Batch drawing method and device based on multiple intelligent drawing models, equipment and medium

Abstract

The invention provides a batch drawing method and device based on multiple intelligent drawing models, equipment and a medium, and the method comprises the steps that a batch drawing task is created, the batch drawing task comprises a plurality of drawing sub-tasks, and each drawing sub-task corresponds to a first drawing prompt word; obtaining a model database, wherein the model database comprises a plurality of AI drawing models; based on the first drawing prompt word corresponding to each drawing subtask, a corresponding target drawing model group is determined from a plurality of AI drawing models included in a model database, and the target drawing model group comprises at least two target drawing models; and performing image batch drawing based on the first drawing prompt word corresponding to each drawing sub-task by adopting the at least two target drawing models corresponding to each drawing sub-task to obtain a batch drawing result corresponding to the batch drawing task. Therefore, the corresponding images are intelligently drawn through the multiple AI drawing models built in the system, and the image generation efficiency is effectively improved.

Description

Technical Field

[0001] Embodiments of the present disclosure relate to the field of intelligent drawing technology, and in particular, to a batch drawing method, apparatus, device and medium based on a multi-intelligent drawing model. Background Art

[0002] With the rapid development of artificial intelligence (AI) technology, AI-assisted creation has become an important trend in the fields of design and art. These AI models can generate high-quality images based on text descriptions, providing creative workers with new creative tools.

[0003] In the related art, when performing intelligent image rendering, simplified image production is mainly performed through a single AI model built into the system to complete the image rendering work. However, when using the existing method to process large-scale batch image rendering, the image generation efficiency is low. Summary of the invention

[0004] The embodiments described herein provide a batch drawing method, apparatus, device and medium based on a multi-intelligent drawing model, which overcomes the above-mentioned problems.

[0005] In a first aspect, according to the content of the present disclosure, a batch drawing method based on a multi-intelligent drawing model is provided, comprising:

[0006] Creating a batch drawing task, wherein the batch drawing task includes: a plurality of drawing subtasks, each of the drawing subtasks corresponds to a first drawing prompt word, and the drawing subtask is used to describe a model drawing task of drawing an image;

[0007] Acquire a model database, wherein the model database includes: a plurality of AI drawing models;

[0008] Based on the first drawing prompt word corresponding to each of the drawing subtasks, determining a corresponding target drawing model group from a plurality of AI drawing models included in the model database, wherein the target drawing model group includes: at least two target drawing models, and the target drawing model is an AI drawing model included in the model database;

[0009] Using at least two target drawing models corresponding to each drawing subtask, and performing batch drawing of images based on the first drawing prompt word corresponding to each drawing subtask, to obtain batch drawing results corresponding to the batch drawing tasks;

[0010] The batch drawing results include: a plurality of target drawing images, each of which corresponds to one of the drawing subtasks.

[0011] In a second aspect, according to the content of the present disclosure, a batch drawing device based on a multi-intelligent drawing model is provided, comprising:

[0012] A creation module, used for creating a batch drawing task, wherein the batch drawing task includes: a plurality of drawing subtasks, each of which corresponds to a first drawing prompt word, and the drawing subtask is used for describing a model drawing task of drawing an image;

[0013] An acquisition module, used to acquire a model database, wherein the model database includes: a plurality of AI drawing models;

[0014] a determination module, configured to determine a corresponding target drawing model group from a plurality of AI drawing models included in the model database based on the first drawing prompt word corresponding to each of the drawing subtasks, wherein the target drawing model group includes: at least two target drawing models, and the target drawing model is an AI drawing model included in the model database;

[0015] A drawing module, configured to use at least two target drawing models corresponding to each drawing subtask, perform batch drawing of images based on the first drawing prompt word corresponding to each drawing subtask, and obtain batch drawing results corresponding to the batch drawing tasks;

[0016] The batch drawing results include: a plurality of target drawing images, each of which corresponds to one of the drawing subtasks.

[0017] In a third aspect, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the steps of the batch drawing method based on the multi-intelligent drawing model in any of the above embodiments are implemented.

[0018] In a fourth aspect, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the batch drawing method based on the multi-intelligent drawing model in any of the above embodiments are implemented.

[0019] The batch drawing method based on multiple intelligent drawing models provided in the embodiment of the present application creates a batch drawing task, wherein the batch drawing task includes: multiple drawing subtasks, each drawing subtask corresponds to a first drawing prompt word, and the drawing subtask is used to describe a model drawing task of drawing an image; obtain a model database, wherein the model database includes: multiple AI drawing models; based on the first drawing prompt word corresponding to each drawing subtask, determine the corresponding target drawing model group from the multiple AI drawing models included in the model database, wherein the target drawing model group includes: at least two target drawing models, and the target drawing model is an AI drawing model included in the model database; use at least two target drawing models corresponding to each drawing subtask, and perform batch drawing of images based on the first drawing prompt word corresponding to each drawing subtask, and obtain batch drawing results corresponding to the batch drawing task; wherein the batch drawing results include: multiple target drawing images, and each target drawing image corresponds to a drawing subtask. In this way, the intelligent drawing of the corresponding images is performed respectively through the multiple AI drawing models built into the system, which effectively improves the efficiency of image generation.

[0020] The above description is only an overview of the technical solution of the embodiment of the present application. In order to more clearly understand the technical means of the embodiment of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the embodiment of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings of the embodiments will be briefly described below. It should be noted that the drawings described below only relate to some embodiments of the present disclosure, but are not intended to limit the present disclosure, wherein:

[0022] Figure 1 It is a flow chart of a batch drawing method based on a multi-intelligent drawing model provided by the present disclosure.

[0023] Figure 2 It is a structural schematic diagram of a batch drawing device based on a multi-intelligent drawing model provided by the present disclosure.

[0024] Figure 3 It is a structural schematic diagram of a computer device provided by the present disclosure.

[0025] It should be noted that the elements in the drawings are schematic and not drawn to scale. DETAILED DESCRIPTION

[0026] In order to make the purpose, technical solution and advantages of the embodiments of the present disclosure clearer, the technical solution of the embodiments of the present disclosure will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present disclosure, rather than all of the embodiments. Based on the described embodiments of the present disclosure, all other embodiments obtained by those skilled in the art without creative work also fall within the scope of protection of the present disclosure.

[0027] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by a person skilled in the art to which the subject matter of the present disclosure belongs. It will be further understood that terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the specification and the relevant art, and will not be interpreted in an idealized or overly formal form unless otherwise explicitly defined herein. As used herein, a statement that two or more parts are "connected" or "coupled" together shall mean that the parts are joined together directly or through one or more intermediate components.

[0028] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase "embodiments" in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0029] The term "and / or" in this article is only a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can mean: A exists, A and B exist at the same time, and B exists. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship. Terms such as "first" and "second" are only used to distinguish one component (or a part of a component) from another component (or another part of a component).

[0030] In the description of the present application, unless otherwise specified, "plurality" means more than two (including two), and similarly, "multiple groups" means more than two groups (including two).

[0031] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0032] Figure 1 is a flow chart of a batch drawing method based on a multi-intelligent drawing model provided by an embodiment of the present disclosure, such as Figure 1As shown, the specific process of the batch drawing method based on the multi-intelligent drawing model includes:

[0033] S110: creating a batch drawing task, wherein the batch drawing task includes: a plurality of drawing subtasks, each drawing subtask corresponding to a first drawing prompt word.

[0034] Among them, the batch drawing task can be a plurality of drawing subtasks created by the user in the drawing system through the user device, and the first drawing prompt word corresponding to each drawing subtask can be customized by the user, or can be randomly generated by the drawing system based on each drawing subtask.

[0035] The drawing subtask can be used to describe a model drawing task of drawing an image. That is, the task goal corresponding to a drawing subtask is to draw a generated image through the AI ​​model.

[0036] The first drawing prompt word can be a drawing reference word corresponding to the drawing subtask. For example, the first drawing prompt word is "ink painting, summer, pond, jade lotus leaves, several people in a boat, sparkling water", "people under task CG style lighting, high details, movie-level lighting, light leakage effect", "lion and lion cub, high details, grassland, movie-level lighting".

[0037] It should be noted that the first drawing prompt word corresponding to a drawing subtask may be one or at least two, that is, a drawing subtask may correspond to one first drawing prompt word (such as "ink painting"), or a drawing subtask may correspond to multiple first drawing prompt words (such as "ink painting, summer, etc.").

[0038] S120, obtaining a model database, wherein the model database includes: a plurality of AI drawing models.

[0039] Among them, each AI drawing model included in the model database may correspond to a drawing category identifier, and the drawing category identifier is used to describe the image category of the image drawn by the corresponding AI drawing model, such as landscape images, animal images, plant images, etc.

[0040] S130. Based on the first drawing prompt word corresponding to each drawing subtask, determine a corresponding target drawing model group from a plurality of AI drawing models included in the model database, wherein the target drawing model group includes: at least two target drawing models.

[0041] The target drawing model is an AI drawing model included in the model database. That is, at least two target drawing models are selected from multiple AI drawing models, and each target drawing model may correspond to an AI drawing model.

[0042] In some embodiments, each AI drawing model included in the model database corresponds to a drawing category identifier.

[0043] Based on the first drawing prompt word corresponding to each drawing subtask, determining a corresponding target drawing model group from a plurality of AI drawing models included in the model database includes:

[0044] Match the first drawing prompt word corresponding to each drawing subtask with the drawing category identification word corresponding to each AI drawing model; determine the AI ​​drawing models corresponding to at least two drawing category identification words that have a matching relationship with the first drawing prompt word corresponding to the drawing subtask as the target drawing models corresponding to the drawing subtask, so as to obtain a target drawing model group corresponding to each drawing subtask.

[0045] Among them, the at least two drawing category identification words having a matching relationship with the first drawing prompt word corresponding to the drawing subtask may be drawing category identification words corresponding to the AI ​​drawing model whose matching degree with the first drawing prompt word corresponding to the drawing subtask exceeds a matching threshold.

[0046] For example, the model database includes 5 AI drawing models, namely model 1, model 2, model 3, model 4 and model 5, the matching threshold is 75%, the matching degree of the drawing category identification word corresponding to model 1 and the first drawing prompt word corresponding to the drawing subtask is 76%, the matching degree of the drawing category identification word corresponding to model 2 and the first drawing prompt word corresponding to the drawing subtask is 73%, the matching degree of the drawing category identification word corresponding to model 3 and the first drawing prompt word corresponding to the drawing subtask is 85%, the matching degree of the drawing category identification word corresponding to model 4 and the first drawing prompt word corresponding to the drawing subtask is 90%, and the matching degree of the drawing category identification word corresponding to model 5 and the first drawing prompt word corresponding to the drawing subtask is 62%. Then, the AI ​​drawing models corresponding to at least two drawing category identification words that have a matching relationship with the first drawing prompt word corresponding to the drawing subtask are: model 1, model 3 and model 4 respectively.

[0047] It should be noted that after matching the first drawing prompt word corresponding to each drawing subtask with the drawing category identification word corresponding to each AI drawing model, if the number of drawing category identification words that have a matching relationship with the first drawing prompt word corresponding to the corresponding drawing subtask in the matching result is less than 2, then one or more drawing category identification words are selected from the matched drawing category identification words in order of the matching degree with the first drawing prompt word corresponding to the corresponding drawing subtask from high to low, so as to obtain the AI ​​drawing model corresponding to at least two drawing category identification words that have a matching relationship with the first drawing prompt word corresponding to the drawing subtask.

[0048] For example, the model database includes 5 AI drawing models, namely model 6, model 7, model 8, model 9 and model 10, the matching threshold is 75%, the matching degree of the drawing category identification word corresponding to model 6 and the first drawing prompt word corresponding to the drawing subtask is 76%, the matching degree of the drawing category identification word corresponding to model 7 and the first drawing prompt word corresponding to the drawing subtask is 63%, the matching degree of the drawing category identification word corresponding to model 8 and the first drawing prompt word corresponding to the drawing subtask is 65%, the matching degree of the drawing category identification word corresponding to model 9 and the first drawing prompt word corresponding to the drawing subtask is 55%, and the matching degree of the drawing category identification word corresponding to model 10 and the first drawing prompt word corresponding to the drawing subtask is 40%. Then, the AI ​​drawing models corresponding to at least two drawing category identification words that have a matching relationship with the first drawing prompt word corresponding to the drawing subtask are: model 6 and model 8 respectively.

[0049] Therefore, by determining the AI ​​drawing models corresponding to at least two drawing category identification words having a matching relationship with the first drawing prompt word corresponding to the drawing subtask, the target drawing model corresponding to the drawing subtask is effectively matched.

[0050] S140: Using at least two target drawing models corresponding to each drawing subtask, and performing batch drawing of images based on the first drawing prompt word corresponding to each drawing subtask, to obtain batch drawing results corresponding to the batch drawing tasks.

[0051] The batch drawing result includes: a plurality of target drawing images, each target drawing image corresponds to a drawing subtask, that is, the task drawing result of a drawing subtask is a target drawing image.

[0052] In some embodiments, at least two target drawing models corresponding to each drawing subtask are used to perform batch drawing of images based on the first drawing prompt word corresponding to each drawing subtask, and batch drawing results corresponding to the batch drawing tasks are obtained, including:

[0053] At least two target drawing models corresponding to each drawing subtask are used, and batch drawing of images is performed based on the first drawing prompt word corresponding to each drawing subtask and the task drawing parameters, so as to obtain multiple model drawing images corresponding to each drawing subtask. The task drawing parameters corresponding to the drawing subtask include: image size; image fusion is performed on the multiple model drawing images corresponding to each drawing subtask, so as to obtain batch drawing results corresponding to the batch drawing tasks.

[0054] Among them, multiple model drawing images corresponding to the drawing subtask have fusion weights, and the fusion weight of each model drawing image can be determined based on the model level of the target drawing model used in the drawing process. The model level of the target drawing model can be customized or determined according to the model category.

[0055] Performing image fusion on multiple model drawing images corresponding to each drawing subtask to obtain batch drawing results corresponding to the batch drawing task may include: for the multiple model drawing images corresponding to each drawing subtask, performing data fusion on the image data of the multiple model drawing images based on the fusion weights of the multiple model drawing images respectively, to obtain the batch drawing results corresponding to the batch drawing task.

[0056] Therefore, for each drawing subtask, multiple model drawing images are fused in a weighted fusion manner, so as to effectively obtain a drawing image that is more suitable for the target drawing model level, so that image drawing data of different model levels are reasonably distributed in the drawing image.

[0057] In this embodiment, a batch drawing task is created, wherein the batch drawing task includes: a plurality of drawing subtasks, each drawing subtask corresponds to a first drawing prompt word, and the drawing subtask is used to describe a model drawing task of drawing an image; a model database is obtained, wherein the model database includes: a plurality of AI drawing models; based on the first drawing prompt word corresponding to each drawing subtask, a corresponding target drawing model group is determined from the plurality of AI drawing models included in the model database, wherein the target drawing model group includes: at least two target drawing models, and the target drawing model is an AI drawing model included in the model database; at least two target drawing models corresponding to each drawing subtask are used, and batch drawing of images is performed based on the first drawing prompt word corresponding to each drawing subtask, and a batch drawing result corresponding to the batch drawing task is obtained; wherein the batch drawing result includes: a plurality of target drawing images, and each target drawing image corresponds to a drawing subtask. In this way, the corresponding images are intelligently drawn respectively through the plurality of AI drawing models built into the system, thereby effectively improving the efficiency of image generation.

[0058] In some embodiments, after batch drawing of images is performed based on the first drawing prompt word corresponding to each drawing subtask using at least two target drawing models corresponding to each drawing subtask and obtaining batch drawing results corresponding to the batch drawing tasks, the method further includes:

[0059] Displaying the target drawing image corresponding to each drawing subtask; and in response to a drawing parameter viewing request for the target drawing image corresponding to the drawing subtask, displaying the target drawing model group corresponding to the drawing subtask and the corresponding first drawing prompt word.

[0060] The target drawing images corresponding to the multiple drawing subtasks can be displayed in a display interface of the drawing system in a folder display manner, so as to effectively view the multiple target drawing images.

[0061] While displaying the target drawing image, the drawing parameters of the target drawing image during the drawing process can also be displayed, so that the viewer can have a deep understanding of the drawing process of the target drawing image.

[0062] In some embodiments, the method of this embodiment further includes:

[0063] In response to an image copying request for a target drawing image, a second drawing prompt word is obtained; a target drawing model corresponding to the target drawing image is used, and image intelligent drawing is performed based on the second drawing prompt word to obtain a corresponding image drawing result.

[0064] The image copying request is used to describe image generation using a target drawing model corresponding to a target drawing image.

[0065] The second drawing prompt words can be drawing reference words, for example, the second drawing prompt words are "ink painting, summer, pond, jade-colored lotus leaves, several people in a boat, sparkling water", "people under mission CG style lighting, high details, movie-level lighting, light leakage effects", "lion and lion cub, high details, grassland, movie-level lighting".

[0066] Therefore, the same model drawing can be quickly generated according to the target drawing model of the generated target drawing image, so as to quickly obtain a similar image.

[0067] It should be noted that after the target drawn image is generated, the target drawn image can also be generated in the same style with one click, so as to effectively obtain the same style image of the target drawn image.

[0068] In some embodiments, the method of this embodiment further includes:

[0069] In response to a parameter adjustment request for the task drawing parameters corresponding to the drawing subtask, the task drawing parameters corresponding to the drawing subtask are adjusted; and based on the adjusted task drawing parameters corresponding to the drawing subtask, the target drawing image corresponding to the drawing subtask is resized.

[0070] Among them, by fine-tuning the image size of the target drawing image after the target drawing image is generated, flexible configuration in the image generation process is ensured to meet the image adjustment needs of users.

[0071] In some embodiments, the method of this embodiment further includes:

[0072] During the process of batch image drawing, if a drawing task progress query request is received, the completed image data of the batch image drawing is obtained; the image drawing progress data is determined based on the completed image data and all image data of the target drawing image corresponding to all drawing subtasks; and the image drawing progress data is sent.

[0073] The completed image data includes: all image data of the completed target drawing image and completed partial data of the uncompleted target drawing image.

[0074] For example, the drawing target of batch image drawing corresponds to 5 target drawing images, namely image 1, image 2, image 3, image 4 and image 5, among which image 1, image 2 and image 3 have been completely drawn, image 4 has not been completely drawn, but 50% of the image data has been drawn, and image 5 has not been completely drawn, but 30% of the image data has been drawn. Then all the image data of the completed target drawing images are all the image data of image 1, all the image data of image 2 and all the image data of image 3; the completed partial data of the unfinished target drawing images are 50% of the image data in image 4 and 30% of the image data in image 5.

[0075] All image data of the target drawing image corresponding to all drawing subtasks can be estimated based on the first drawing prompt word corresponding to each drawing subtask. For example, there are three first drawing prompt words corresponding to the drawing subtask, namely "blue sky, city, street". The image data corresponding to "blue sky" can be estimated based on the blue sky data included in the existing image, the image data corresponding to "city" can be estimated based on the city data included in the existing image, and the image data corresponding to "street" can be estimated based on the street data included in the existing image. The sum of the estimated data corresponding to "blue sky, city, street" is the total image data of the target drawing image corresponding to the drawing subtask.

[0076] The image drawing progress data can be determined by the proportion of the completed image data and the total image data of the target drawing image corresponding to all drawing subtasks, so as to effectively measure the drawing progress of the image batch drawing, so that the user can check the image drawing progress in time.

[0077] The drawing system in this embodiment supports the integration of multiple AI drawing models, and users can freely select and combine these models in one application; the system can manage the calls of different models through a unified interface, ensuring the smoothness and efficiency of cross-platform content generation. The system uses React-table to implement table management. Users can set and maintain various parameters for generating images in the table, such as prompt, negative prompt, reference image, image control, etc. The table also supports real-time saving, field display and hiding, line number adjustment and other functions, which facilitates users to quickly configure generation tasks. Users can customize the size and quantity of image generation by selecting a combination of generation parameters and application models, and trigger batch tasks with one click. The system automatically processes batch generation tasks and provides task progress tracking and result management functions, so users can easily monitor and adjust the generation process. Flexible size selection options are provided, and corresponding preset sizes are provided according to different AI models, such as 1024×1024 (1:1 ratio), 1152×896 (4:3 ratio), 896×1152 (3:4 ratio), 1344×768 (16:9 ratio), 768×1344 (9:16 ratio), etc. These preset sizes cover commonly used image ratios, including squares, horizontal and vertical rectangles, and widescreen ratios to meet different creative needs. Users can choose the appropriate size according to the specific creative purpose, and the system will automatically adjust the generation parameters to adapt to the selected size. The system supports the function of fine-tuning the generation results again. Users can regenerate the modified image by adjusting parameters such as prompt and size. The system also provides a one-click generation of the same model function, so users can quickly generate multiple similar image versions to meet creative expansion needs.

[0078] By integrating multiple AI models, designers can flexibly generate images of different styles and themes on a single platform to meet the diverse needs of creative design. It supports batch generation of advertising images, greatly improving the efficiency of advertising creation, especially in advertising projects that require rapid generation of a large number of images. This method can be used to explore various styles of artworks and generate multiple versions in a short period of time for screening and optimization.

[0079] This embodiment significantly improves the efficiency of image generation and the convenience of operation by integrating multiple AI drawing models, combined with efficient parameter management and batch task triggering functions. Among them, multi-model integration: realizes the efficient integration of multiple AI drawing models and provides more flexible creation tools. Multi-dimensional table parameter management: The use of tables optimizes the management method of generation parameters, making complex parameter configuration and management more intuitive and efficient. Efficient triggering of batch tasks: Through the one-click batch task triggering function, the time for large-scale image generation is significantly shortened, and the creation efficiency is improved. Intelligent fine-tuning and same-style generation: supports intelligent fine-tuning of generation results and one-click same-style generation, ensuring that users can quickly generate high-quality images that meet expectations.

[0080] Figure 2 This is a schematic structural diagram of a batch drawing device based on a multi-intelligent drawing model provided in this embodiment. The batch drawing device based on a multi-intelligent drawing model may include: a creation module 210 , an acquisition module 220 , a determination module 230 and a drawing module 240 .

[0081] The creation module 210 is used to create a batch drawing task, wherein the batch drawing task includes: a plurality of drawing subtasks, each drawing subtask corresponds to a first drawing prompt word, and the drawing subtask is used to describe a model drawing task of drawing an image.

[0082] The acquisition module 220 is used to acquire a model database, which includes: a plurality of AI drawing models.

[0083] The determination module 230 is used to determine a corresponding target drawing model group from a plurality of AI drawing models included in the model database based on the first drawing prompt word corresponding to each drawing subtask, wherein the target drawing model group includes: at least two target drawing models, and the target drawing model is an AI drawing model included in the model database.

[0084] The drawing module 240 is configured to use at least two target drawing models corresponding to each drawing subtask to perform batch drawing of images based on the first drawing prompt word corresponding to each drawing subtask, and obtain batch drawing results corresponding to the batch drawing tasks.

[0085] The batch drawing result includes: a plurality of target drawing images, each target drawing image corresponds to a drawing subtask.

[0086] In this embodiment, optionally, each AI drawing model included in the model database corresponds to a drawing category identifier.

[0087] The determination module 230 is specifically configured to:

[0088] Match the first drawing prompt word corresponding to each drawing subtask with the drawing category identification word corresponding to each AI drawing model; determine the AI ​​drawing models corresponding to at least two drawing category identification words that have a matching relationship with the first drawing prompt word corresponding to the drawing subtask as the target drawing models corresponding to the drawing subtask, so as to obtain a target drawing model group corresponding to each drawing subtask.

[0089] In this embodiment, optionally, the drawing module 240 is specifically used to:

[0090] At least two target drawing models corresponding to each drawing subtask are used, and batch drawing of images is performed based on the first drawing prompt word corresponding to each drawing subtask and the task drawing parameters, so as to obtain multiple model drawing images corresponding to each drawing subtask. The task drawing parameters corresponding to the drawing subtask include: image size; image fusion is performed on the multiple model drawing images corresponding to each drawing subtask, so as to obtain batch drawing results corresponding to the batch drawing tasks.

[0091] In this embodiment, optionally, it also includes: a display module.

[0092] The display module is used to display the target drawing image corresponding to each drawing subtask; in response to a drawing parameter viewing request for the target drawing image corresponding to the drawing subtask, the target drawing model group corresponding to the drawing subtask and the corresponding first drawing prompt word are displayed.

[0093] In this embodiment, optionally, the acquisition module 220 is further used to acquire a second drawing prompt word in response to an image cloning request for a target drawing image, where the image cloning request is used to describe image generation using a target drawing model corresponding to the target drawing image.

[0094] The drawing module 240 is further configured to use a target drawing model corresponding to the target drawing image to perform intelligent image drawing based on the second drawing prompt word to obtain a corresponding image drawing result.

[0095] In this embodiment, optionally, it also includes: an adjustment module.

[0096] The adjustment module is used to adjust the task drawing parameters corresponding to the drawing subtask in response to a parameter adjustment request of the task drawing parameters corresponding to the drawing subtask; and adjust the size of the target drawing image corresponding to the drawing subtask based on the adjusted task drawing parameters corresponding to the drawing subtask.

[0097] In this embodiment, optionally, it also includes: a sending module.

[0098] The acquisition module 220 is also used to obtain the completed image data of the batch drawing of images if a drawing task progress query request is received during the process of batch drawing of images. The completed image data includes: all image data of the completed target drawing images and the completed partial data of the uncompleted target drawing images.

[0099] The determination module 230 is further configured to determine the image drawing progress data based on the completed image data and all image data of the target drawing images corresponding to all drawing subtasks.

[0100] The sending module is used to send image drawing progress data.

[0101] The batch drawing device based on the multi-intelligent drawing model provided by the present disclosure can execute the above method embodiments. Its specific implementation principles and technical effects can be found in the above method embodiments, and the present disclosure will not repeat them here.

[0102] The present application also provides a computer device. Figure 3 , Figure 3 This is a basic structural block diagram of the computer device in this embodiment.

[0103] The computer device includes a memory 310 and a processor 320 that are connected to each other through a system bus. It should be noted that the figure only shows a computer device with a memory 310 and a processor 320, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (Application Specific Integrated Circuit, ASIC), programmable gate arrays (Field-Programmable Gate Array, FPGA), digital processors (Digital Signal Processor, DSP), embedded devices, etc.

[0104] Computer devices can be computing devices such as desktop computers, notebooks, PDAs, and cloud servers. Computer devices can interact with users through keyboards, mice, remote controls, touch pads, or voice control devices.

[0105] The memory 310 includes at least one type of readable storage medium, and the readable storage medium includes a non-volatile memory or a volatile memory, for example, a flash memory, a hard disk, a multimedia card, a card-type memory (for example, an SD or DX memory, etc.), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, an optical disk, etc., and the RAM may include a static RAM or a dynamic RAM. In some embodiments, the memory 310 may be an internal storage unit of a computer device, for example, a hard disk or a memory of the computer device. In other embodiments, the memory 310 may also be an external storage device of the computer device, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, or a flash card (FlashCard) equipped on the computer device. Of course, the memory 310 may also include both the internal storage unit of the computer device and its external storage device. In this embodiment, the memory 310 is generally used to store the operating system and various application software installed on the computer device, such as the program code of the above method. In addition, the memory 310 may also be used to temporarily store various data that have been output or are to be output.

[0106] The processor 320 is generally used to perform the overall operation of the computer device. In this embodiment, the memory 310 is used to store program codes or instructions, the program code includes computer operation instructions, and the processor 320 is used to execute the program codes or instructions stored in the memory 310 or process data, such as running the program code of the above method.

[0107] In this article, the bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus system can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0108] Another embodiment of the present application also provides a computer-readable medium, which may be a computer-readable signal medium or a computer-readable medium. A processor in a computer reads a computer-readable program code stored in the computer-readable medium, so that the processor can execute the functional actions specified in each step or a combination of steps in the above method; and generate a device for implementing the functional actions specified in each block or a combination of blocks in the block diagram.

[0109] Computer-readable media include but are not limited to electronic, magnetic, optical, electromagnetic, infrared memory or semiconductor systems, devices or apparatuses, or any appropriate combination of the foregoing, the memory is used to store program codes or instructions, the program codes include computer operating instructions, and the processor is used to execute the program codes or instructions of the above methods stored in the memory.

[0110] For the definitions of memory and processor, please refer to the description of the aforementioned computer device embodiment and will not be repeated here.

[0111] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of modules or units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0112] Each functional unit or module in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0113] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) or a processor (processor) to perform all or part of the steps of each embodiment method of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), disk or optical disk and other media that can store program code.

[0114] In the claims, any reference symbols placed between brackets shall not be construed as limiting the claims. The word "comprising" described in the present application does not exclude the presence of elements or steps not listed in the claims. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present application can be implemented with the aid of hardware comprising several different elements and with the aid of a suitably programmed computer. In a unit claim that lists a number of devices, several units of these devices may be embodied by the same hardware item. The use of first, second, and third, etc. does not indicate any order, and these words may be interpreted as names. The steps in the above embodiments, unless otherwise specified, should not be understood as limitations on the order of execution.

[0115] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A batch drawing method based on a multi-intelligent drawing model, characterized in that: include: Creating a batch drawing task, wherein the batch drawing task includes: a plurality of drawing subtasks, each of the drawing subtasks corresponds to a first drawing prompt word, and the drawing subtask is used to describe a model drawing task of drawing an image; Acquire a model database, wherein the model database includes: a plurality of AI drawing models; Based on the first drawing prompt word corresponding to each of the drawing subtasks, determining a corresponding target drawing model group from a plurality of AI drawing models included in the model database, wherein the target drawing model group includes: at least two target drawing models, and the target drawing model is an AI drawing model included in the model database; Using at least two target drawing models corresponding to each drawing subtask, and performing batch drawing of images based on the first drawing prompt word corresponding to each drawing subtask, to obtain batch drawing results corresponding to the batch drawing tasks; The batch drawing results include: a plurality of target drawing images, each of which corresponds to one of the drawing subtasks.

2. The method according to claim 1, characterized in that Each of the AI ​​drawing models included in the model database corresponds to a drawing category identifier; The determining, based on the first drawing prompt word corresponding to each of the drawing subtasks, a corresponding target drawing model group from a plurality of AI drawing models included in the model database comprises: Matching the first drawing prompt word corresponding to each of the drawing subtasks with the drawing category identification word corresponding to each of the AI ​​drawing models; Determine the AI ​​drawing models corresponding to at least two drawing category identification words having a matching relationship with the first drawing prompt word corresponding to the drawing subtask as the target drawing model corresponding to the drawing subtask, so as to obtain a target drawing model group corresponding to each of the drawing subtasks.

3. The method according to claim 1, characterized in that: The step of using at least two target drawing models corresponding to each drawing subtask and performing batch drawing of images based on the first drawing prompt word corresponding to each drawing subtask to obtain batch drawing results corresponding to the batch drawing tasks includes: Using at least two target drawing models corresponding to each of the drawing subtasks, batch drawing of images is performed based on the first drawing prompt word corresponding to each of the drawing subtasks and the task drawing parameters, to obtain a plurality of model drawing images corresponding to each of the drawing subtasks, wherein the task drawing parameters corresponding to the drawing subtasks include: image size; Image fusion is performed on a plurality of model drawing images corresponding to each of the drawing subtasks to obtain a batch drawing result corresponding to the batch drawing task.

4. The method according to claim 1, characterized in that: After using at least two of the target drawing models corresponding to each of the drawing subtasks to perform batch drawing of images based on the first drawing prompt word corresponding to each of the drawing subtasks, and obtaining batch drawing results corresponding to the batch drawing tasks, the method further includes: Display the target drawing image corresponding to each of the drawing subtasks; In response to a drawing parameter viewing request for a target drawing image corresponding to the drawing subtask, a target drawing model group corresponding to the drawing subtask and a corresponding first drawing prompt word are displayed.

5. The method according to claim 1, characterized in that Also includes: In response to an image copying request for the target drawing image, obtaining a second drawing prompt word, wherein the image copying request is used to describe image generation using a target drawing model corresponding to the target drawing image; The target drawing model corresponding to the target drawing image is used to perform image intelligent drawing based on the second drawing prompt word to obtain a corresponding image drawing result.

6. The method according to claim 3, characterized in that Also includes: In response to a parameter adjustment request for the task drawing parameter corresponding to the drawing subtask, adjusting the parameter of the task drawing parameter corresponding to the drawing subtask; Based on the adjusted task drawing parameters corresponding to the drawing subtask, the target drawing image corresponding to the drawing subtask is resized.

7. The method according to claim 1, characterized in that Also includes: In the process of batch drawing of images, if a drawing task progress query request is received, the completed image data of the batch drawing of images is obtained, and the completed image data includes: all image data of the target drawing images that have been drawn and the completed partial data of the target drawing images that have not been drawn; Determining image drawing progress data based on the completed image data and all image data of the target drawing images corresponding to all the drawing subtasks; The image drawing progress data is sent.

8. A batch drawing device based on a multi-intelligent drawing model, characterized in that: include: A creation module, used for creating a batch drawing task, wherein the batch drawing task includes: a plurality of drawing subtasks, each of which corresponds to a first drawing prompt word, and the drawing subtask is used for describing a model drawing task of drawing an image; An acquisition module, used to acquire a model database, wherein the model database includes: a plurality of AI drawing models; a determination module, configured to determine a corresponding target drawing model group from a plurality of AI drawing models included in the model database based on the first drawing prompt word corresponding to each of the drawing subtasks, wherein the target drawing model group includes: at least two target drawing models, and the target drawing model is an AI drawing model included in the model database; A drawing module, configured to use at least two target drawing models corresponding to each drawing subtask, perform batch drawing of images based on the first drawing prompt word corresponding to each drawing subtask, and obtain batch drawing results corresponding to the batch drawing tasks; The batch drawing results include: a plurality of target drawing images, each of which corresponds to one of the drawing subtasks.

9. A computer device, characterized in that: The invention comprises a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, a batch drawing method based on a multi-intelligent drawing model as claimed in any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the batch drawing method based on the multi-intelligent drawing model as claimed in any one of claims 1 to 7 is implemented.

Images