Automatic brand plane originality generation method and system based on AIGC

Abstract

The invention discloses an AIGC-based brand plane originality automatic generation method and system, and the method comprises the steps: S1, inputting brand demand information to an AI model, and outputting a plurality of originality content directions; s2, generating a preliminary design sketch for each creative content direction through an AI model; s3, after the creative content direction and the corresponding preliminary design sketch are confirmed, batch image generation and material expansion are carried out through an AI model; s4, automatically scoring the images generated in batches and the expanded materials, and screening out high-quality creative images; and S5, after confirming the high-quality creative image, finely adjusting and optimizing the selected creative image, and finally generating a plane creative design drawing.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to an AIGC-based brand graphic creative automatic generation method and system. Background Art

[0002] The traditional brand creative generation process does often rely on the professional skills and artistic intuition of professional creative designers, from the initial conception to the final design realization. Designers usually conduct in-depth market research to understand the preferences and behavior patterns of the target audience, while also grasping the brand's positioning and core values. Based on this information, preliminary creative sketches are sketched on paper or on a computer, and then design elements such as colors, fonts, graphics, etc. are gradually refined until a visually attractive brand image that conveys the right information is formed.

[0003] However, this process not only requires designers to have a high level of artistic accomplishment and creative thinking, but also means a lot of time and energy investment. The communication between designers and clients often requires multiple rounds of feedback and adjustments, and each modification may bring additional time consumption.

[0004] In view of this, the present invention is proposed. Summary of the invention

[0005] The purpose of the present invention is to overcome the above-mentioned technical deficiencies and provide a method and system for automatically generating brand graphic creativity based on AIGC, so as to solve the technical problems in the related art that the brand creativity generation process relies on manual labor, resulting in high cost and long time consumption.

[0006] In order to achieve the above technical objectives, the present invention adopts the following technical solutions:

[0007] According to one aspect of the present invention, a method for automatically generating brand graphic creativity based on AIGC is provided, comprising:

[0008] Step S1, input brand demand information into the AI ​​model and output multiple creative content directions;

[0009] Step S2, generating a preliminary design sketch for each creative content direction through the AI ​​model;

[0010] Step S3: After confirming the creative content direction and the corresponding preliminary design sketch, batch image generation and material expansion are performed through the AI ​​model;

[0011] Step S4, automatically scoring the batch-generated images and expanded materials to select high-quality creative images;

[0012] Step S5, after confirming the high-quality creative image, fine-tune and optimize the selected creative image to finally generate a graphic creative design drawing.

[0013] Furthermore, the creative content direction includes creative themes, visual elements, color tones, text elements, and overall impression.

[0014] Furthermore, in step S2, the preliminary design sketch is generated by a Stable Diffusion model; the Stable Diffusion model is based on a diffusion model and includes:

[0015] Forward diffusion: gradually add noise to the image, each step adds noise based on the previous step, and the way to generate time steps is:

[0016]

[0017] Among them, x t is the output, is the mean, β i is the variance.

[0018] Backward diffusion: Starting from a random noise, the original image is gradually restored through continuous denoising. The time step is generated as follows:

[0019]

[0020] Among them, ε~N(0,1), θ represents the parameters of the network model, and α is a hyperparameter.

[0021] Furthermore, the step S3 further includes: injecting the parameters of the LoRA model into the Stable Diffusion model, thereby changing the generation style of the model, and the mathematical formula thereof is expressed as follows:

[0022] W=W0+BA

[0023] Where W0 is the parameter of the initial SD model, BA is the low-rank matrix, that is, the parameter of the LoRA model, and W represents the final SD model parameter after being affected by the LoRA model.

[0024] Furthermore, in step S4, the automatic scoring mechanism is based on multiple evaluation indicators, including visual beauty, creative uniqueness, and brand fit.

[0025] Furthermore, in step S5, the fine adjustment and optimization specifically include color correction, detail modification, and layout adjustment.

[0026] According to another aspect of the present invention, there is provided an AIGC brand graphic creative automatic generation system, comprising:

[0027] Demand understanding unit, used to input brand demand information into the AI ​​model and output multiple creative content directions;

[0028] Sketch design unit, which is used to generate preliminary design sketches for each creative content direction through the AI ​​model;

[0029] Batch generation unit, which is used to generate batch images and expand materials through AI models after confirming the creative content direction and the corresponding preliminary design sketch;

[0030] The scoring and screening unit is used to automatically score batch-generated images and expanded materials to screen out high-quality creative images;

[0031] The adjustment and optimization unit is used to confirm the high-quality creative images, and then fine-tune and optimize the selected creative images to finally generate a graphic creative design drawing.

[0032] According to another aspect of the present invention, there is also provided an electronic device, comprising: a processor and a memory;

[0033] The memory stores a computer-readable program executable by the processor;

[0034] When the processor executes the computer-readable program, the steps in the above method are implemented.

[0035] According to another aspect of the present invention, a computer-readable storage medium is provided, which stores one or more programs. The one or more programs can be executed by one or more processors to implement the steps in the above method.

[0036] The present invention provides a method and system for automatically generating brand graphic ideas based on AIGC, which can automatically generate creative directions and graphic designs, and flexibly modify and adjust them according to customer needs. Under the premise of ensuring the quality of design, this method significantly shortens the time for creative generation from the previous week level to the hour level, greatly improving the efficiency of brand creative production. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 A flowchart of a method for automatically generating brand graphic creativity based on AIGC is provided for an embodiment of the present invention;

[0038] Figure 2 A schematic diagram of generating a sketch in a method for automatically generating brand graphic creativity based on AIGC is provided for an embodiment of the present invention;

[0039] Figure 3A schematic diagram of batch generation of images in a method for automatically generating brand graphic creativity based on AIGC is provided for an embodiment of the present invention;

[0040] Figure 4 Provided is a graphic design drawing finally generated in a method for automatically generating brand graphic creativity based on AIGC in an embodiment of the present invention;

[0041] Figure 5 A schematic diagram of the structure of a brand graphic creative automatic generation system based on AIGC is provided for an embodiment of the present invention;

[0042] Figure 6 The present invention is a block diagram of a terminal that can implement an AIGC-based brand graphic creative automatic generation method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0043] 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 drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0044] Embodiment 1

[0045] Combination Figure 1-4 The embodiment of the present invention provides a method for automatically generating brand graphic creativity based on AIGC, comprising:

[0046] Step S1, input brand demand information into the AI ​​model and output multiple creative content directions;

[0047] In step S1, at this stage, the system first needs to fully understand the customer's product needs and market positioning. Through detailed communication with the customer, key brand information, target audience, market trends and specific design requirements are obtained. By inputting detailed demand information into the AI ​​big model, multiple creative content directions can be output. Each creative direction includes 5 aspects: creative theme, visual elements, color tone, text elements, and overall impression, providing a basis for subsequent design. For example, the creative content direction can be generated as follows:

[0048] Creative Theme

[0049] “Golden Growth Moments” - This theme not only meets the requirements of the golden main color, but also conveys the importance of milk powder to the growth of infants, symbolizing health, wealth and high-quality life.

[0050] Visual Elements

[0051] Baby image: Show a lively and healthy baby. You can use gold, red and white elements on the baby's clothes or toys to echo the overall color theme.

[0052] Furniture scene: To design a modern and tasteful home environment, you can choose white furniture with some gold or red decorations to create an elegant and warm atmosphere.

[0053] Milk powder image: The product image should be placed in a prominent position, and a gold and white packaging design can be used to highlight the high-end quality of the product.

[0054] Color tone

[0055] Gold: symbolizes quality and value, used to emphasize the high quality of products

[0056] Red: conveys enthusiasm and vitality, symbolizing the healthy growth of the baby.

[0057] White: represents purity and safety, which is consistent with the core value of infant products.

[0058] Text elements

[0059] Using elegant and modern fonts, the text content can highlight the main features of the product and the theme of the child's growth, such as "Protecting your baby's golden growth moments."

[0060] Overall impression

[0061] The entire advertisement should convey a high-end, healthy and energetic feeling. By cleverly combining the colors required by the client and a warm and family atmosphere, this advertisement will be able to effectively attract the attention of target consumers while conveying the brand's commitment to high quality.

[0062] By taking all these elements into consideration, this advertisement will not only meet the client's specific requirements, but also stand out in a highly competitive market and create a unique brand image.

[0063] Step S2, generating a preliminary design sketch for each creative content direction through the AI ​​model;

[0064] After the initial creative generation, the system generates demo sketches of various creative directions. These sketches are produced by the Stable Diffusion (SD) model, and are preliminary design solutions quickly generated according to different creative directions. Customers can intuitively understand the visual effects of different creative directions through these sketches. At this stage, through further communication with the customer, the final creative direction is confirmed to ensure that the design solution is highly consistent with the customer's brand positioning and market demand.

[0065] In step S2, the preliminary design sketch is generated by a Stable Diffusion model; the Stable Diffusion model is based on a diffusion model and includes:

[0066] Forward diffusion: gradually add noise to the image, each step adding noise based on the previous step, and the way to generate the time step x_t is:

[0067]

[0068] Among them, x t is the output, is the mean, β i is the variance.

[0069] Backward diffusion: Starting from a random noise, the original image is gradually restored through continuous denoising, generating time steps x _ The t-1 method is:

[0070]

[0071] Among them, ε~N(0,1), θ represents the parameters of the network model, and α is a hyperparameter.

[0072] Step S3: After confirming the creative content direction and the corresponding preliminary design sketch, batch image generation and material expansion are performed through the AI ​​model;

[0073] Once the customer confirms the sketch direction, the system enters the batch image generation and material expansion stage. In this process, the pre-trained LoRA (Low-Rank Adaptation of Large Language Models) model is integrated. LoRA can train a style / character with a small amount of data without modifying the Stable Diffusion model to meet customized needs. LoRA trains low rank matrices and injects the parameters of the LoRA model into the Stable Diffusion model when used, thereby changing the generation style of the model. Its mathematical formula is expressed as follows:

[0074] W=W0+BA

[0075] Where W0 is the parameter of the initial SD model (Weights), BA is the low-rank matrix, that is, the parameter of the LoRA model, and W represents the final SD model parameter after being affected by the LoRA model. The whole process is a simple linear relationship, which can be considered as a new model after the original SD model is superimposed on the LoRA model.

[0076] Step S4, automatically scoring the batch-generated images and expanded materials to screen out high-quality creative images.

[0077] In step S4, after a large number of design images are generated, the system will automatically score these images. The scoring mechanism is based on a variety of evaluation indicators, such as visual beauty, creative uniqueness, brand fit, etc. Through AI scoring, the system screens out high-quality creative images. For example, images with scores above a certain threshold can be output preferentially. These images are then submitted to the customer for confirmation. The customer can further evaluate and provide feedback on the screened images to ensure that the creative images finally selected fully meet their expectations.

[0078] Step S5, after confirming the high-quality creative image, fine-tune and optimize the selected creative image to finally generate a graphic creative design drawing.

[0079] After the customer confirms the high-quality creative image, the system enters the final refinement stage. The system will fine-tune and optimize the selected creative image, including color correction, detail modification, layout adjustment, etc. Finally, a high-quality graphic creative design is generated. This stage ensures that all details meet professional design standards. The final version of the graphic creative image generated is not only visually impactful, but also can effectively convey brand information and meet all customer needs.

[0080] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0081] Embodiment 2

[0082] According to an embodiment of the present invention, there is provided a method according to another aspect of the present invention, Figure 5 , provides an AIGC brand graphic creative automatic generation system, including

[0083] Demand understanding unit, used to input brand demand information into the AI ​​model and output multiple creative content directions;

[0084] Sketch design unit, which is used to generate preliminary design sketches for each creative content direction through the AI ​​model;

[0085] Batch generation unit, which is used to generate batch images and expand materials through AI models after confirming the creative content direction and the corresponding preliminary design sketch;

[0086] The scoring and screening unit is used to automatically score batch-generated images and expanded materials to screen out high-quality creative images;

[0087] The adjustment and optimization unit is used to confirm the high-quality creative images, and then fine-tune and optimize the selected creative images to finally generate a graphic creative design drawing.

[0088] Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments, and this embodiment will not be described in detail here.

[0089] It should be noted that the examples and application scenarios implemented by the above modules and corresponding steps are the same, but are not limited to the contents disclosed in the above embodiments. It should be noted that the above modules, as part of the device, can be run in a corresponding hardware environment, can be implemented by software, and can also be implemented by hardware, wherein the hardware environment includes a network environment.

[0090] Figure 6 is a structural block diagram of a terminal according to an embodiment of the present application, such as Figure 6 As shown, the terminal may include: one or more (only one is shown) processors 101, a memory 103, and a transmission device 105, such as Figure 6 As shown, the terminal may also include an input and output device 107 .

[0091] Among them, the memory 103 can be used to store software programs and modules, such as program instructions / modules corresponding to the methods and devices in the embodiments of the present application. The processor 101 executes various functional applications and data processing by running the software programs and modules stored in the memory 103, that is, implementing the above-mentioned method. The memory 103 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 103 may further include a memory remotely arranged relative to the processor 101, and these remote memories may be connected to the terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0092] The transmission device 105 is used to receive or send data via a network, and can also be used for data transmission between a processor and a memory. Specific examples of the above-mentioned network may include a wired network and a wireless network. In one example, the transmission device 105 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices and routers via a network cable so as to communicate with the Internet or a local area network. In one example, the transmission device 105 is a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0093] Specifically, the memory 103 is used to store application programs.

[0094] The processor 101 may call the application program stored in the memory 103 through the transmission device 105 to execute the steps in the above method.

[0095] Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments, and this embodiment will not be described in detail here.

[0096] Those skilled in the art will appreciate that the above terminal structures are for illustration only, and the terminals may be smart phones (such as Android phones, iOS phones, etc.), tablet computers, PDAs, mobile Internet devices (MID), PADs, and other terminal devices. Figure 6 It does not limit the structure of the above electronic device. For example, the terminal may also include Figure 6 More or fewer components (such as network interfaces, display devices, etc.) shown in, or having Figure 6 Different configurations are shown.

[0097] A person of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing the hardware related to the terminal device through a program, and the program can be stored in a computer-readable storage medium, and the storage medium may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0098] The embodiment of the present application further provides a storage medium. Optionally, in this embodiment, the storage medium can be used to execute the program code of the above method.

[0099] Optionally, in this embodiment, the storage medium may be located on at least one network device among a plurality of network devices in the network shown in the above embodiment.

[0100] Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments, and this embodiment will not be described in detail here.

[0101] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for automatically generating brand graphic creativity based on AIGC, characterized in that: include: Step S1, input brand demand information into the AI ​​model and output multiple creative content directions; Step S2, generating a preliminary design sketch for each creative content direction through the AI ​​model; Step S3: After confirming the creative content direction and the corresponding preliminary design sketch, batch image generation and material expansion are performed through the AI ​​model; Step S4, automatically scoring the batch-generated images and expanded materials to select high-quality creative images; Step S5, after confirming the high-quality creative image, fine-tune and optimize the selected creative image to finally generate a graphic creative design drawing.

2. The method for automatically generating brand graphic creativity based on AIGC according to claim 1, characterized in that: The creative content direction includes creative theme, visual elements, color tone, text elements, and overall impression.

3. The method for automatically generating brand graphic creativity based on AIGC according to claim 1, characterized in that: In step S2, the preliminary design sketch is generated by a Stable Diffusion model; the Stable Diffusion model is based on a diffusion model and includes: Forward diffusion: gradually add noise to the image, each step adds noise based on the previous step, and the way to generate time steps is: Among them, x t is the output, is the mean, β i is the variance. Backward diffusion: Starting from a random noise, the original image is gradually restored through continuous denoising. The time step is generated as follows: Among them, ε~N(0,1), θ represents the parameters of the network model, and α is a hyperparameter.

4. The method for automatically generating brand graphic creativity based on AIGC according to claim 3 is characterized in that: The step S3 also includes: injecting the parameters of the LoRA model into the Stable Diffusion model, thereby changing the generation style of the model, and its mathematical formula is expressed as follows: W=W0+BA Where W0 is the parameter of the initial SD model, BA is the low-rank matrix, that is, the parameter of the LoRA model, and W represents the final SD model parameter after being affected by the LoRA model.

5. The AIGC brand graphic creative automatic generation method according to claim 1 is characterized in that: In step S4, the automatic scoring mechanism is based on multiple evaluation indicators, including visual beauty, creative uniqueness, and brand fit.

6. The AIGC brand graphic creative automatic generation method according to claim 1 is characterized in that: In step S5, the fine adjustment and optimization specifically include color correction, detail modification, and layout adjustment.

7. An AIGC brand graphic creative automatic generation system, characterized by: include Demand understanding unit, used to input brand demand information into the AI ​​model and output multiple creative content directions; Sketch design unit, which is used to generate preliminary design sketches for each creative content direction through the AI ​​model; Batch generation unit, which is used to generate batch images and expand materials through AI models after confirming the creative content direction and the corresponding preliminary design sketch; The scoring and screening unit is used to automatically score batch-generated images and expanded materials to screen out high-quality creative images; The adjustment and optimization unit is used to confirm the high-quality creative images, and then fine-tune and optimize the selected creative images to finally generate a graphic creative design drawing.

8. An electronic device, characterized in that: include: Processor and memory; The memory stores a computer-readable program executable by the processor; When the processor executes the computer-readable program, the steps in the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the steps in the method according to any one of claims 1 to 6.

Images