Drawing interaction method and device, storage medium and electronic equipment

Abstract

The embodiment of the invention discloses a drawing interaction method and device, a storage medium and electronic equipment, and the method comprises the steps: carrying out the stick figure conversion processing of an image photographed by a user through a drawing creation large model, and obtaining a reference simulated stick figure, so that the user can select a target simulated stick figure, performing drawing customization processing based on the target imitation stick figure to obtain a drawing line draft and a color filling area corresponding to the drawing line draft, displaying the drawing line draft and the color filling area to a user, obtaining first drawing operation data input by the user, generating an initial drawing work based on the first drawing operation data, and displaying the initial drawing work on the user. And performing painting detail detection processing on the initial painting work to obtain a painting detail complete area, displaying the painting detail complete area to the user, obtaining second painting operation data input by the user, and generating a target painting work based on the second painting operation data. Therefore, the drawing interaction function of the intelligent shooting equipment is enriched, and meanwhile, the user can be helped to improve the drawing ability.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computers, and particularly relates to a painting interaction method and device, a storage medium and an electronic device. BACKGROUND

[0002] Nowadays, intelligent shooting devices provide many shooting auxiliary functions for users, such as automatic optimization of image quality, intelligent recognition of scenes, intelligent composition, and the like. Among them, automatic optimization of image quality mainly reflects that through the advanced image processing algorithm built in the intelligent shooting device, the exposure, contrast, color balance and the like of the photo can be automatically adjusted to ensure that high-quality photos can be taken even under complex light conditions. Intelligent recognition of scenes mainly reflects that the intelligent shooting device can recognize different shooting scenes (such as landscapes, portraits, night scenes, and the like) and automatically adjust the shooting parameters to adapt to the current scene. Intelligent composition mainly reflects that through the grid lines, golden section points and the like, the user is helped to better compose. These functions can all help users more easily take high-quality photos and greatly improve the user shooting experience.

[0003] With the development of artificial intelligence and image processing technology, the functions of intelligent shooting devices are also constantly expanding. Therefore, how to enrich the interactive functions of intelligent shooting devices is a technical problem that needs to be solved by those skilled in the art. SUMMARY

[0004] The embodiments of the present application provide a painting interaction method and device, a storage medium and an electronic device. The technical solution is as follows:

[0005] In a first aspect, the embodiments of the present application provide a painting interaction method applied to an intelligent shooting device, and the method comprises the following steps:

[0006] obtaining a user shooting image, performing sketch conversion processing on the user shooting image through a large painting creation model to obtain a reference mimic sketch, and showing the reference mimic sketch to the user;

[0007] determining a target mimic sketch selected by the user for the reference mimic sketch, performing painting customization processing on the target mimic sketch through the large painting creation model to obtain a painting draft and a color filling area corresponding to the painting draft;

[0008] showing the painting draft and the color filling area to the user, obtaining first painting operation data input by the user based on the painting draft and the color filling area, and generating an initial painting work based on the first painting operation data;

[0009] obtaining second drawing operation data input by the user based on the drawing detail improvement area, and generating a target drawing work based on the second drawing operation data.

[0010] obtaining second drawing operation data input by the user based on the drawing detail improvement area, and generating a target drawing work based on the second drawing operation data.

[0011] In combination with the first aspect, in some possible implementation manners, the obtaining, by the drawing creation large model, of the initial drawing sketch based on the target mimic sketch and the obtaining, by the drawing creation large model, of the initial color filling area based on the image captured by the user, include:

[0012] obtaining, by the drawing creation large model, the initial drawing sketch based on the target mimic sketch, and determining, by the drawing creation large model, an initial color filling area corresponding to the initial drawing sketch based on the image captured by the user;

[0013] obtaining drawing creation reference information corresponding to the user;

[0014] obtaining, by the drawing creation large model, the initial drawing sketch based on the drawing creation reference information, and obtaining, by the drawing creation large model, a color filling area corresponding to the initial drawing sketch based on the drawing creation reference information.

[0015] In combination with the above implementation manners, in some possible implementation manners, the obtaining, by the drawing creation large model, of the initial drawing sketch based on the target mimic sketch and the obtaining, by the drawing creation large model, of the initial color filling area based on the image captured by the user, include:

[0016] obtaining, by the drawing creation large model, a target sketch style corresponding to the target mimic sketch, obtaining a basic drawing sketch based on line extraction processing performed on the target mimic sketch, and obtaining the initial drawing sketch based on sketch style adaptation processing performed on the basic drawing sketch based on the target sketch style;

[0017] obtaining, by the drawing creation large model, basic color information based on color extraction processing performed on the image captured by the user, and obtaining the initial color filling area based on color style configuration processing performed on the initial drawing sketch based on the target sketch style and the basic color information.

[0018] In combination with the first aspect, in some possible implementation manners, the obtaining, by the drawing creation large model, of the initial drawing sketch based on the target mimic sketch and the obtaining, by the drawing creation large model, of the initial color filling area based on the image captured by the user, include:

[0019] presenting the drawing sketch to the user, obtaining sketch tracing operation data input by the user based on the drawing sketch, performing line drawing detection processing based on the sketch tracing operation data to obtain a line drawing detection result;

[0020] if the line drawing detection result is a drawing error type, outputting a line drawing prompt to the user;

[0021] if the line drawing detection result is a correct drawing type, generating a user-drawn sketch when it is determined that the drawing sketch is in a drawing completion state;

[0022] when it is determined that the drawing sketch is in a drawing completion state, presenting the color filling area to the user, obtaining color filling operation data input by the user based on the color filling area, and performing color filling detection processing based on the color filling operation data to obtain a color filling detection result;

[0023] if the color filling detection result is a filling error type, outputting a color filling prompt to the user;

[0024] if the color filling detection result is a correct filling type, performing color filling processing on the user-drawn sketch based on the color filling data to obtain an initial painting work when it is determined that the color filling area is in a filling completion state.

[0025] In combination with the first aspect, in some possible implementation manners, the drawing detail perfecting area obtained by the drawing creation large model through the initial painting work includes:

[0026] determining, by the drawing creation large model, a mimic similarity based on the initial painting work and the target mimic sketch, and determining a to-be-adjusted area in the initial painting work based on the mimic similarity;

[0027] determining, by the drawing creation large model, a detail perfecting prompt corresponding to the to-be-adjusted area, and generating a drawing detail perfecting area based on the to-be-adjusted area and the detail perfecting prompt.

[0028] In combination with the first aspect, in some possible implementation manners, the reference mimic sketch obtained by the drawing creation large model through the user-shot image includes:

[0029] determining a reference sketch style corresponding to the user-shot image;

[0030] performing, by the drawing creation large model, sketch conversion processing on the user-shot image based on the reference sketch style to obtain a reference mimic sketch.

[0031] In combination with the above-mentioned embodiments, in some possible embodiments, the determining the reference sketch style corresponding to the image taken by the user comprises:

[0032] obtaining user age information, and determining the reference sketch style corresponding to the image taken by the user based on the user age information; or

[0033] obtaining historical drawing data of the user, and determining the reference sketch style corresponding to the image taken by the user based on the historical drawing data.

[0034] In a second aspect, an embodiment of the present application provides a drawing interaction device applied to an intelligent shooting device, and the device comprises:

[0035] an image conversion module configured to obtain an image taken by a user, perform sketch conversion processing on the image taken by the user by using a large drawing creation model to obtain a reference mimic sketch, and show the reference mimic sketch to the user;

[0036] a drawing conversion module configured to determine a target mimic sketch selected by the user for the reference mimic sketch, perform drawing customization processing on the target mimic sketch by using the large drawing creation model to obtain a drawing draft and a color filling area corresponding to the drawing draft;

[0037] a drawing creation module configured to show the drawing draft and the color filling area to the user, obtain first drawing operation data input by the user based on the drawing draft and the color filling area, and generate an initial drawing work based on the first drawing operation data;

[0038] a drawing perfecting module configured to perform drawing detail detection processing on the initial drawing work by using the large drawing creation model to obtain a drawing detail perfecting area, and show the drawing detail perfecting area to the user;

[0039] a drawing generation module configured to obtain second drawing operation data input by the user based on the drawing detail perfecting area, and generate a target drawing work based on the second drawing operation data.

[0040] Optionally, the drawing conversion module comprises:

[0041] a drawing conversion unit configured to generate an initial drawing draft based on the target mimic sketch by using the large drawing creation model, and determine an initial color filling area corresponding to the initial drawing draft based on the image taken by the user;

[0042] an information obtaining unit configured to obtain drawing creation reference information corresponding to the user;

[0043] The line sketch adjusting unit is configured to perform line sketch adjustment processing on the initial drawing sketch based on the drawing creation reference information to obtain a drawing sketch, and perform color adjustment processing on the initial color filling region based on the drawing creation reference information to obtain a color filling region corresponding to the drawing sketch.

[0044] Optionally, the drawing conversion unit is specifically configured to:

[0045] determine a target sketch style corresponding to the target mimetic sketch by using the drawing creation large model, perform line extraction processing on the target mimetic sketch to obtain a basic drawing sketch, and perform line sketch style adaptation processing on the basic drawing sketch based on the target sketch style to obtain an initial drawing sketch;

[0046] perform color extraction processing on the user's photographed image based on the drawing creation large model to obtain basic color information, and perform color style configuration processing on the initial drawing sketch based on the target sketch style and the basic color information to obtain an initial color filling region.

[0047] Optionally, the drawing creation module is specifically configured to:

[0048] display the drawing sketch to the user, acquire line sketch copying operation data input by the user based on the drawing sketch, and perform line drawing detection processing based on the line sketch copying operation data to obtain a line drawing detection result;

[0049] if the line drawing detection result is a drawing error type, output a line drawing prompt to the user;

[0050] if the line drawing detection result is a correct drawing type, generate a user-drawn sketch when it is determined that the drawing sketch is in a drawing completion state;

[0051] when it is determined that the drawing sketch is in a drawing completion state, display the color filling region to the user, acquire color filling operation data input by the user based on the color filling region, and perform color filling detection processing based on the color filling operation data to obtain a color filling detection result;

[0052] if the color filling detection result is a filling error type, output a color filling prompt to the user;

[0053] if the color filling detection result is a correct filling type, perform color filling processing on the user-drawn sketch based on the color filling data to obtain an initial drawing work when it is determined that the color filling region is in a filling completion state.

[0054] Optionally, the drawing perfecting module is specifically configured to:

[0055] determine a mimic similarity based on the initial painting work and the target sketch, and determine a region to be adjusted in the initial painting work based on the mimic similarity;

[0056] determine a detail perfecting prompt corresponding to the region to be adjusted by the painting creation model, and generate a painting detail perfecting region based on the region to be adjusted and the detail perfecting prompt.

[0057] Optionally, the image conversion module comprises:

[0058] a style determination unit configured to determine a reference sketch style corresponding to the user-shot image;

[0059] a sketch conversion unit configured to perform sketch conversion processing on the user-shot image based on the reference sketch style by the painting creation model to obtain a reference mimic sketch.

[0060] Optionally, the style determination unit is specifically configured to:

[0061] obtain user age information, and determine the reference sketch style corresponding to the user-shot image based on the user age information; or

[0062] obtain historical painting data of the user, and determine the reference sketch style corresponding to the user-shot image based on the historical painting data.

[0063] In a third aspect, an embodiment of the present application provides a computer storage medium, which has a plurality of instructions, the instructions being adapted to be loaded by a processor and execute the method described above.

[0064] In a fourth aspect, an embodiment of the present application provides an electronic device, which can comprise a memory and a processor; wherein the memory stores a computer program, the computer program being adapted to be loaded by the memory and execute the method described above.

[0065] The technical scheme provided by the embodiments of the present application has at least the following beneficial effects:

[0066] The drawing interaction method provided by the embodiment of the present application, through the drawing creation large model, reference imitation sketch is obtained by processing the sketch conversion of the image shot by the user, so that the user selects the target imitation sketch from the reference imitation sketch, and the drawing customization processing is performed based on the target imitation sketch by the drawing creation large model to obtain the drawing draft and the color filling area corresponding to the drawing draft, the drawing draft and the color filling area are displayed to the user, the first drawing operation data input by the user based on the drawing draft and the color filling area is obtained, the initial drawing work is generated based on the first drawing operation data, the drawing detail detection processing is performed on the initial drawing work by the drawing creation large model to obtain the drawing detail perfect area, the drawing detail perfect area is displayed to the user, the second drawing operation data input by the user based on the drawing detail perfect area is obtained, and the target drawing work is generated based on the second drawing operation data. Thus, the real scene photo is first converted into the imitation sketch, and after the user selects the target imitation sketch for copying, the drawing draft for copying and the color filling area are gradually generated to guide the user to complete the drawing draft copying, coloring operation and detail perfect operation in sequence, thereby enriching the drawing interaction function of the intelligent shooting device and helping the user to improve the drawing ability. BRIEF DESCRIPTION OF DRAWINGS

[0067] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor on the basis of these drawings.

[0068] Figure 1 is a flowchart of a drawing interaction method provided by the embodiment of the present application;

[0069] Figure 2 is a flowchart of another drawing interaction method provided by the embodiment of the present application;

[0070] Figure 3 is a structural schematic diagram of a drawing interaction device provided by the embodiment of the present application;

[0071] Figure 4 is a structural schematic diagram of a drawing conversion module provided by the embodiment of the present application;

[0072] Figure 5 is a structural schematic diagram of an electronic device provided by the embodiment of the present application. DETAILED DESCRIPTION

[0073] In order to make the application purposes, features and advantages of the embodiments of the present application more obvious and easy to understand, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of protection of the present application.

[0074] In the description of the present application, it should be understood that the terms "first", "second" and the like are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance. In the description of the present application, it should be noted that, unless otherwise explicitly specified and limited, "including" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device including a series of steps or units is not limited to the listed steps or units, but can optionally include steps or units not listed, or can optionally include other steps or units inherent to the process, method, product or device. Those skilled in the art can understand the specific meaning of the above terms in the present application according to the specific circumstances. In addition, in the description of the present application, "multiple" means two or more, unless otherwise specified. "And / or" describes the relationship between the associated objects, which means that there can be three relationships, for example, A and / or B can represent the following three cases: A exists alone, A and B exist together, and B exists alone. The character " / " generally represents an "or" relationship between the associated objects.

[0075] The present application will be described in detail below with reference to specific embodiments.

[0076] In one embodiment, as shown in Figure 1 A drawing interaction method is specifically proposed, which can be realized by relying on a computer program and can run on a drawing interaction device based on von Neumann system. The computer program can be integrated in an application or can run as an independent tool application. The drawing interaction method can be applied to a smart shooting device, which can be a smart camera, a smart phone, a tablet or other portable smart device with a camera and a display screen.

[0077] Specifically, the drawing interaction method comprises:

[0078] S101, acquiring a user shooting image, performing a sketch conversion processing on the user shooting image by a drawing creation large model to obtain a reference imitated sketch, and showing the reference imitated sketch to the user.

[0079] It can be understood that the user photographed image refers to a photo photographed by the user using the camera of the smart photographing device. The user photographed image can be obtained in particular by determining the latest collected image in the photographed image as the user photographed image, or obtaining a target image selected by the user from the photographed image and determining the target image as the user photographed image.

[0080] It can be understood that the reference mimetic sketch can be a sketch for the user to mimic, which is converted based on the user photographed image. The reference mimetic sketch can include multiple color-drawn sketches and single-color sketches, and can specifically include sketches of different styles, such as pencil sketches, crayon sketches, oil painting sketches, colored pencil sketches, and the like. The reference mimetic sketch can be obtained by inputting the user photographed image into the painting creation large model, and converting the user photographed image into reference mimetic sketches of different styles by the painting creation large model. After at least one reference mimetic sketch is generated by using the painting creation large model, the at least one reference mimetic sketch is displayed on the display screen.

[0081] In the embodiments of the present application, the painting creation large model can be obtained based on a multi-modal large model training.

[0082] Optionally, the training process of the painting creation large model can include: creating an initial painting creation large model based on a multi-modal large model, the initial painting creation large model can include an initial sketch conversion module and an initial painting customization module; obtaining sample data, the sample data including a sample user photographed image, the sample data being labeled with a reference mimic sketch label, a painting draft label, and a color filling area label; performing at least one round of model training on the initial painting creation large model using the sample data; in the model forward training process, performing sketch conversion processing on the sample user photographed image through the initial sketch module to obtain a predicted mimic sketch, determining a sample mimic sketch selected by the sample user for the predicted mimic sketch, performing painting customization processing based on the sample mimic sketch through the initial painting customization module to obtain a predicted painting draft and a predicted color filling area corresponding to the predicted painting draft, obtaining first painting operation sample data input by the sample user based on the predicted painting draft and the predicted color filling area, generating an initial predicted painting work based on the first painting operation sample data through the first initial painting generation module, and performing painting detail detection processing on the initial predicted painting work through the initial painting creation large model to obtain a predicted painting detail improvement area, and generating a predicted painting work based on second painting operation sample data input by the sample user through the initial painting creation large model; in the model backward training process, generating a first loss value based on the predicted mimic sketch and the reference mimic sketch label, generating a second loss value based on the predicted painting draft and the painting draft label, generating a third loss value based on the predicted color filling area and the color filling area label, and determining a model comprehensive loss based on the first loss value, the second loss value, and the third loss value; and performing model parameter adjustment on the initial sketch conversion module and the initial painting customization module in the initial painting creation large model based on the model comprehensive loss to obtain a painting creation large model after model training.

[0083] Optionally, the first loss value, the second loss value, and the third loss value can be determined using any one of a hinge loss function, a contrastive loss function, a Euclidean distance loss function, or a cross-entropy loss function in related technologies.

[0084] Optionally, the model end training condition for obtaining the painting creation large model can include that a loss function value is less than or equal to a preset loss function threshold, or the number of iterations reaches a preset number threshold. The model end training condition can be determined based on actual conditions, and is not specifically limited here.

[0085] S102, determining a target mimic sketch selected by the user for the reference mimic sketch, and performing painting customization processing on the target mimic sketch through the painting creation large model to obtain a painting draft and a color filling area corresponding to the painting draft.

[0086] It can be understood that the drawing sketch refers to a sketch customized for a user for the user to copy, and the color filling area refers to a color area customized for the user to fill colors on the drawing sketch. The color filling area can include color areas of different color indications.

[0087] In some embodiments, the simplified sketch of the target imitation, the image shot by the user, and the drawing customization task description information are input into the drawing creation large model. The drawing customization task description information includes specific work steps for instructing the drawing creation large model to generate a drawing sketch and a color filling area. The specific work steps include: instructing the drawing creation large model to generate a drawing sketch corresponding to the simplified sketch of the target imitation, and generating a color filling area corresponding to the drawing sketch according to the image shot by the user.

[0088] S103, the drawing sketch and the color filling area are displayed to the user, first drawing operation data input by the user based on the drawing sketch and the color filling area is obtained, and an initial drawing work is generated based on the first drawing operation data.

[0089] It can be understood that the first drawing operation data can include line drawing data input based on the drawing sketch and color filling data input based on the color filling area. The user-drawn sketch is generated according to the line drawing data, the color filling area is generated according to the color filling data, the user-drawn sketch and the color filling area are merged, and the initial drawing work is generated.

[0090] S104, the drawing creation large model is used to perform drawing detail detection processing on the initial drawing work to obtain a drawing detail improvement area, and the drawing detail improvement area is displayed to the user.

[0091] It can be understood that the drawing detail improvement area refers to an area in the initial drawing work that needs to be improved in detail, such as an area that needs to increase shading, an area that needs to modify a gradient color, or an area that needs to modify an object contour. The drawing detail improvement area can include an adjusted area and a detail improvement prompt for the adjusted area.

[0092] Specifically, the initial drawing work, the simplified sketch of the target imitation, and the drawing detection task description information are input into the drawing creation large model. The drawing detection task description information is used to instruct the drawing creation large model to compare the initial drawing work with the simplified sketch of the target imitation, identify an adjusted area in the initial drawing work, instruct the drawing creation large model to determine a detail improvement prompt for the adjusted area, and generate a drawing detail improvement area according to the adjusted area and the detail improvement prompt.

[0093] S105, second drawing operation data input by the user based on the drawing detail improvement area is obtained, and a target drawing work is generated based on the second drawing operation data.

[0094] It can be understood that the second drawing operation data can include line drawing data and / or color filling data input by the user based on the drawing detail perfecting area. Specifically, the drawing detail perfecting area in the initial drawing work is updated according to the second drawing operation data, and a target drawing work is generated.

[0095] The drawing interaction method provided by the embodiments of the present application can convert a user's photographed image into a reference mimic sketch by using a large drawing creation model, so that the user can select a target mimic sketch from the reference mimic sketch, and the large drawing creation model can generate a drawing sketch and a color filling area corresponding to the drawing sketch based on the target mimic sketch, so as to show the drawing sketch and the color filling area to the user, obtain first drawing operation data input by the user based on the drawing sketch and the color filling area, generate an initial drawing work based on the first drawing operation data, perform drawing detail detection processing on the initial drawing work by using the large drawing creation model to obtain a drawing detail perfecting area, show the drawing detail perfecting area to the user, obtain second drawing operation data input by the user based on the drawing detail perfecting area, and generate a target drawing work based on the second drawing operation data. Thus, the present application can first convert a real scene photo into a mimic sketch, and then gradually generate a sketch and a color filling area for sketching after the user selects a target mimic sketch to be copied, so as to guide the user to complete the sketching, coloring and detail perfecting operations in sequence, thereby enriching the drawing interaction function of the intelligent shooting device and helping the user to improve the drawing ability.

[0096] Next, please refer to Figure 2 , a flowchart of another embodiment of a drawing interaction method proposed by the present application.

[0097] Specifically, the drawing interaction method comprises:

[0098] S201, obtaining a user's photographed image, converting the user's photographed image into a reference mimic sketch by using a large drawing creation model, and showing the reference mimic sketch to the user.

[0099] In some embodiments, the step of converting the user's photographed image into a reference mimic sketch by using a large drawing creation model can specifically comprise: A1: determining a reference sketch style corresponding to the user's photographed image; and A2: converting the user's photographed image into a reference mimic sketch based on the reference sketch style by using a large drawing creation model.

[0100] The step A1 can comprise: A11: obtaining user age information, and determining the reference sketch style corresponding to the user's photographed image based on the user age information; or A12: obtaining historical drawing data of the user, and determining the reference sketch style corresponding to the user's photographed image based on the historical drawing data.

[0101] In step A11, a stick figure style mapping table is obtained, the stick figure style mapping table is configured with stick figure styles corresponding to different age groups, a target age group corresponding to the user age information is determined, a stick figure style corresponding to the target age group is queried in the stick figure style mapping table, and the stick figure style corresponding to the target age group is determined as a reference stick figure style corresponding to the user photographed image.

[0102] In step A12, historical drawing data of the user is obtained from the local storage of the intelligent shooting device, the historical drawing data can include historical drawing works of the user, a historical drawing style corresponding to the historical drawing data is determined, and the reference stick figure style is filtered from the preset stick figure style according to the historical drawing style.

[0103] In step A2, the drawing creation large model can be obtained based on a multi-modal large language model training. The reference stick figure style and the user photographed image are input into the drawing creation large model, edge detection processing is performed on the user photographed image by using the drawing creation large model to obtain an edge image, the edge image can be an image composed of the contour and shape boundary of an object, image key features of the user photographed image are identified, the image key features can be pixel regions or contours corresponding to the most representative and identifiable parts in the image, object key contours are extracted according to the image key features, and a basic stick figure is obtained by performing contour filtering, contour merging and contour smoothing according to the edge image and the object key contours. The basic stick figure is color-filled according to the user photographed image to obtain a basic mimic stick figure, and the reference mimic stick figure adapted to various reference stick figure styles is generated according to the basic mimic stick figure.

[0104] After at least one reference mimic stick figure is generated by using the drawing creation large model, the at least one reference mimic stick figure is displayed on the display screen.

[0105] S202, determining a target mimic stick figure selected by the user for the reference mimic stick figure.

[0106] It can be understood that the target mimic stick figure can be any one of the reference mimic stick figures selected by the user from the at least one reference mimic stick figure. A touch selection operation or a voice selection instruction input by the user for the at least one reference mimic stick figure is received, and the target mimic stick figure indicated by the touch selection operation or the voice selection instruction is determined.

[0107] S203, generating an initial drawing sketch based on the target mimic stick figure by using the drawing creation large model, and determining an initial color filling area corresponding to the initial drawing sketch based on the user photographed image.

[0108] It can be understood that the initial drawing sketch refers to a sketch that conforms to the style of the target imitated sketch and is used for the user to draw the sketch by imitation. The initial color filling area refers to a color area that conforms to the style of the target imitated sketch and is used for the user to fill colors on the sketch drawn by imitation.

[0109] The target imitated sketch directly serves as a colored sketch drawn by imitation, and there is a certain difficulty in drawing for a user who is not professional in drawing. Converting the target imitated sketch into the initial drawing sketch and the initial color filling area can reduce the difficulty of the user's imitation and guide the user to complete the drawing of the sketch in steps, that is, first imitating the sketch according to the initial drawing sketch, and then filling colors according to the initial color filling area to obtain a colored sketch drawn by the user.

[0110] In some embodiments, step S203 is performed, which can specifically include: B1: determining, by the drawing creation large model, a target sketch style corresponding to the target imitated sketch, performing line extraction processing on the target imitated sketch to obtain a basic drawing sketch, and performing sketch style adaptation processing on the basic drawing sketch based on the target sketch style to obtain the initial drawing sketch; B2: performing color extraction processing on the user's photographed image by the drawing creation large model to obtain basic color information, and performing color style configuration processing on the initial drawing sketch based on the target sketch style and the basic color information to obtain the initial color filling area.

[0111] In step B1, a first prompt word is generated according to the target imitated sketch and sketch generation task description information, and the first prompt word is input into the drawing creation large model. The sketch generation task description information is used to instruct the drawing creation large model to perform a first step of determining a target sketch style corresponding to the target imitated sketch, then perform a second step of performing line extraction processing on the target imitated sketch, and then perform a third step of performing style adaptation processing on the extracted lines according to the target sketch style. The initial drawing sketch is obtained by performing sketch style adaptation processing on the basic drawing sketch based on the target sketch style by the drawing creation large model. Specifically, the drawing creation large model can be used to determine a target line width, a target line curvature, and a target line fluency according to the target sketch style, and adjust the line width, the line curvature, and the line fluency of the basic drawing sketch according to the target line width, the target line curvature, and the target line fluency to obtain the initial drawing sketch.

[0112] In step B2, a second prompt word is generated according to the user's photographed image, the target sketch style, the initial drawing sketch, and the color region generation task description information. The second prompt word is input into the drawing creation large model. The color region generation task description information is used to instruct the drawing creation large model to perform a first working step of color extraction processing on the user's photographed image, and then perform a second working step of configuring a color filling region corresponding to the initial drawing sketch according to the target sketch style and the extracted color information. The drawing creation large model performs color style configuration processing on the initial drawing sketch based on the target sketch style and the basic color information to obtain an initial color filling region. Specifically, the drawing creation large model can determine color filling parameters of each basic color filling region corresponding to the initial drawing sketch according to the basic color information, and the color filling parameters can include but are not limited to color categories, color saturation, color matching strategies, etc. The color filling parameters of each basic color filling region are adjusted according to the target sketch style to obtain the initial color filling region. It can be understood that the basic color filling region refers to a plurality of color regions divided from the initial drawing sketch according to the basic color information of the user's photographed image. For example, if the initial drawing sketch is a sketch of a sunset at sea, the basic color filling region can include a color region of the sea and a color region of the sky.

[0113] S204, obtaining drawing creation reference information corresponding to the user.

[0114] It can be understood that the drawing creation reference information can include user age information and drawing level evaluation information, and the drawing level evaluation information can be determined based on historical drawing works of the user.

[0115] Specifically, the user's age information and historical drawing works can be obtained from local storage. The drawing level evaluation information can be determined based on line evaluation, object shape evaluation, color evaluation, and composition evaluation of the historical drawing works. The drawing creation reference information can be generated based on the drawing level evaluation information and the user's age information. For example, the drawing creation reference information can include description information such as "low-age children with weak drawing basis" and "high-age children with high drawing level".

[0116] S205, performing line adjustment processing on the initial drawing sketch based on the drawing creation reference information by the drawing creation large model to obtain a drawing sketch, and performing color adjustment processing on the initial color filling region based on the drawing creation reference information to obtain a color filling region corresponding to the drawing sketch.

[0117] It can be understood that the drawing sketch is a line sketch that is adjusted based on the initial drawing sketch and is more suitable for the user to imitate, and the color filling region is a color region that is adjusted based on the initial color filling region and is more suitable for the user to fill colors.

[0118] Specifically, the painting operation reference information, the initial painting sketch and the initial color filling area are input to the painting creation large model, the line density and the line shape of the initial painting sketch are adjusted according to the painting creation reference information by the painting creation large model to obtain a painting sketch, and the color category, the color saturation and the color matching strategy of the initial color filling area are adjusted according to the painting creation reference information by the painting creation large model to obtain a color filling area.

[0119] In S206, the painting sketch is displayed to the user, the sketch copying operation data input by the user based on the painting sketch is obtained, and line drawing detection processing is performed based on the sketch copying operation data to obtain a line drawing detection result.

[0120] Specifically, the display area of the display screen can be divided into a sketch display area and a copying painting area, the painting sketch is displayed in the sketch display area, and the line drawing tool is displayed in the copying painting area, and the user can input the sketch copying operation data for the painting sketch in the copying painting area using the line drawing tool. The sketch copying operation data can be the operation data of the line input by the user using the line drawing tool, and the sketch copying operation data can include the line position, the line length, the line width and the line bending radian. The line drawing detection processing is performed on the line position, the line length, the line width and the line bending radian to obtain a line drawing detection result.

[0121] The line drawing detection processing is performed on the line position, the line length, the line width and the line bending radian. Specifically, it can be detected whether the first deviation value of the line position exceeds the first preset value, whether the second deviation value of the line length and the preset length exceeds the second preset value, whether the third deviation value of the line width and the preset width exceeds the third preset value, and whether the fourth deviation value of the line bending radian and the preset bending radian exceeds the fourth preset value. When any one of the above-mentioned first deviation value, second deviation value, third deviation value and fourth deviation value exceeds the corresponding preset value, a line drawing detection result of a drawing error type is generated. When all of the above-mentioned first deviation value, second deviation value, third deviation value and fourth deviation value do not exceed the corresponding preset value, a line drawing detection result of a correct drawing type is generated.

[0122] In S207, if the line drawing detection result is of the drawing error type, a line drawing prompt is output to the user.

[0123] When the line drawing detection result is a drawing error type, a reference deviation value indicated by the line drawing detection result is determined, the reference deviation value is a deviation value exceeding a corresponding preset value, the reference deviation value can be any one of the first deviation value, the second deviation value, the third deviation value, and the fourth deviation value, a line drawing prompt corresponding to the reference deviation value is determined, and the line drawing prompt is output to the user, such as being displayed on the display screen or outputting a voice prompt corresponding to the line drawing prompt.

[0124] In S208, if the line drawing detection result is a drawing correct type, the user-drawn sketch is generated when the drawing sketch is determined to be in a drawing completion state.

[0125] When the line drawing detection result is a drawing correct type, the drawing state of the drawing sketch is monitored, and the user-drawn line is combined to generate the user-drawn sketch when the drawing sketch is monitored to be in a drawing completion state.

[0126] In S209, when the drawing sketch is determined to be in a drawing completion state, the color filling area is displayed to the user, color filling operation data input by the user based on the color filling area is obtained, and color filling detection processing based on the color filling operation data is performed to obtain a color filling detection result.

[0127] Specifically, the drawing sketch and the color filling area are displayed in the sketch display area, and the color filling tool is displayed in the sketching area. The user can input color filling operation data for the color filling area using the color filling tool in the sketching area. The color filling operation data can be operation data input by the user using the color filling tool. The color filling operation data can include a filling color and a filling area corresponding to the filling color. The filling color and the filling area are subjected to color filling detection processing to obtain a color filling detection result.

[0128] The filling color and the filling area are subjected to color filling detection processing to obtain a color filling detection result. Specifically, it can be detected whether the filling color is a correct color, and whether the area deviation degree of the filling area and a preset area corresponding to the color filling area exceeds a deviation degree threshold. When the filling color is a correct color and the area deviation degree does not exceed the deviation degree threshold, a color filling detection result of a filling correct type is generated. When the filling color is an incorrect color and / or the area deviation degree exceeds the deviation degree threshold, a color filling detection result of a filling error type is generated.

[0129] In S210, if the color filling detection result is a filling error type, a color filling prompt is output to the user.

[0130] It can be understood that the color filling prompt can include a first filling prompt and a second filling prompt, the first filling prompt can be used to prompt the user that the color filling color is an error color and prompt the user for the correct filling color, and the second filling prompt can be used to prompt the user that the color filling area is incorrect and prompt the user for the correct color filling range.

[0131] When the color filling detection result is a filling error type, if it is determined that the filling color is an error color, a first filling prompt corresponding to the filling color is obtained, and the first filling prompt is output to the user; if it is determined that the area deviation of the color filling area from the preset area exceeds the deviation threshold, a second filling prompt corresponding to the color filling area is obtained, and the second filling prompt is output to the user.

[0132] S211, if the color filling detection result is a filling correct type, when it is determined that the color filling area is in a filling completion state, the user-drawn line drawing is color filled based on the color filling data to obtain an initial painting work.

[0133] The color filling processing of the user-drawn line drawing based on the color filling data to obtain the initial painting work can be specifically that a color filling area is generated according to the color filling data, and the color filling area and the user-drawn line drawing are combined to generate the initial painting work.

[0134] S212, the initial painting work is subjected to painting detail detection processing by the painting creation large model to obtain a painting detail perfect area, and the painting detail perfect area is displayed to the user.

[0135] In some embodiments, the painting detail perfect area obtained by the painting creation large model based on the initial painting work can be obtained by: C1: determining a mimic similarity based on the initial painting work and the target mimic sketch by the painting creation large model, and determining a to-be-adjusted area in the initial painting work based on the mimic similarity; and C2: determining a detail perfect prompt corresponding to the to-be-adjusted area by the painting creation large model, and generating the painting detail perfect area based on the to-be-adjusted area and the detail perfect prompt.

[0136] In step C1, the initial painting work and the target mimic sketch are input to the painting creation large model, the painting creation large model calculates a mimic similarity of the initial painting work and the target mimic sketch, a preset similarity corresponding to the user is determined based on the painting creation reference information, and when the mimic similarity is less than the preset similarity, a to-be-adjusted area in the initial painting work is identified. The to-be-adjusted area can be an area that needs to add a shadow, an area that needs to refine an object contour, or an area that needs to modify a color gradient effect, and the like.

[0137] In step C2, a detail improvement prompt corresponding to the to-be-adjusted region is determined by the large model created by the drawing, and the detail improvement prompt is added to the to-be-adjusted region in the form of a mark to obtain a drawing detail improvement region. For example, for a to-be-adjusted region that needs to add a shadow, the detail improvement prompt can be to add a shadow using color A. For another example, for a to-be-adjusted region that needs to modify the color gradient effect, the detail improvement prompt can be to transition from color B to color C.

[0138] Specifically, the drawing detail improvement region can be displayed in the mimic drawing region.

[0139] In S213, second drawing operation data input by the user based on the drawing detail improvement region is obtained, and a target drawing work is generated based on the second drawing operation data.

[0140] Specifically, the user can input second drawing operation data for the drawing detail improvement region using a drawing tool in the mimic drawing region. The second drawing operation data can be operation data input by the user using the drawing tool. The second drawing operation data can include line drawing data and / or color filling data drawn in the drawing detail improvement region. The drawing detail improvement region in the initial drawing work is updated according to the second drawing operation data to generate a target drawing work.

[0141] In the drawing interaction method provided by the embodiment of the present application, the user's photographed image is obtained, the reference mimic sketch is obtained by performing sketch conversion processing on the user's photographed image through the large drawing creation model, the reference mimic sketch is displayed to the user, the target mimic sketch selected by the user for the reference mimic sketch is determined, the initial drawing draft is generated based on the target mimic sketch through the large drawing creation model, and the initial color filling area corresponding to the initial drawing draft is determined based on the user's photographed image. The drawing creation reference information corresponding to the user is obtained, the initial drawing draft is adjusted through the large drawing creation model based on the drawing creation reference information to obtain the drawing draft, and the initial color filling area is adjusted in color based on the drawing creation reference information to obtain the color filling area corresponding to the drawing draft. In this way, by fusing the drawing creation reference information of the user, the complexity of the drawing draft and the color filling area is dynamically adjusted, and a customized drawing scheme for the user is realized. Subsequently, the drawing draft is displayed to the user, the line draft copying operation data input by the user based on the drawing draft is obtained, line drawing detection processing is performed based on the line draft copying operation data to obtain a line drawing detection result, if the line drawing detection result is a drawing error type, a line drawing prompt is output to the user, if the line drawing detection result is a correct drawing type, the user's drawn line draft is generated when it is determined that the drawing draft is in a drawing completion state, the color filling area is displayed to the user when it is determined that the drawing draft is in the drawing completion state, the color filling operation data input by the user based on the color filling area is obtained, color filling detection processing is performed based on the color filling operation data to obtain a color filling detection result, if the color filling detection result is a filling error type, a color filling prompt is output to the user, if the color filling detection result is a correct filling type, the initial drawing work is obtained by performing color filling processing on the user's drawn line draft based on the color filling data when it is determined that the color filling area is in a filling completion state. In this way, the user's drawing behavior can be detected during the user's drawing process, and targeted guidance and feedback can be provided to the user in a timely manner to realize intelligent drawing learning guidance. Then, the drawing detail perfecting area is obtained by performing drawing detail detection processing on the initial drawing work through the large drawing creation model, the drawing detail perfecting area is displayed to the user, the second drawing operation data input by the user based on the drawing detail perfecting area is obtained, and the target drawing work is generated based on the second drawing operation data. In this way, by detecting the drawing complexity and the drawing work effect of the user, the user is provided with detail perfecting guidance, the user is guided to optimize the drawing work details, the drawing work completed by the user is more vivid and complete, the observability of the user's drawing work can be improved, the user's creation interest is further stimulated, and thus the user's drawing ability can be improved.

[0142] The embodiments of the present application will be described below in conjunction with Figure 3 The drawing interaction device provided by the embodiment of the present application will be described in detail. It should be noted that Figure 3 The drawing interaction device shown in the figure is used to execute theFigures 1-2 The method of the embodiment shown, for ease of illustration, only shows the part related to the embodiment of the present application, and the specific technical details not disclosed, please refer to the application Figures 1-2 The embodiment shown.

[0143] Please refer to Figure 3 , which shows the structure diagram of the drawing interaction device of the embodiment of the present application. The drawing interaction device 1 can be realized by software, hardware or combination of the two to become all or part of the device. According to some embodiments, the drawing interaction device 1 includes an image conversion module 11, a drawing conversion module 12, a drawing creation module 13, a drawing perfecting module 14 and a drawing generation module 15, which are specifically used for:

[0144] The image conversion module 11 is configured to obtain a user shot image, perform a sketch conversion processing on the user shot image by a drawing creation large model to obtain a reference mimic sketch, and show the reference mimic sketch to the user.

[0145] The drawing conversion module 12 is configured to determine a target mimic sketch selected by the user for the reference mimic sketch, perform a drawing customization processing based on the target mimic sketch by the drawing creation large model to obtain a drawing draft and a color filling area corresponding to the drawing draft.

[0146] The drawing creation module 13 is configured to show the drawing draft and the color filling area to the user, obtain first drawing operation data input by the user based on the drawing draft and the color filling area, and generate an initial drawing work based on the first drawing operation data.

[0147] The drawing perfecting module 14 is configured to perform a drawing detail detection processing on the initial drawing work by the drawing creation large model to obtain a drawing detail perfecting area, and show the drawing detail perfecting area to the user.

[0148] The drawing generation module 15 is configured to obtain second drawing operation data input by the user based on the drawing detail perfecting area, and generate a target drawing work based on the second drawing operation data.

[0149] Optionally, please refer to Figure 4 The structure diagram of a drawing conversion module 12 shown, the drawing conversion module 12 includes a drawing conversion unit 121, an information acquisition unit 122 and a draft adjustment unit 123, which includes:

[0150] The drawing conversion unit 121 is configured to generate an initial drawing draft based on the target mimic sketch by the drawing creation large model, and determine an initial color filling area corresponding to the initial drawing draft based on the user shot image.

[0151] The information acquisition unit 122 is configured to acquire painting creation reference information corresponding to the user.

[0152] The sketch adjustment unit 123 is configured to perform sketch adjustment processing on the initial painting sketch based on the painting creation reference information by using the painting creation large model to obtain a painting sketch, and perform color adjustment processing on the initial color filling area based on the painting creation reference information to obtain a color filling area corresponding to the painting sketch.

[0153] Optionally, the painting conversion unit 121 is specifically configured to:

[0154] determine a target sketch style corresponding to the target mimic sketch by using the painting creation large model, perform line extraction processing on the target mimic sketch to obtain a basic painting sketch, and perform sketch style adaptation processing on the basic painting sketch based on the target sketch style to obtain an initial painting sketch;

[0155] perform color extraction processing on the user's photographed image based on the painting creation large model to obtain basic color information, and perform color style configuration processing on the initial painting sketch based on the target sketch style and the basic color information to obtain an initial color filling area.

[0156] Optionally, the painting creation module 13 is specifically configured to:

[0157] display the painting sketch to the user, acquire line sketch copying operation data input by the user based on the painting sketch, and perform line drawing detection processing based on the line sketch copying operation data to obtain a line drawing detection result;

[0158] If the line drawing detection result is a drawing error type, output a line drawing prompt to the user;

[0159] If the line drawing detection result is a correct drawing type, generate a user-drawn sketch when it is determined that the painting sketch is in a drawing completion state.

[0160] When it is determined that the painting sketch is in a drawing completion state, display the color filling area to the user, acquire color filling operation data input by the user based on the color filling area, and perform color filling detection processing based on the color filling operation data to obtain a color filling detection result.

[0161] If the color filling detection result is a filling error type, output a color filling prompt to the user.

[0162] If the color filling detection result is a correct filling type, when it is determined that the color filling area is in a filling completion state, the user-drawn sketch is color-filled based on the color filling data to obtain an initial painting work.

[0163] Optionally, the painting perfecting module 14 is specifically configured to:

[0164] determine, by the painting creation large model, a mimic similarity based on the initial painting work and the target mimic sketch, and determine a to-be-adjusted area in the initial painting work based on the mimic similarity;

[0165] determine, by the painting creation large model, a detail perfecting prompt corresponding to the to-be-adjusted area, and generate a painting detail perfecting area based on the to-be-adjusted area and the detail perfecting prompt.

[0166] Optionally, the image conversion module 11 comprises:

[0167] a style determining unit configured to determine a reference sketch style corresponding to the user-shot image;

[0168] a sketch converting unit configured to perform sketch conversion processing on the user-shot image based on the reference sketch style by the painting creation large model to obtain a reference mimic sketch.

[0169] Optionally, the style determining unit is specifically configured to:

[0170] obtain user age information, and determine the reference sketch style corresponding to the user-shot image based on the user age information; or

[0171] obtain historical painting data of the user, and determine the reference sketch style corresponding to the user-shot image based on the historical painting data.

[0172] The drawing interaction device provided by the embodiment of the present application can obtain a reference imitation sketch by converting a user's photographed image into a sketch through a drawing creation large model, so that the user can select a target imitation sketch from the reference imitation sketch, obtain a drawing draft and a color filling area corresponding to the drawing draft by performing drawing customization processing on the target imitation sketch through the drawing creation large model, show the user the drawing draft and the color filling area, obtain first drawing operation data input by the user based on the drawing draft and the color filling area, generate an initial drawing work based on the first drawing operation data, obtain a drawing detail perfecting area by performing drawing detail detection processing on the initial drawing work through the drawing creation large model, show the user the drawing detail perfecting area, obtain second drawing operation data input by the user based on the drawing detail perfecting area, and generate a target drawing work based on the second drawing operation data. Thus, the present application can first convert a real scene photo into an imitation sketch, then gradually generate a draft and a color filling area for sketching after the user selects a target imitation sketch for copying, and guide the user to complete the draft copying, coloring operation and detail perfecting operation in sequence, thereby enriching the drawing interaction function of the intelligent shooting device and helping the user improve the drawing ability.

[0173] Please refer to Figure 5 , Figure 5 A structural schematic diagram of an electronic device is provided for the embodiment of the present application. The electronic device can include one or more of the following components: a processor 110, a memory 120, an input device 130, an output device 140, and a bus 150. The processor 110, the memory 120, the input device 130, and the output device 140 can be connected through the bus 150.

[0174] The processor 110 can include one or more processing cores. The processor 110 connects various parts within the entire electronic device by various interfaces and lines, performs various functions of the electronic device and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 120, and calling data stored in the memory 120. Alternatively, the processor 110 can be implemented in at least one of a hardware form of a digital signal processing (DSP), a field-programmable gate array (FPGA), a programmable logic array (PLA). The processor 110 can integrate a combination of one or several of a central processing unit (CPU), a graphics processing unit (GPU), and a modem, etc. Among them, the CPU mainly processes an operating system, a user interface, and an application program, etc.; the GPU is responsible for rendering and drawing display content; and the modem is used for processing wireless communication. It can be understood that the above-mentioned modem can also not be integrated into the processor 110, but be implemented by a separate communication chip.

[0175] The memory 120 can include a random access memory (RAM) and can also include a read-only memory (ROM). Optionally, the memory 120 includes a non-transitory computer-readable storage medium. The memory 120 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 120 can include a program storage area and a data storage area, wherein the program storage area can store instructions for implementing an operating system, instructions for implementing at least one function (such as a touch function, a sound playing function, an image playing function, etc.), instructions for implementing each of the following method embodiments, etc., and the operating system can be an Android system, an IOS system developed by Apple Inc., a system developed based on the Android system or other systems.

[0176] In order to enable the operating system to distinguish the specific application scenarios of the third-party application, it is necessary to open up the data communication between the third-party application and the operating system, so that the operating system can obtain the current scenario information of the third-party application at any time, and then perform targeted system resource adaptation based on the current scenario.

[0177] The input device 130 is configured to receive input instructions or data, and the input device 130 includes but is not limited to a keyboard, a mouse, a camera, a microphone, or a touch device. The output device 140 is configured to output instructions or data, and the output device 140 includes but is not limited to a display device and a speaker. In an example, the input device 130 and the output device 140 can be combined, and the input device 130 and the output device 140 are a touch display screen.

[0178] The touch display screen can be designed as a full screen, a curved screen, or a special-shaped screen. The touch display screen can also be designed as a combination of a full screen and a curved screen, a combination of a special-shaped screen and a curved screen, and the present application does not limit this.

[0179] In addition, those skilled in the art can understand that the structure of the electronic device shown in the above-mentioned drawings does not constitute a limitation on the electronic device, and the electronic device can include more or fewer components than the drawings, or combine certain components, or different component arrangements. For example, the electronic device also includes radio frequency circuitry, an input unit, a sensor, audio circuitry, a wireless fidelity (WiFi) module, a power supply, a Bluetooth module, and the like, which are not described here.

[0180] In Figure 5 In the electronic device shown, the processor 110 can be configured to call the program of the drawing interaction method stored in the memory 120, and specifically perform the following operations:

[0181] Obtain a user-shot image, perform a sketch conversion process on the user-shot image by a drawing creation large model to obtain a reference mimic sketch, and show the reference mimic sketch to the user;

[0182] Determine a target mimic sketch selected by the user for the reference mimic sketch, perform drawing customization processing based on the target mimic sketch by the drawing creation large model to obtain a drawing draft and a color filling area corresponding to the drawing draft;

[0183] Show the drawing draft and the color filling area to the user, obtain first drawing operation data input by the user based on the drawing draft and the color filling area, and generate an initial drawing work based on the first drawing operation data;

[0184] Perform drawing detail detection processing on the initial drawing work by the drawing creation large model to obtain a drawing detail perfecting area, and show the drawing detail perfecting area to the user;

[0185] Obtain second drawing operation data input by the user based on the drawing detail perfecting area, and generate a target drawing work based on the second drawing operation data.

[0186] In some embodiments, the processor 110, in performing the step of generating, by the painting creation large model, an initial painting sketch based on the target mimic sketch, and determining an initial color filling area corresponding to the initial painting sketch based on the user-shot image, specifically performs the following operations:

[0187] generating, by the painting creation large model, an initial painting sketch based on the target mimic sketch, and determining an initial color filling area corresponding to the initial painting sketch based on the user-shot image;

[0188] obtaining painting creation reference information corresponding to the user;

[0189] adjusting, by the painting creation large model, the initial painting sketch based on the painting creation reference information to obtain a painting sketch, and adjusting the initial color filling area based on the painting creation reference information to obtain a color filling area corresponding to the painting sketch.

[0190] In some embodiments, the processor 110, in performing the step of generating, by the painting creation large model, an initial painting sketch based on the target mimic sketch, and determining an initial color filling area corresponding to the initial painting sketch based on the user-shot image, specifically performs the following operations:

[0191] determining, by the painting creation large model, a target sketch style corresponding to the target mimic sketch, extracting, based on the target mimic sketch, a line to obtain a basic painting sketch, and adapting, based on the target sketch style, the line style of the basic painting sketch to obtain an initial painting sketch;

[0192] extracting, by the painting creation large model, color information based on the user-shot image, and configuring, based on the target sketch style and the basic color information, the color style of the initial painting sketch to obtain an initial color filling area.

[0193] In some embodiments, the processor 110, in performing the step of displaying the painting sketch and the color filling area to the user, obtaining first painting operation data input by the user based on the painting sketch and the color filling area, and generating an initial painting work based on the first painting operation data, specifically performs the following operations:

[0194] displaying the painting sketch to the user, obtaining line sketch copying operation data input by the user based on the painting sketch, and performing line drawing detection processing based on the line sketch copying operation data to obtain a line drawing detection result;

[0195] If the line drawing detection result is a drawing error type, a line drawing prompt is output to the user;

[0196] If the line drawing detection result is a correct drawing type, a user-drawn sketch is generated when it is determined that the drawing sketch is in a drawing completion state;

[0197] When it is determined that the drawing sketch is in a drawing completion state, the color filling area is displayed to the user, color filling operation data input by the user based on the color filling area is obtained, and color filling detection processing is performed based on the color filling operation data to obtain a color filling detection result.

[0198] If the color filling detection result is a filling error type, a color filling prompt is output to the user.

[0199] If the color filling detection result is a correct filling type, an initial painting work is obtained by performing color filling processing on the user-drawn sketch based on the color filling data when it is determined that the color filling area is in a filling completion state.

[0200] In some embodiments, when the processor 110 performs the step of performing painting detail detection processing on the initial painting work by the painting creation large model to obtain a painting detail improvement area, the following operations are specifically performed:

[0201] Determining a mimic similarity based on the initial painting work and the target mimic sketch by the painting creation large model, and determining an adjustment area in the initial painting work based on the mimic similarity;

[0202] Determining a detail improvement prompt corresponding to the adjustment area by the painting creation large model, and generating a painting detail improvement area based on the adjustment area and the detail improvement prompt.

[0203] In some embodiments, when the processor 110 performs the step of performing sketch conversion processing on the user-shot image by the painting creation large model to obtain a reference mimic sketch, the following operations are specifically performed:

[0204] Determining a reference sketch style corresponding to the user-shot image;

[0205] Performing sketch conversion processing on the user-shot image based on the reference sketch style by the painting creation large model to obtain a reference mimic sketch.

[0206] In some embodiments, when the processor 110 performs the step of determining the reference sketch style corresponding to the user-shot image, the following operations are specifically performed:

[0207] obtaining user age information, determining the reference sketch style corresponding to the image shot by the user based on the user age information; or

[0208] obtaining historical drawing data of the user, and determining the reference sketch style corresponding to the image shot by the user based on the historical drawing data.

[0209] The embodiments of the present application further provide a computer readable storage medium, which stores at least one instruction, and the at least one instruction is used for being executed by a processor to implement the drawing interaction method in the above various embodiments.

[0210] The embodiments of the present application further provide a computer program product, which stores at least one instruction, and the at least one instruction is loaded and executed by the processor to implement the drawing interaction method in the above various embodiments.

[0211] Those skilled in the art should be aware that the functions described in the above one or more examples can be implemented in hardware, software, firmware or any combination thereof. When implemented in software, the functions can be stored in a computer readable medium or transmitted as one or more instructions or codes on a computer readable medium. The computer readable medium includes computer storage medium and communication medium, and the communication medium includes any medium that facilitates the transfer of computer programs from one place to another. The storage medium can be any available medium that can be accessed by a general or special purpose computer.

[0212] The above description is only optional embodiments of the present application, and does not limit the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A painting interaction method, characterized in that: Applied to a smart camera device, the method includes: Acquire an image taken by a user, convert the image taken by the user into a stick figure using a painting creation model to obtain a reference imitation stick figure, and display the reference imitation stick figure to the user; Determining a target imitation stick figure selected by the user for the reference imitation stick figure, and performing a painting customization process based on the target imitation stick figure using the painting creation macro model to obtain a painting line drawing and a color-filled area corresponding to the painting line drawing; showing the drawing line drawing and the color-filled area to the user, obtaining first drawing operation data input by the user based on the drawing line drawing and the color-filled area, and generating an initial drawing based on the first drawing operation data; performing painting detail detection processing on the initial painting work using the painting creation macro model to obtain a painting detail improvement area, and displaying the painting detail improvement area to the user; Second painting operation data input by the user based on the painting detail improvement area is acquired, and a target painting work is generated based on the second painting operation data.

2. The method according to claim 1, characterized in that The step of performing a custom painting process based on the target imitating stick figure through the painting creation large model to obtain a painting line drawing and a color-filled area corresponding to the painting line drawing includes: Generating an initial painting line draft based on the target imitation stick figure using the painting creation large model, and determining an initial color filling area corresponding to the initial painting line draft based on the user-captured image; Obtaining the painting creation reference information corresponding to the user; The painting creation large model adjusts the initial painting line draft based on the painting creation reference information to obtain the painting line draft, and the initial color filling area is color-adjusted based on the painting creation reference information to obtain the color filling area corresponding to the painting line draft.

3. The method according to claim 2, characterized in that The step of generating an initial painting line draft based on the target imitation stick figure using the painting creation large model, and performing color extraction processing based on the user-photographed image to obtain an initial color-filled area corresponding to the initial painting line draft includes: Determining a target stick figure style corresponding to the target imitation stick figure using the painting creation large model, performing line extraction processing based on the target imitation stick figure to obtain a basic painting line draft, and performing line draft style adaptation processing on the basic painting line draft based on the target stick figure style to obtain an initial painting line draft; The painting creation model performs color extraction processing based on the user-shot image to obtain basic color information, and performs color style configuration processing on the initial painting line draft based on the target simple drawing style and the basic color information to obtain an initial color filling area.

4. The method according to claim 1, wherein The step of displaying the drawing line drawing and the color-filled area to the user, obtaining first drawing operation data input by the user based on the drawing line drawing and the color-filled area, and generating an initial drawing based on the first drawing operation data includes: Displaying the drawing line draft to the user, obtaining line draft copying operation data input by the user based on the drawing line draft, and performing line drawing detection processing based on the line draft copying operation data to obtain a line drawing detection result; If the line drawing detection result is a drawing error type, outputting a line drawing prompt to the user; If the line drawing detection result is a correct drawing type, then when it is determined that the drawing line draft is in a drawing completion state, generating a user drawing line draft; When it is determined that the drawing line draft is in a drawing completion state, the color filling area is displayed to the user, color filling operation data input by the user based on the color filling area is obtained, and color filling detection processing is performed based on the color filling operation data to obtain a color filling detection result; If the color filling detection result is a filling error type, outputting a color filling prompt to the user; If the color filling detection result is a correct filling type, when it is determined that the color filling area is in a filling completion state, the user-drawn line drawing is color-filled based on the color filling data to obtain an initial painting work.

5. The method according to claim 1, wherein The step of performing painting detail detection on the initial painting work using the painting creation large model to obtain a painting detail improvement area includes: Determining an imitation similarity based on the initial painting and the target imitation stick figure using the painting creation macro model, and determining a region to be adjusted in the initial painting based on the imitation similarity; The detail improvement prompt corresponding to the area to be adjusted is determined through the painting creation model, and a painting detail improvement area is generated based on the area to be adjusted and the detail improvement prompt.

6. The method according to claim 1, characterized in that The step of converting the user-photographed image into a stick figure using the painting creation model to obtain a reference imitation stick figure includes: Determining a reference stick figure style corresponding to the image captured by the user; The painting creation model performs a simple drawing conversion process on the user-captured image based on the reference simple drawing style to obtain a reference imitation simple drawing.

7. The method according to claim 6, characterized in that The determining of a reference stick figure style corresponding to the image captured by the user includes: Acquiring user age information, and determining a reference stick figure style corresponding to the image captured by the user based on the user age information; or, The user's historical drawing data is obtained, and a reference stick figure style corresponding to the user's captured image is determined based on the historical drawing data.

8. A painting interactive device, characterized in that: Applied to intelligent photographing equipment, the device comprises: An image conversion module is used to obtain an image taken by a user, convert the image taken by the user into a stick figure using a painting creation model to obtain a reference imitation stick figure, and display the reference imitation stick figure to the user; A painting conversion module is used to determine a target imitation stick figure selected by the user for the reference imitation stick figure, and perform painting customization processing based on the target imitation stick figure using the painting creation macro model to obtain a painting line drawing and a color-filled area corresponding to the painting line drawing; a painting creation module, configured to display the painting line drawing and the color-filled area to the user, obtain first painting operation data input by the user based on the painting line drawing and the color-filled area, and generate an initial painting work based on the first painting operation data; a painting improvement module, configured to perform painting detail detection processing on the initial painting work using the painting creation macromodel to obtain a painting detail improvement area, and display the painting detail improvement area to the user; The painting generation module is configured to obtain second painting operation data input by the user based on the painting detail improvement area, and generate a target painting based on the second painting operation data.

9. A computer storage medium, characterized in that The computer storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing the method according to any one of claims 1 to 7.

10. An electronic device, characterized in that: include: A processor and a memory; wherein the memory stores a computer program, and the computer program is suitable for being loaded by the processor and executing the method according to any one of claims 1 to 7.

Images