associated with the target comic to be generated, and split the story information to obtain multiple storyboards;

[0023] a transceiver module, configured to send the plurality of storyboards to a client, and receive a target comic style sent by the client in response to a confirmation operation on the plurality of storyboards;

[0024] a processing module, configured to determine at least one object feature based on the plurality of storyboards and the target comic style, and obtain a character image matching the object feature;

[0025] The transceiver module is further configured to send the character image to the client and receive a target image sent by the client; wherein the target image is determined based on the character image;

[0026] A generating module, configured to generate the target comic based on the character image, the plurality of storyboards, and the target comic style;

[0027] The transceiver module is further configured to send the target comic to the client.

[0028] According to a fifth aspect of the present disclosure, there is provided an electronic device, including:

[0029] at least one processor; and

[0030] a memory communicatively connected to the at least one processor; wherein,

[0031] 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 so that the at least one processor can execute the comic generation method proposed in the first aspect of the present disclosure, or execute the comic generation method proposed in the second aspect of the present disclosure.

[0032] According to a sixth aspect of the present disclosure, a non-transitory computer-readable storage medium of computer instructions is provided, wherein the computer instructions are used to enable the computer to execute the comic generation method proposed in the first aspect of the present disclosure, or to execute the comic generation method proposed in the second aspect of the present disclosure.

[0033] According to a seventh aspect of the present disclosure, a computer program product is provided, comprising a computer program, wherein when executed by a processor, the computer program implements the comic generation method proposed in the above-mentioned first aspect of the present disclosure, or, when executed, implements the comic generation method proposed in the above-mentioned second aspect of the present disclosure.

[0034] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] The accompanying drawings are provided to facilitate a better understanding of the present invention and do not constitute a limitation of the present disclosure.

[0036] Figure 1This is a flowchart of the comic generation method provided in the first embodiment of the present disclosure;

[0037] Figure 2 This is a flowchart of the comic generation method provided in the second embodiment of the present disclosure;

[0038] Figure 3 Schematic diagram of the display interface of the client provided in the embodiment of the present disclosure Figure 1 ;

[0039] Figure 4 Schematic diagram of the display interface of the client provided in the embodiment of the present disclosure Figure 2 ;

[0040] Figure 5 This is a flowchart of the comic generation method provided in the third embodiment of the present disclosure;

[0041] Figure 6 Schematic diagram of the display interface of the client provided in the embodiment of the present disclosure Figure 3 ;

[0042] Figure 7 Schematic diagram of the display interface of the client provided in the embodiment of the present disclosure Figure 4 ;

[0043] Figure 8 Schematic diagram of the display interface of the client provided in the embodiment of the present disclosure Figure 5 ;

[0044] Figure 9 This is a flowchart of the comic generation method provided in the fourth embodiment of the present disclosure;

[0045] Figure 10 Schematic diagram of the display interface of the client provided in the embodiment of the present disclosure Figure 6 ;

[0046] Figure 11 Schematic diagram of the display interface of the client provided in the embodiment of the present disclosure Figure 7 ;

[0047] Figure 12 This is a flowchart of the comic generation method provided in the fifth embodiment of the present disclosure;

[0048] Figure 13 This is a flowchart of the comic generation method provided in the sixth embodiment of the present disclosure;

[0049] Figure 14 This is a flowchart of the comic generation method provided in the seventh embodiment of the present disclosure;

[0050] Figure 15 This is a structural diagram of a comic generation device provided in the eighth embodiment of the present disclosure;

[0051] Figure 16 This is a structural diagram of a comic generation device provided in Example 9 of the present disclosure;

[0052] Figure 17 A schematic block diagram of an example electronic device that can be used to implement embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0053] The following description of exemplary embodiments of the present disclosure is made in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding. These details should be considered as merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0054] At present, the manual creation of electronic comics by comic creators or comic enthusiasts has a high creation threshold, a long creation cycle, and low creation efficiency and output.

[0055] Therefore, in order to solve the above-mentioned problems, the present disclosure proposes a comic generation method, device, electronic device and storage medium.

[0056] The following describes the comic book generation method, device, electronic device, and storage medium of the embodiments of the present disclosure with reference to the accompanying drawings. Before describing the embodiments of the present disclosure in detail, for ease of understanding, the following common technical terms are introduced:

[0057] Large models are machine learning models with large parameters and complex computational structures. They are typically built from deep neural networks and contain billions or even hundreds of billions of parameters. Large models are designed to improve their expressiveness and predictive performance, enabling them to handle more complex tasks and data. Large models are widely used in various fields, including natural language processing, computer vision, speech recognition, and recommendation systems.

[0058] The LLM in the large model is a type of natural language processing model based on deep learning. Its main features are huge model parameters and complex neural network structure, strong language understanding, context perception and language generation capabilities, and it can automatically learn useful feature representations from input data and generate relevant text.

[0059] Figure 1 This is a flowchart of the comic generation method provided in the first embodiment of the present disclosure.

[0060] The comic generation method of the embodiment of the present disclosure can be applied to a client terminal, where the client terminal refers to a software program running on an electronic device to provide services to users.

[0061] Among them, the electronic device can be any device with computing capabilities, such as a personal computer, mobile terminal, etc. The mobile terminal can be, for example, a mobile phone, tablet computer, personal digital assistant, wearable device, etc., which are hardware devices with various operating systems, touch screens and / or display screens.

[0062] like Figure 1 As shown, the comic generation method may include the following steps:

[0063] Step S101: Acquire and display multiple storyboards.

[0064] In the disclosed embodiment, the storyboards are obtained by splitting the story information associated with the target comic to be generated. For example, the story information can be split based on the plot and / or key scenes in the story information to obtain multiple storyboards.

[0065] In the disclosed embodiment, the client may obtain multiple storyboards and display the multiple storyboards.

[0066] Step S102, in response to the confirmation operation of multiple storyboards, sends a target comic style adapted to the target comic to the server; wherein, the target comic style is used by the server to combine multiple storyboards, determine object features, and obtain at least one character image matching the object features.

[0067] The target comic styles include but are not limited to: a certain series of cartoons (i.e. cartoons with a certain characteristic or style, for example, series A cartoons (such as cartoons in the style of country A, cartoons in the style of country B, etc.)), romantic thick painting, exquisite realism, fresh and cute style, etc.

[0068] The objects include but are not limited to humans, animals, etc.

[0069] In an embodiment of the present disclosure, the client can send a comic style that is compatible with the target comic (referred to as the target comic style in the present disclosure) to the server in response to a user-triggered confirmation operation of multiple storyboards. Accordingly, after receiving the target comic style, the server can determine the object characteristics (for example, taking the object as a person as an example, the object characteristics can be character characteristics) based on the target comic style and multiple storyboards, and determine at least one character image that matches the object characteristics from multiple character images in the character library.

[0070] As an example, the server can use a large model (or LLM) to extract or determine object features (such as character features) based on the target comic style and multiple storyboards, and determine a character image that matches the object features from multiple character images in the character library.

[0071] As another example, the server can extract image features (e.g., character image features) and era features (e.g., era features of the character's historical background (such as ancient, modern, etc.)) from multiple storyboards, and determine the object features by combining the image features, era features, and target comic style, so as to determine the character image that matches the object features from the multiple character images in the character library.

[0072] For example, taking the object as a character, assuming that the object feature indicates that the era background of the character is era A, the character image is a fashionable girl wearing cheongsam, and the target comic style is humorous comics, then the character image with gender label of female, clothing label of cheongsam, style label of humor, and era label of era A in the character library can be used as the character image that matches the object feature.

[0073] Step S103, receiving and displaying the character image sent by the server, and sending a target image determined based on the character image to the server; wherein the target image is used by the server to combine multiple storyboards and target comic styles to generate a target comic.

[0074] In an embodiment of the present disclosure, the client can receive and display the character image sent by the server, and determine the target character image required by the user (referred to as the target image in this disclosure) based on the character image. Afterwards, the client can send the target image to the server.

[0075] Correspondingly, after receiving the target image, the server can combine multiple storyboards, target comic style and target image to generate the target comic.

[0076] As an example, the server can use a large model to generate a target comic based on multiple storyboards, a target comic style, and a target image.

[0077] As another example, the server can generate a storyboard comic corresponding to each storyboard based on the character image, each storyboard and the target comic style, and splice the storyboard comics of multiple storyboards according to the storyboard order between the multiple storyboards to obtain the target comic.

[0078] Among them, the storyboard order refers to arranging multiple storyboards in chronological order.

[0079] Step S104: Receive and display the target comic sent by the server.

[0080] In the disclosed embodiment, the client can also receive and display the target comic sent by the server.

[0081] The comic generation method of the embodiment of the present disclosure can determine a character image that is suitable for the comic to be generated based on multiple storyboards and comic styles associated with the comic, and automatically generate the comic based on the character image, multiple storyboards and comic style. This can shorten the comic creation cycle and lower the threshold for comic creation, so that ordinary comic lovers can also realize their dream of comic creation and improve the user experience.

[0082] It should be noted that in the technical solutions disclosed herein, the collection, storage, use, processing, transmission, provision and disclosure of user personal information are all carried out with the user's consent, and are in compliance with relevant laws and regulations and do not violate public order and good morals.

[0083] In order to clearly illustrate how the client obtains and displays multiple storyboards in any embodiment of the present disclosure, the present disclosure also proposes a comic generation method.

[0084] Figure 2 This is a flowchart of the comic generation method provided in the second embodiment of the present disclosure.

[0085] like Figure 2 As shown, the comic generation method may include the following steps:

[0086] Step S201: Acquire text information associated with the target comic to be generated.

[0087] The text information may be input or uploaded by a user on the client side, wherein input methods include but are not limited to touch input (such as sliding, clicking, etc.), keyboard input, voice input, etc.

[0088] In an embodiment of the present disclosure, the client may obtain text information associated with the target comic to be generated.

[0089] As a possible implementation method, the client may obtain subject information associated with the target comic and generate text information according to the subject information.

[0090] The theme information is used to indicate the theme of the target comic, and the theme information may be input by the user.

[0091] As another possible implementation manner, the client may obtain keyword information associated with the target comic and generate text information according to the keyword information.

[0092] The keyword information is used to indicate keywords related to the target comic, and the keyword information may also be input by the user.

[0093] As another possible implementation manner, the client may obtain a first input text associated with the target comic, and generate text information according to the first input text.

[0094] The first input text is input by the user. For example, the first input text may be document content input by the user online.

[0095] As another possible implementation manner, the client may obtain a target document associated with the target comic and extract text information from the target document.

[0096] The target document may be a local document uploaded by the user.

[0097] It should be noted that the target document may contain a large amount of character information. Generating a story based on the full amount of character information in the target document not only imposes a heavy processing burden, but also some of the character information in the target document may be irrelevant to the target comic to be generated. In this case, if the story is generated based on the full amount of character information, the generation quality of the target comic may also be reduced. Therefore, considering the above problems, in the present disclosure, text information associated with the target comic can be extracted from the target document.

[0098] For example, the user may select or intercept the text information from the target document, that is, the user may adjust the interception range of the document content.

[0099] In summary, it is possible to obtain text information associated with the target comic in different ways, which can improve the flexibility and applicability of the method.

[0100] As an example, the client's display interface can be as follows Figure 3 As shown, the user can select a comic generation method by clicking on multiple options in area 31. For example, if the user clicks on the option "Input theme to generate comic" shown in area 311, the comic theme can be entered in the input box shown in area 32, so that the client can use the comic theme as text information associated with the comic.

[0101] Step S202, sending text information to the server; wherein the text information is used by the server to generate story information associated with the target comic, and split the story information to obtain multiple storyboards.

[0102] In the disclosed embodiment, the client can send text information associated with the target comic to the server. Accordingly, after receiving the text information, the server can generate story information associated with the target comic based on the text information. For example, the server can use a large model (or LLM) to generate story information associated with the target comic based on the text information. Afterwards, the server can split the story information to obtain multiple storyboards.

[0103] As an example, the server may split the story information based on the plot and / or key scenes in the story information to obtain multiple storyboards.

[0104] Step S203: Receive and display multiple storyboards sent by the server.

[0105] In an embodiment of the present disclosure, the client may receive multiple storyboards sent by the server and display the multiple storyboards.

[0106] As an example, suppose the text message is Figure 3 Taking the online document content shown in area 33 as an example, the story information generated by the server based on the text information can be as follows Figure 4 As shown in the middle area 41 , the server splits the story information, and the resulting multiple storyboards may be as shown in area 42 .

[0107] Step S204, in response to the confirmation operation of the multiple storyboards, sending a target comic style adapted to the target comic to the server; wherein the target comic style is used by the server to combine the multiple storyboards, determine the object features, and obtain at least one character image matching the object features.

[0108] Step S205, receiving and displaying the character image sent by the server, and sending a target image determined based on the character image to the server; wherein the target image is used by the server to combine multiple storyboards and target comic styles to generate a target comic.

[0109] Step S206: Receive and display the target comic sent by the server.

[0110] For explanations of steps S204 to S206 , reference may be made to the relevant descriptions in any embodiment of the present disclosure, and no further details will be given here.

[0111] The comic generation method of the disclosed embodiment can realize that a server with strong computing power can automatically generate story information associated with a target comic based on simple text input by a user, and split the story information to obtain multiple storyboards. This can not only improve the efficiency of obtaining storyboards, but also improve the quality of obtaining storyboards.

[0112] In order to clearly illustrate how the client determines a target comic style that is adapted to the target comic in any embodiment of the present disclosure, the present disclosure also proposes a comic generation method.

[0113] Figure 5 This is a flowchart of the comic generation method provided in the third embodiment of the present disclosure.

[0114] like Figure 5 As shown, the comic generation method may include the following steps:

[0115] Step S501, obtaining and displaying a plurality of storyboards; wherein the storyboards are obtained by splitting the story information associated with the target comic to be generated.

[0116] For explanation of step S501, please refer to the relevant description in any embodiment of the present disclosure, and will not be repeated here.

[0117] Step S502 : In response to the confirmation operation on the multiple storyboards, render and display multiple candidate comic styles.

[0118] Among them, candidate comic styles include but are not limited to: certain cartoons, romantic thick painting, exquisite realism, fresh and cute style, etc.

[0119] In an embodiment of the present disclosure, the client may render and display multiple candidate comic styles in response to a user-triggered confirmation operation on multiple storyboards.

[0120] Step S503 : In response to the style selection operation, a target comic style is selected from a plurality of candidate comic styles.

[0121] In an embodiment of the present disclosure, the client may select a target comic style that is compatible with the target comic from a plurality of candidate comic styles in response to a style selection operation triggered by the user.

[0122] As an example, a user can click Figure 4 The "Next" button in Figure 6 The user can click on the multiple candidate comic styles shown. Figure 6 A candidate comic style in is used as the target comic style adapted to the target comic.

[0123] Step S504: sending the target comic style to the server; wherein the target comic style is used by the server to combine multiple storyboards, determine object features, and obtain at least one character image that matches the object features.

[0124] In an embodiment of the present disclosure, the client can send a target comic style that is adapted to the target comic to the server. Accordingly, after receiving the target comic style, the server can determine the object features based on the target comic style and multiple storyboards, and determine at least one character image that matches the object features from multiple character images in the character library.

[0125] Step S505, receiving and displaying the character image sent by the server, and sending the target image determined based on the character image to the server; wherein the target image is used by the server to combine multiple storyboards and target comic styles to generate a target comic.

[0126] For explanation of step S505, please refer to the relevant description in any embodiment of the present disclosure, and will not be repeated here.

[0127] In any embodiment of the present disclosure, the client may select a target image from the character images in response to a first image selection operation triggered by the user, and send the target image to the server.

[0128] As an example, users can click Figure 6 Click the "Next" button in the target comic style to send it to the server. After the server determines the character image that is suitable for the target comic style and multiple storyboards, it can send the character image to the client. For example, the character image displayed by the client can be as follows: Figure 7 As shown, users can click Figure 7 A character image in is used as the target image.

[0129] In any embodiment of the present disclosure, when the target image required by the user does not exist in the character image, the client can obtain the image description information input by the user and send the image description information to the server.

[0130] As an example, the user can Figure 8 In the text box shown in the middle area 81, enter the image description information.

[0131] Accordingly, after receiving the image description information, the server can regenerate the character image (referred to as a candidate image in this disclosure) based on the image description information and the target comic style. For example, the server can use a large model to generate a candidate image based on the image description information and the target comic style. Afterwards, the server can send the candidate image to the client. Accordingly, the client can receive and display the candidate image sent by the server, so that the user can select the target image from the candidate images. That is, the client can select the target image from the candidate images in response to the second image selection operation triggered by the user. Afterwards, the client can send the target image to the server.

[0132] In summary, when the character image sent by the server cannot meet the user's comic creation needs, the user can input image description information to regenerate the target image that meets the user's actual needs based on the image description information, so that the subsequently generated target comic can meet the user's personalized creation needs and improve the user's usage experience.

[0133] Step S506: Receive and display the target comic sent by the server.

[0134] The comic generation method of the disclosed embodiment can enable users to select a target comic style that is compatible with the target comic from multiple candidate comic styles based on their own comic creation needs, thereby improving the personalization of comic creation.

[0135] In order to clearly illustrate any embodiment of the present disclosure, the present disclosure also proposes a comic generation method.

[0136] Figure 9 This is a flowchart of the comic generation method provided in the fourth embodiment of the present disclosure.

[0137] like Figure 9 As shown, the comic generation method may include the following steps:

[0138] Step S901: Acquire and display multiple storyboards.

[0139] The storyboards are obtained by splitting the story information associated with the target comic to be generated.

[0140] For explanation of step S901, please refer to the relevant description in any embodiment of the present disclosure, and will not be repeated here.

[0141] In any embodiment of the present disclosure, if the storyboards generated by the server do not meet the user's comic creation needs, the user can update the story information associated with the target comic so that the server can regenerate multiple storyboards based on the updated story information.

[0142] As an example, the client can also receive and display the story information and title information of the story information sent by the server. Afterwards, the client can update the story information in response to a story update operation triggered by the user and send the updated story information to the server.

[0143] Accordingly, after receiving the updated story information, the server can divide the updated story information to obtain multiple regenerated story stories and send the multiple regenerated story stories to the client. Accordingly, the client can receive and display the multiple regenerated story stories sent by the server.

[0144] In this way, users can dynamically update the story information and storyboards that are compatible with the target comics based on their actual comic creation needs, so that the subsequently generated target comics can meet the user's personalized creation needs.

[0145] In any embodiment of the present disclosure, if the storyboard generated by the server does not meet the user's comic creation needs, the user can update the storyboard so that the server can generate the target comic based on the updated storyboard.

[0146] As an example, the client may also update at least one storyboard among the multiple storyboards in response to a storyboard update operation triggered by the user.

[0147] In this way, users can dynamically update any storyboard according to their actual comic creation needs, so that the target comic generated subsequently can meet the user's personalized creation needs.

[0148] Step S902, in response to the confirmation operation of multiple storyboards, sending a target comic style adapted to the target comic to the server; wherein the target comic style is used by the server to combine multiple storyboards, determine object features, and obtain at least one character image matching the object features.

[0149] Step S903, receiving and displaying the character image sent by the server, and sending the target image determined based on the character image to the server; wherein the target image is used by the server to combine multiple storyboards and target comic styles to generate a target comic.

[0150] Step S904: Receive and display the target comic sent by the server.

[0151] For explanations of steps S902 to S904 , reference may be made to the relevant descriptions in any embodiment of the present disclosure, and no further details will be given here.

[0152] Step S905 : In response to the comic update operation, obtain the picture description information for the first picture in the target comic.

[0153] The first screen is the screen selected by the user. The number of the first screens may be one or more, which is not limited in the embodiment of the present disclosure.

[0154] In the disclosed embodiment, if a comic frame in a target comic generated by the server does not meet the user's actual creative needs, the user can update the comic frame. First, in response to the comic update operation triggered by the user, the client can select the first frame from the target comic and obtain the frame description information for the first frame input by the user.

[0155] As an example, users can Figure 10 The text box shown in the middle area 1001 is used to input screen description information for the first screen.

[0156] Step S906: Send the picture description information to the server; wherein the picture description information is used by the server to generate a second picture that matches the picture description information and the target comic style.

[0157] In an embodiment of the present disclosure, the client may send the picture description information to the server, so that the server generates a second picture matching the picture description information and the target comic style based on the picture description information and the target comic style.

[0158] Step S907: Receive the second frame sent by the server, and use the second frame to update the first frame in the target comic.

[0159] In the embodiment of the present disclosure, the client may receive the second frame sent by the server, and use the second frame to update the first frame in the target comic.

[0160] In any embodiment of the present disclosure, the user may also add props to the target comic and / or adjust the layout position of the comic screen in the target comic.

[0161] As an example, in response to a comic editing operation triggered by a user, the client may select a target prop from a plurality of displayed candidate props, and update at least one third frame in the target comic using the target prop.

[0162] Among them, the third screen is the screen selected by the user, and the target props include but are not limited to: text; stickers; filters; background; animation effects, etc.

[0163] For example, the user can select Figure 11 The props shown in the middle area 1101 are used to update the selected third screen.

[0164] As an example, the client can update the layout position of at least one fourth frame in the target comic in response to a layout update operation triggered by the user. For example, the user can update the layout position of the fourth frame by dragging and dropping.

[0165] Among them, the fourth picture is the picture selected by the user.

[0166] In summary, users can add props to the target comic and / or adjust the layout position of the pictures in the target comic according to their actual comic creation needs, which can improve the overall quality of the target comic and further meet the user's personalized comic creation needs.

[0167] The comic generation method of the disclosed embodiment can enable users to update the picture content in the target comic according to their actual comic creation needs, thereby further meeting the personalized comic creation needs of different users.

[0168] The above are various method embodiments executed by the client. The present disclosure also proposes a comic generation method executed by the server.

[0169] Figure 12This is a flowchart of the comic generation method provided in the fifth embodiment of the present disclosure.

[0170] The comic generation method of the embodiment of the present disclosure can be applied to a server.

[0171] like Figure 12 As shown, the comic generation method may include the following steps:

[0172] Step S1201: Acquire story information associated with the target comic to be generated, and split the story information to obtain multiple storyboards.

[0173] Step S1202: Send multiple storyboards to the client, and receive a target comic style sent by the client in response to a confirmation operation on the multiple storyboards.

[0174] Step S1203: Determine at least one object feature based on the multiple storyboards and the target comic style, and obtain a character image that matches the object feature.

[0175] Step S1204: sending the character image to the client, and receiving the target image sent by the client; wherein the target image is determined based on the character image.

[0176] Step S1205: Generate a target comic based on the character image, multiple storyboards, and the target comic style, and send the target comic to the client.

[0177] It should be noted that the explanations of the various method embodiments executed by the client in the aforementioned embodiments are also applicable to this embodiment, and the implementation principles are similar, so they will not be elaborated here.

[0178] The comic generation method of the embodiment of the present disclosure can determine a character image that is suitable for the comic to be generated based on multiple storyboards and comic styles associated with the comic, and automatically generate the comic based on the character image, multiple storyboards and comic style. This can shorten the comic creation cycle and lower the threshold for comic creation, so that ordinary comic lovers can also realize their dream of comic creation and improve the user experience.

[0179] In order to clearly illustrate how the server in the above embodiment obtains story information associated with the target comic to be generated and splits the story information to obtain multiple storyboards, the present disclosure also proposes a comic generation method.

[0180] Figure 13 This is a flowchart of the comic generation method provided in Example 6 of the present disclosure.

[0181] The comic generation method of the embodiment of the present disclosure can be applied to a server.

[0182] like Figure 13 As shown, the comic generation method may include the following steps:

[0183] Step S1301: receiving text information associated with a target comic to be generated from a client.

[0184] The text information may be input or uploaded by a user on the client side, and the input method may include but is not limited to touch input (such as sliding, clicking, etc.), keyboard input, voice input, etc.

[0185] In an embodiment of the present disclosure, the client may obtain text information associated with the target comic to be generated, and send the text information to the server.

[0186] As a possible implementation method, the client may obtain subject information associated with the target comic and generate text information according to the subject information.

[0187] The theme information is used to indicate the theme of the target comic, and the theme information may be input by the user.

[0188] As another possible implementation manner, the client may obtain keyword information associated with the target comic and generate text information according to the keyword information.

[0189] The keyword information is used to indicate keywords related to the target comic, and the keyword information may also be input by the user.

[0190] As another possible implementation manner, the client may obtain a first input text associated with the target comic, and generate text information according to the first input text.

[0191] The first input text is input by the user. For example, the first input text may be document content input by the user online.

[0192] As another possible implementation manner, the client may obtain a target document associated with the target comic and extract text information from the target document.

[0193] Step S1302: Call the large model to generate story information associated with the target comic based on the text information.

[0194] In the embodiment of the present disclosure, after receiving text information adapted to the target comic, the server can call the big model to generate story information associated with the target comic based on the text information.

[0195] Step S1303: split the story information based on the storyline and / or key scenes in the story information to obtain multiple storyboards.

[0196] In the disclosed embodiment, the server may split the story information based on the storyline and / or key scenes in the story information to obtain multiple storyboards.

[0197] Step S1304: sending a plurality of storyboards to the client, and receiving a target comic style sent by the client in response to a confirmation operation on the plurality of storyboards.

[0198] Step S1305 , determining at least one object feature based on the multiple storyboards and the target comic style, and obtaining a character image that matches the object feature.

[0199] Step S1306: sending the character image to the client, and receiving the target image sent by the client; wherein the target image is determined based on the character image.

[0200] Step S1307: Generate a target comic based on the character image, multiple storyboards, and the target comic style, and send the target comic to the client.

[0201] For explanations of steps S1304 to S1307 , reference may be made to the relevant descriptions in any embodiment of the present disclosure and will not be repeated here.

[0202] The comic generation method of the embodiment of the present disclosure uses a large model with large-scale parameters and complex computing structure to generate story information, which can improve the generation quality of the story information, and then generate the target comic based on the high-quality story information, which can improve the generation quality of the target comic.

[0203] In order to clearly illustrate how the server in the above embodiment determines at least one object feature based on multiple storyboards and the target comic style, and obtains a character image that matches the object feature, the present disclosure also proposes a comic generation method.

[0204] Figure 14 This is a flowchart of the comic generation method provided in Example 7 of the present disclosure.

[0205] The comic generation method of the embodiment of the present disclosure can be applied to a server.

[0206] like Figure 14 As shown, the comic generation method may include the following steps:

[0207] Step S1401: Acquire story information associated with the target comic to be generated, and split the story information to obtain multiple storyboards.

[0208] Step S1402: Send multiple storyboards to the client, and receive a target comic style sent by the client in response to a confirmation operation on the multiple storyboards.

[0209] For explanations of steps S1401 to S1402 , reference may be made to the relevant descriptions in any embodiment of the present disclosure and will not be repeated here.

[0210] Step S1403: extracting image features and era features from multiple storyboards.

[0211] Among them, image characteristics are used to indicate the image of the subject (such as a character) in the story information, and era characteristics are used to indicate the era background (such as ancient times, modern times, etc.) in which the subject is located.

[0212] As an example, the server can call a large model to extract features from multiple storyboards to obtain the image features and era characteristics of the subject.

[0213] Step S1404: Determine object features based on image features, era features, and target comic style.

[0214] In the disclosed embodiment, the server may determine the object characteristics by combining the image characteristics, the era characteristics and the target comic style.

[0215] Step S1405 , determining a character image that matches the object feature from a plurality of character images in the character library.

[0216] In the embodiment of the present disclosure, the server may determine a character image that matches the object feature from a plurality of character images in the character library.

[0217] For example, taking the object as a character, assuming that the object feature indicates that the era background of the character is era A, the character image is a fashionable girl wearing cheongsam, and the target comic style is humorous comics, then the character image with gender label of female, clothing label of cheongsam, style label of humor, and era label of era A in the character library can be used as the character image that matches the object feature.

[0218] Step S1406: sending the character image to the client, and receiving the target image sent by the client; wherein the target image is determined based on the character image.

[0219] Step S1407: Generate a target comic based on the character image, multiple storyboards, and the target comic style, and send the target comic to the client.

[0220] For explanations of steps S1406 to S1407, please refer to the relevant descriptions in any embodiment of the present disclosure and will not be repeated here.

[0221] In any embodiment of the present disclosure, the server can generate a storyboard comic corresponding to each storyboard based on the character image, each storyboard and the target comic style, and splice the storyboard comics of multiple storyboards according to the storyboard order between the multiple storyboards to obtain the target comic.

[0222] Among them, the storyboard order refers to arranging multiple storyboards in chronological order.

[0223] Therefore, by creating each storyboard comic separately, it is possible to achieve more refined comic design and expression based on the characteristics and needs of each storyboard. This flexibility helps to better show the storyline, character personality and emotional changes, thereby enhancing the attractiveness and appeal of the comic. In addition, splicing the storyboard comics of multiple storyboards according to the storyboard order between multiple storyboards can ensure that the final comic maintains visual coherence and smoothness. This coherence helps readers better understand the development of the plot and enhance the reading experience.

[0224] The comic generation method of the disclosed embodiment combines the image characteristics and era characteristics of the story subjects (such as characters) in multiple storyboards and the target comic style to determine the character image that is compatible with the target comic from the character library, so that the selected character image can meet the user's actual comic creation needs and improve the user experience.

[0225] In any of the embodiments of the present disclosure, the capabilities of the AI ​​big model can be used to help comic creators improve the efficiency of comic production, shorten the creative cycle of comic creators, increase output, and enhance the richness of comic styles, comic quality, character consistency, and style consistency; at the same time, it can lower the threshold for comic creation, allowing comic enthusiasts to realize their dream of comic creation.

[0226] As an example, the implementation principle of AI-generated comics can include the following parts:

[0227] Part 1: Text extraction to generate stories.

[0228] Three methods of extracting text content can be provided to users. Among them, in method one, the user enters a subject word or keyword, and the big model will generate a complete story information (i.e., a comic story) based on the subject word or keyword, and automatically split the story information to obtain multiple story frames (or comic frames) for users to view and edit; method two, based on the current online document content, the big model automatically refines the online document content and generates story information, and automatically splits the story information to obtain multiple story frames (or comic frames); method three, the user uploads a local document, and the big model will automatically generate story information and story frames based on the document content in the local document.

[0229] That is, in the present disclosure, the user's text appeal can be identified based on three methods: user-entered subject words or keywords, written document content, or uploaded existing local documents. Based on the text analysis capabilities of the large model, the user's input content can be extracted, and a complete comic story can be intelligently generated and automatically split into storyboards.

[0230] That is to say, in this disclosure, three comic generation methods can be provided for users, such as: input keywords to generate comics, upload documents to generate comics, and generate comics based on Figure 3 The left middle area (i.e. Figure 3 Generate comic strips in area 33).

[0231] Furthermore, users can adjust the scope of document content selection and generate related storyboards based on the selected document content. Similarly, users can modify the storyboards as desired. In other words, a large model can be used to generate complete story information for users and automatically create storyboards. Users can then adjust the story information and storyboard content according to their own requirements.

[0232] The second part is to select the comic style. In the next step of generating storyboards (or comic storyboards), users are provided with a variety of mainstream comic styles (such as Figure 6 for users to choose.

[0233] For example, after confirming that there are no other problems with the storyboard, the user can enter the comic style selection stage.

[0234] The third step is character selection. After the user selects a comic style, they will enter the character image selection stage. The large model will extract corresponding object characteristics (such as character features) based on the storyboard and the selected comic style, intelligently match the set character library, and present the most relevant character image for the user to choose. If the user is not satisfied with the provided character image, they can choose to enter an image description (indicating the user's desired character image), and the large model will immediately generate a new character image to meet the user's needs.

[0235] That is, after the user confirms the comic style, the big model will extract relevant story characters based on the user's storyline, and match them with character images that fit the story characters, for the user to choose the required character image. If the user is not satisfied with all the character images, the user can enter the image description information they need, and the big model will immediately generate a new character image based on the image description information. After the user confirms the character image, the complete comic can be generated.

[0236] The fourth part is comic frame regeneration. After the complete comic is generated, the user can view each frame in the comic. If the user is not satisfied with a certain frame, they can add or modify the frame description information to produce a new comic frame. For example, if the user is dissatisfied with any frame, they can choose to regenerate the frame. The large model can immediately generate a frame that meets the requirements based on the user's description information, while maintaining the consistency of the frame style.

[0237] The fifth part, comic post-editing, provides users with basic comic capabilities, allowing them to easily edit text, add speech bubbles, and special effects, and freely adjust the comic's image and layout, making it easier for users to create beautiful comics. For example, it provides editor capabilities to meet users' needs for editing text and graphics within comics, while also supporting the editing of comic images and overall typesetting capabilities, ensuring comic post-processing capabilities and outputting excellent comic works.

[0238] That is, after the comic is generated, the user can request to regenerate any picture in the comic. The large model will immediately generate a new picture according to the user's requirements. Moreover, the entire comic area supports user editing, which makes it convenient to modify the layout, dialogue, special effects and other elements of the comic to improve the overall quality of the comic.

[0239] With the above Figures 1 to 9 Corresponding to the comic generation method provided in the embodiment, the present disclosure also provides a comic generation device. Since the comic generation device provided in the embodiment of the present disclosure is similar to the above-mentioned comic generation method, Figures 1 to 9 The comic generation method provided in the embodiment corresponds to the embodiment, so the implementation of the comic generation method is also applicable to the comic generation device provided in the embodiment of the present disclosure, and will not be described in detail in the embodiment of the present disclosure.

[0240] Figure 15 This is a structural diagram of the comic generation device provided in Example 8 of the present disclosure.

[0241] like Figure 15 As shown, the comic generation device 1500 may include: an acquisition and display module 1510 , a sending module 1520 , and a receiving and display module 1530 .

[0242] The acquisition and display module 1510 is used to acquire and display multiple storyboards; wherein the storyboards are obtained by splitting the story information associated with the target comic to be generated;

[0243] The sending module 1520 is configured to send a target comic style adapted to the target comic to the server in response to a confirmation operation on the multiple storyboards; wherein the target comic style is used by the server to combine the multiple storyboards, determine object features, and obtain at least one character image matching the object features;

[0244] The receiving and displaying module 1530 is used to receive and display the character image sent by the server;

[0245] The sending module 1520 is further configured to send a target image determined based on the character image to the server; wherein the target image is used by the server to generate a target comic by combining multiple storyboards and a target comic style;

[0246] The receiving and displaying module 1530 is further configured to receive and display the target comic sent by the server.

[0247] In a possible implementation of the embodiment of the present disclosure, the acquisition and display module 1510 is used to: obtain text information associated with the target comic to be generated; send the text information to the server; wherein the text information is used by the server to generate story information associated with the target comic, and split the story information to obtain multiple story frames; receive and display the multiple story frames sent by the server.

[0248] In a possible implementation of the embodiment of the present disclosure, the acquisition and display module 1510 is used to: obtain subject information associated with the target comic and generate text information based on the subject information; or obtain keyword information associated with the target comic and generate text information based on the keyword information; or obtain a first input text associated with the target comic and generate text information based on the first input text; or obtain a target document associated with the target comic and extract text information from the target document.

[0249] In a possible implementation of an embodiment of the present disclosure, the sending module 1520 is used to: render and display multiple candidate comic styles in response to a confirmation operation on multiple storyboards; select a target comic style from multiple candidate comic styles in response to a style selection operation; and send the target comic style to the server.

[0250] In a possible implementation of the embodiment of the present disclosure, the sending module 1520 is configured to:

[0251] In response to a first image selection operation, a target image is selected from the character images and the target image is sent to the server; or, in response to the required target image not existing in the character images, image description information is obtained; the image description information is sent to the server; wherein the image description information is used by the server to generate a candidate image that matches the image description information and the target comic style; the candidate image sent by the server is received and displayed, and in response to a second image selection operation, a target image is selected from the candidate images; and the target image is sent to the server.

[0252] In a possible implementation of the embodiment of the present disclosure, the comic generation device 1500 further includes:

[0253] The first update module is used to receive and display story information sent by the server; update the story information in response to the story update operation; send the updated story information to the server; wherein the updated story information is used by the server to regenerate multiple storyboards; receive and display the regenerated multiple storyboards sent by the server.

[0254] In a possible implementation of the embodiment of the present disclosure, the comic generation device 1500 further includes:

[0255] The second updating module is used to update at least one storyboard among the multiple storyboards in response to a storyboard updating operation.

[0256] In a possible implementation of the embodiment of the present disclosure, the comic generation device 1500 further includes:

[0257] The third update module is used to obtain picture description information for the first picture in the target comic in response to the comic update operation; send the picture description information to the server; wherein the picture description information is used by the server to generate a second picture that matches the picture description information and the style of the target comic; receive the second picture sent by the server, and use the second picture to update the first picture in the target comic.

[0258] In a possible implementation of the embodiment of the present disclosure, the comic generation device 1500 further includes:

[0259] The fourth update module is used to select a target prop from multiple displayed candidate props in response to a comic editing operation, and use the target prop to update at least one third frame in the target comic; and / or, in response to a typesetting update operation, update the typesetting position of at least one fourth frame in the target comic.

[0260] The comic generation device of the embodiment of the present disclosure can determine a character image that is suitable for the comic to be generated based on multiple storyboards and comic styles associated with the comic, and automatically generate comics based on the character image, multiple storyboards and comic styles. This can shorten the comic creation cycle and lower the threshold for comic creation, so that ordinary comic lovers can also realize their dream of comic creation and improve the user experience.

[0261] With the above Figures 12 to 14 Corresponding to the comic generation method provided in the embodiment, the present disclosure also provides a comic generation device. Since the comic generation device provided in the embodiment of the present disclosure is similar to the above-mentioned comic generation method, Figures 12 to 14 The comic generation method provided in the embodiment corresponds to the embodiment, so the implementation of the comic generation method is also applicable to the comic generation device provided in the embodiment of the present disclosure, and will not be described in detail in the embodiment of the present disclosure.

[0262] Figure 16 This is a structural diagram of the comic generation device provided in Example 9 of the present disclosure.

[0263] like Figure 16 As shown, the comic generation device 1600 may include: an acquisition and splitting module 1610 , a transceiver module 1620 , a processing module 1630 and a generation module 1640 .

[0264] The acquisition and splitting module 1610 is used to obtain story information associated with the target comic to be generated, and split the story information to obtain multiple storyboards;

[0265] The transceiver module 1620 is configured to send a plurality of storyboards to a client, and receive a target comic style sent by the client in response to a confirmation operation on the plurality of storyboards;

[0266] A processing module 1630 is configured to determine at least one object feature based on the plurality of storyboards and the target comic style, and obtain a character image that matches the object feature;

[0267] The transceiver module 1620 is further configured to send the character image to the client and receive the target image sent by the client; wherein the target image is determined based on the character image;

[0268] A generating module 1640 is configured to generate a target comic based on a character image, a plurality of storyboards, and a target comic style;

[0269] The transceiver module 1620 is further configured to send the target comic to the client.

[0270] In a possible implementation of the embodiment of the present disclosure, a splitting module 1610 is obtained, which is used to: receive text information associated with the target comic to be generated sent by the client; call the large model to generate story information associated with the target comic based on the text information; and split the story information based on the plot and / or key scenes in the story information to obtain multiple storyboards.

[0271] In a possible implementation of the embodiment of the present disclosure, the processing module 1630 is used to: extract image features and era features from multiple storyboards; determine object features based on the image features, era features and target comic style; and determine a character image that matches the object features from multiple character images in the character library.

[0272] In a possible implementation of the embodiment of the present disclosure, the generation module 1640 is used to: generate a storyboard comic corresponding to each storyboard based on the character image, each storyboard and the target comic style; and splice the storyboard comics of multiple storyboards according to the storyboard order between the multiple storyboards to obtain the target comic.

[0273] The comic generation device of the embodiment of the present disclosure can determine a character image that is suitable for the comic to be generated based on multiple storyboards and comic styles associated with the comic, and automatically generate comics based on the character image, multiple storyboards and comic styles. This can shorten the comic creation cycle and lower the threshold for comic creation, so that ordinary comic lovers can also realize their dream of comic creation and improve the user experience.

[0274] In order to implement the above embodiments, the present disclosure also provides an electronic device, which may include at least one processor; and a memory communicatively connected to the at least one processor; wherein 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 execute the comic generation method proposed in any of the above embodiments of the present disclosure.

[0275] In order to implement the above embodiments, the present disclosure further provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable a computer to execute the comic generation method proposed in any of the above embodiments of the present disclosure.

[0276] In order to implement the above embodiments, the present disclosure further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, it implements the comic generation method proposed in any of the above embodiments of the present disclosure.

[0277] 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.

[0278] Figure 17 A schematic block diagram of an example electronic device that can be used to implement an embodiment of the present disclosure is shown. The electronic device may include the server and client in the above-mentioned embodiments. 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 can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0279] like Figure 17As shown, electronic device 1700 includes a computing unit 1701, which can perform various appropriate actions and processes based on computer programs stored in ROM (Read-Only Memory) 1702 or loaded from storage unit 1707 into RAM (Random Access Memory) 1703. RAM 1703 may also store various programs and data required for the operation of device 1700. Computing unit 1701, ROM 1702, and RAM 1703 are interconnected via bus 1704. An I / O (Input / Output) interface 1705 is also connected to bus 1704.

[0280] Various components in device 1700 are connected to I / O interface 1705, including an input unit 1706, such as a keyboard, mouse, etc.; an output unit 1707, such as various types of displays, speakers, etc.; a storage unit 1708, such as a magnetic disk, optical disk, etc.; and a communication unit 1709, such as a network card, modem, wireless communication transceiver, etc. The communication unit 1709 allows device 1700 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0281] Computing unit 1701 can be any general-purpose and / or specialized processing component with processing and computing capabilities. Some examples of computing unit 1701 include, but are not limited to, CPUs (Central Processing Units), GPUs (Graphic Processing Units), various specialized AI (Artificial Intelligence) computing chips, various computing units that run machine learning model algorithms, DSPs (Digital Signal Processors), and any suitable processors, controllers, microcontrollers, etc. Computing unit 1701 performs the various methods and processes described above, such as the comic generation method described above. For example, in some embodiments, the comic generation method described above can be implemented as a computer software program tangibly embodied in a machine-readable medium, such as storage unit 1708. In some embodiments, part or all of the computer program can be loaded and / or installed onto device 1700 via ROM 1702 and / or communication unit 1709. When the computer program is loaded into RAM 1703 and executed by computing unit 1701, one or more steps of the comic generation method described above can be performed. Alternatively, in other embodiments, the computing unit 1701 may be configured to execute the above-mentioned comic generation method in any other appropriate manner (for example, by means of firmware).

[0282] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, FPGAs (Field Programmable Gate Arrays), ASICs (Application-Specific Integrated Circuits), ASSPs (Application-Specific Standard Products), SOCs (System on Chips), CPLDs (Complex Programmable Logic Devices), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable 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.

[0283] 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.

[0284] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may 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 machine-readable storage media may include an electrical connection based on one or more wires, a portable computer disk, a hard disk, RAM, ROM, EPROM (Electrically Programmable Read-Only-Memory) or flash memory, optical fiber, CD-ROM (Compact Disc Read-Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0285] To provide for user interaction, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (Cathode-Ray Tube) or LCD (Liquid Crystal Display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide for user interaction; 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 input, voice input, or tactile input.

[0286] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, 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: LAN (Local Area Network), WAN (Wide Area Network), the Internet, and blockchain networks.

[0287] A computer system may include a client and a server. The client and server are generally remote from each other and typically interact via a communication network. This client-server relationship arises through computer programs running on the respective computers, establishing a client-server relationship. The server may be a cloud server, also known as a cloud computing server or cloud host. This server is a host product within the cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosts and VPS (Virtual Private Server) services. The server may also be a server in a distributed system or a server integrated with blockchain.

[0288] It's important to note that artificial intelligence (AI) is the study of how computers can simulate certain human thought processes and intelligent behaviors (such as learning, reasoning, thinking, and planning). This encompasses both hardware and software technologies. AI hardware technologies generally include sensors, specialized AI chips, cloud computing, distributed storage, and big data processing. AI software technologies primarily encompass computer vision, speech recognition, natural language processing, machine learning / deep learning, big data processing, and knowledge graphs.

[0289] According to the technical solution of the embodiment of the present disclosure, it is possible to determine a character image that is suitable for the comic to be generated based on multiple storyboards and comic styles associated with the comic, and automatically generate comics based on the character image, multiple storyboards and comic styles. This can shorten the comic creation cycle and lower the threshold for comic creation, so that ordinary comic lovers can also realize their dream of comic creation and improve the user experience.

[0290] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this disclosure can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved. This is not a limitation herein.

[0291] The above specific embodiments do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure shall be included within the scope of protection of this disclosure.

Claims

1. A comic generation method, comprising: Acquire text information associated with the target comic to be generated, where the text information is input or uploaded by a user on the client side; Sending the text information to a server; wherein the text information is used by the server to generate story information associated with the target comic, and split the story information to obtain multiple storyboards; Receive and display the multiple storyboards sent by the server; wherein the storyboards are obtained by splitting the story information associated with the target comic to be generated; In response to a confirmation operation on the plurality of storyboards, a target comic style adapted to the target comic is sent to a server; wherein the target comic style is used by the server to determine object features by combining the plurality of storyboards and to obtain at least one character image matching the object features; receiving and displaying the character image sent by the server, and sending a target image determined based on the character image to the server; wherein the target image is used by the server to generate the target comic by combining the multiple storyboards and the target comic style; Receive and display the target comic sent by the server.

2. The method according to claim 1, wherein The acquiring of text information associated with the target comic to be generated includes any one of the following: Acquire subject information associated with the target comic, and generate the text information according to the subject information; Acquire keyword information associated with the target comic, and generate the text information according to the keyword information; Acquire a first input text associated with the target comic, and generate the text information according to the first input text; A target document associated with the target comic is acquired, and the text information is extracted from the target document.

3. The method according to claim 1, wherein In response to the confirmation operation on the plurality of storyboards, sending a target comic style adapted to the target comic to the server, comprising: In response to a confirmation operation on the plurality of storyboards, rendering and displaying a plurality of candidate comic styles; In response to a style selection operation, selecting the target comic style from the plurality of candidate comic styles; The target comic style is sent to the server.

4. The method according to claim 1, wherein The sending of the target image determined based on the character image to the server includes: In response to a first image selection operation, selecting the target image from the character images and sending the target image to the server; or, In response to the desired target image not existing in the character images, acquiring image description information; Sending the image description information to the server; wherein the image description information is used by the server to generate a candidate image that matches the image description information and the target comic style; receiving and displaying the candidate images sent by the server, and selecting the target image from the candidate images in response to a second image selection operation; The target image is sent to the server.

5. The method according to any one of claims 1 to 4, wherein Before sending the target comic style adapted to the target comic to the server in response to the confirmation operation of the plurality of storyboards, the method further includes: Receive and display the story information sent by the server; In response to a story update operation, updating the story information; Sending the updated story information to the server; wherein the updated story information is used by the server to regenerate multiple storyboards; Receive and display the regenerated multiple storyboards sent by the server.

6. The method according to any one of claims 1 to 4, wherein After obtaining and displaying multiple storyboards, the method further includes: In response to the storyboard update operation, at least one storyboard among the plurality of storyboards is updated.

7. The method according to any one of claims 1 to 4, wherein After receiving and displaying the target comic sent by the server, the method further includes: In response to a comic update operation, obtaining picture description information for a first picture in the target comic; Sending the picture description information to the server; wherein the picture description information is used by the server to generate a second picture that matches the picture description information and the target comic style; The second frame sent by the server is received, and the first frame in the target comic is updated using the second frame.

8. The method according to claim 7, wherein: The method further comprises: In response to a comic editing operation, selecting a target prop from a plurality of displayed candidate props; Using the target prop, updating at least one third frame in the target comic; and / or, In response to the layout update operation, the layout position of at least one fourth frame in the target comic is updated.

9. A comic generation method comprising: Receiving text information associated with a target comic to be generated from a client, wherein the text information is input or uploaded by a user on the client side; Calling the large model to generate story information associated with the target comic based on the text information; Splitting the story information based on the plot and / or key scenes in the story information to obtain multiple storyboards; Sending the plurality of storyboards to a client, and receiving a target comic style sent by the client in response to a confirmation operation on the plurality of storyboards; Determining at least one object feature according to the plurality of storyboards and the target comic style, and acquiring a character image matching the object feature; sending the character image to the client, and receiving a target image sent by the client; wherein the target image is determined based on the character image; Based on the character image, the multiple storyboards and the target comic style, the target comic is generated and sent to the client.

10. The method according to claim 9, wherein: The determining, based on the plurality of storyboards and the target comic style, at least one object feature and obtaining a character image matching the object feature comprises: extracting image features and era features from the plurality of storyboards; Determining the object characteristics according to the image characteristics, the era characteristics, and the target comic style; A character image matching the object feature is determined from a plurality of character images in a character library.

11. The method according to claim 9, wherein Generating the target comic based on the character image, the plurality of storyboards, and the target comic style includes: Based on the character image, each storyboard and the target comic style, generating a storyboard comic corresponding to each storyboard; The storyboard comics of the multiple storyboards are spliced ​​according to the storyboard sequence between the multiple storyboards to obtain the target comic.

12. A comic generation device, comprising: An acquisition and display module is used to acquire text information associated with the target comic to be generated, wherein the text information is input or uploaded by a user on the client side; Sending the text information to a server; wherein the text information is used by the server to generate story information associated with the target comic, and split the story information to obtain multiple storyboards; receiving and displaying the multiple storyboards sent by the server; wherein the storyboards are obtained by splitting the story information associated with the target comic to be generated; a sending module configured to send a target comic style adapted to the target comic to a server in response to a confirmation operation on the plurality of storyboards; wherein the target comic style is used by the server to determine object features based on the plurality of storyboards and to obtain at least one character image matching the object features; A receiving and displaying module, configured to receive and display the character image sent by the server; The sending module is further configured to send a target image determined based on the character image to the server; wherein the target image is used by the server to generate the target comic by combining the multiple storyboards and the target comic style; The receiving and displaying module is further configured to receive and display the target comic sent by the server.

13. The device according to claim 12, wherein The acquisition and display module is used to: Acquire subject information associated with the target comic, and generate the text information according to the subject information; or, Acquire keyword information associated with the target comic, and generate the text information according to the keyword information; or, Acquire a first input text associated with the target comic, and generate the text information according to the first input text; or, A target document associated with the target comic is acquired, and the text information is extracted from the target document.

14. The device according to claim 12, wherein The sending module is used to: In response to a confirmation operation on the plurality of storyboards, rendering and displaying a plurality of candidate comic styles; In response to a style selection operation, selecting the target comic style from the plurality of candidate comic styles; The target comic style is sent to the server.

15. The device according to claim 12, wherein The sending module is used to: In response to a first image selection operation, selecting the target image from the character images and sending the target image to the server; or, In response to the desired target image not existing in the character images, acquiring image description information; Sending the image description information to the server; wherein the image description information is used by the server to generate a candidate image that matches the image description information and the target comic style; receiving and displaying the candidate images sent by the server, and selecting the target image from the candidate images in response to a second image selection operation; The target image is sent to the server.

16. The device according to any one of claims 12 to 15, wherein: The device further comprises: The first update module is used to receive and display the story information sent by the server; update the story information in response to a story update operation; send the updated story information to the server; wherein the updated story information is used by the server to regenerate multiple storyboards; receive and display the regenerated multiple storyboards sent by the server.

17. The device according to any one of claims 12 to 15, wherein: The device further comprises: The second updating module is used to update at least one story story among the multiple story stories in response to a story story updating operation.

18. The device according to any one of claims 12 to 15, wherein: The device further comprises: A third update module is configured to, in response to a comic update operation, obtain picture description information for a first picture in the target comic; send the picture description information to the server; wherein the picture description information is used by the server to generate a second picture that matches the picture description information and the style of the target comic; receive the second picture sent by the server, and use the second picture to update the first picture in the target comic.

19. The device according to claim 18, wherein The device further comprises: The fourth update module is used to select a target prop from multiple displayed candidate props in response to a comic editing operation, and use the target prop to update at least one third frame in the target comic; and / or, in response to a typesetting update operation, update the typesetting position of at least one fourth frame in the target comic.

20. A comic book generating device, comprising: An acquisition and splitting module is configured to receive text information associated with a target comic to be generated and sent by a client, wherein the text information is input or uploaded by a user on the client side; Calling the large model to generate story information associated with the target comic based on the text information; Splitting the story information based on the plot and / or key scenes in the story information to obtain multiple storyboards; a transceiver module, configured to send the plurality of storyboards to a client, and receive a target comic style sent by the client in response to a confirmation operation on the plurality of storyboards; a processing module, configured to determine at least one object feature based on the plurality of storyboards and the target comic style, and obtain a character image matching the object feature; The transceiver module is further configured to send the character image to the client and receive a target image sent by the client; wherein the target image is determined based on the character image; A generating module, configured to generate the target comic based on the character image, the plurality of storyboards, and the target comic style; The transceiver module is further configured to send the target comic to the client.

21. The device according to claim 20, wherein The processing module is used to: extracting image features and era features from the plurality of storyboards; Determining the object characteristics according to the image characteristics, the era characteristics, and the target comic style; A character image matching the object feature is determined from a plurality of character images in a character library.

22. The device according to claim 20, wherein The generating module is used to: Based on the character image, each storyboard and the target comic style, generating a storyboard comic corresponding to each storyboard; The storyboard comics of the multiple storyboards are spliced ​​according to the storyboard sequence between the multiple storyboards to obtain the target comic.

23. An electronic device comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, 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 execute the comic generation method according to any one of claims 1 to 8, or to execute the comic generation method according to any one of claims 9 to 11.

24. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to enable the computer to execute the comic generation method according to any one of claims 1 to 8, or to execute the comic generation method according to any one of claims 9 to 11.

25. A computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements the steps of the comic generation method according to any one of claims 1 to 8, or implements the steps of the comic generation method according to any one of claims 9 to 11.

Images