Creative material correction system based on AIGC

Abstract

The invention relates to the technical field of image generation, in particular to an AIGC-based creative material correction system, which comprises a model disassembling device for determining a corresponding active model core and a plurality of follow-up model cores according to the structure of an original image; the path builder is used for determining a corresponding test path and a stable jitter interval according to the running path of the active model; the defect diagnostor is used for collecting radial jitter corresponding to the radial vibration and torsional jitter corresponding to the torsional vibration; the material corrector is used for repairing the corresponding fault frame; according to the method, the contact condition of each follow-up model and the active model is determined according to the vibration path and the vibration amplitude, so that a frame with relatively low picture quality is determined, the monitoring complexity is effectively reduced, the interference to other images is reduced, and the positioning accuracy of a material correction system is effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of image generation, and in particular to a creative material correction system based on AIGC. Background Art

[0002] AIGC (artificial intelligence generated content) is widely used in the fields of text, graphics, music, and drama, and can generate high-quality works. It is currently in a stage of rapid development and application. Through deep learning models, AIGC technology can automatically create text, images, videos and other content, greatly improving content production efficiency and creating high-quality creative content.

[0003] Its application in the advertising field is becoming increasingly extensive. It not only improves the efficiency of advertising creativity, but also optimizes advertising effects through data analysis and machine learning.

[0004] However, during the generation process, inevitable image conflicts occurred between the colliding elements, and this type of problem has become one of the main problems that AIGC needs to solve when generating content.

[0005] The Chinese patent authorization announcement number CN117115843B provides a system for producing exhibition engineering content based on AIGC technology, including: a creative input unit, which is a platform for inputting creative design information; a creative production unit, which identifies the creative design information, processes and generates initial material pictures; an effect evaluation unit, which corrects the initial material pictures and generates corrected materials; a creative adjustment unit, which makes detailed adjustments to the corrected materials; a server, which is connected to the creative input unit, the creative production unit, and the creative adjustment unit, and the server transmits data information to the connected units and outputs the final materials. The present invention also provides a method for producing exhibition engineering content, which is convenient for designers to master this system. The invention uses AI to learn the content of the material library and create matching creative materials, which can improve the production efficiency of exhibition design materials and greatly shorten the work cycle of exhibition projects.

[0006] The Chinese patent authorization announcement number CN110298229B discloses a video image processing method and device, wherein the method includes: reviewing the first video file and the second video file based on the video clarity to obtain the review result, the first video file is used for editing and processing, and the second video file is used for material sampling; performing face detection on the first video file to obtain the first face image, performing face detection on the second video file to obtain the second face image; feature extraction step, performing face feature extraction on the first face image to obtain the first face image feature, performing face feature extraction on the second face image to obtain the second face image feature; performing feature mapping on the first face feature and the second face feature; replacing the first face feature based on the second face feature to obtain the feature-replaced first face image. The invention improves the image clarity of the synthesized video.

[0007] For dynamic creative materials, there may be collisions between dynamic elements or mutual influences between paths in the materials. During the processing of generative AI, it is difficult to generate or correct the materials correctly. Summary of the invention

[0008] To this end, the present invention provides a creative material correction system based on AIGC to overcome the problem in the prior art that collisions between certain elements or mutual influences between paths may occur in video materials, and it is difficult to generate or correct materials correctly during the processing of generative AI, thereby resulting in a decrease in the quality of the generated materials.

[0009] To achieve the above-mentioned purpose, the present invention provides a creative material correction system based on AIGC, which collects original image materials of AIGC and corrects the materials according to input corresponding text instructions, including: A model disassembler determines the corresponding active model core and several follower model cores according to the structure of the original image, and determines several running paths of the active model and / or the follower model according to the text instructions; A path builder determines the corresponding test path and stable jitter interval according to the running path of the active model, and According to the coordinate system of each follower model, the directions of radial vibration and torsional vibration corresponding to the collision between the follower model and the active model in the test path are determined; A defect diagnostic device, which is used to collect radial jitter corresponding to radial vibration and torsional jitter corresponding to torsional vibration, and determine the mutation phase and mutation path according to the test path, and, determining a potential fault frame of an active model or a follower model in response to the sudden phase change, or, determining a potential fault displacement of an active model in response to the mutation path; A material corrector, which determines an actual fault frame according to the potential fault frame and / or the potential fault displacement, determines a corresponding smooth running path according to a previous frame and / or a subsequent frame of the actual fault frame, and repairs the corresponding fault frame; The stable jitter interval is related to the accuracy of the original image, and is mapped to the jitter bandwidth of the radial jitter or the torsional jitter.

[0010] Further, the path builder determines the number of collision events of the original image according to the number of frames of the active model and each follower model, and determines the collision path of each follower model according to the number of collision events; The maximum amplitude of the radial vibration or torsional vibration of each follow-up model is recorded according to the collision path as the radial jitter or torsional jitter of a single collision event; Wherein, the amplitude of the radial jitter is the maximum vibration distance between the follower model core and the active model core; The amplitude of the torsional vibration is the maximum vibration distance of the follower model core during operation.

[0011] Furthermore, the model disassembler sets an active model core corresponding to the active model according to the geometric position of the active model, and determines a corresponding follower model core according to the position and angle corresponding to the follower model; In a single collision, the model disassembler sets the follower model coordinate system of each follower model based on the follower model core according to the contact position between the active model and each follower model.

[0012] Furthermore, the defect diagnostic device is provided with a stable jitter interval, and a number of jitters exceeding the stable jitter interval are set as sudden jitters; According to the position of each sudden jitter on the follower model, the projection of the sudden jitter on the corresponding surface where the line connecting the follower model core and the active model core is located is determined as the sudden phase of the sudden jitter.

[0013] Furthermore, for a single mutation path, the defect diagnostic device also determines the equivalent mutations of each servo model according to the mutation phase, and determines the corresponding path for the recurrence of each equivalent mutation, and records it as the mutation path of the mutation phase.

[0014] Furthermore, the defect diagnostic device compares the mutation path with the test path to form a corresponding mutation fit, determines an active model boundary of the active model and a follower model boundary of the follower model according to the mutation fit, and records the active model boundary and the follower model boundary as potential fault displacements.

[0015] Furthermore, the defect diagnostic device maps the mutation path onto the test path and forms a corresponding mutation mapping relationship, and based on the mutation mapping relationship, records several frames in which the follower model contacts the active model in the collision path where the mutation jitter occurs as potential fault frames.

[0016] Further, the material trimmer determines the corresponding potential fault frame of the active model as an actual fault frame in response to the potential fault frame overlapping with the potential fault displacement in a plurality of test paths, or, In response to the potential fault frame and the potential fault displacement not overlapping in any test path, determining that the follower model fails; A single test includes at least two consecutive test paths.

[0017] Further, if the mutation path does not overlap with the test path in any test path, the model disassembler determines that the collision path is abnormal and adjusts the structure of the original image.

[0018] Further, when determining the actual fault frame, the defect diagnostic device performs fault frame verification and performs tests on at least three test paths; Each test path marks the actual fault frame, and when running to each follower model, performs verification according to the interaction between each follower model and the active model.

[0019] Compared with the prior art, the beneficial effect of the present invention lies in that, by detecting the vibration of the original image and each follower model, the contact status of each follower model with the active model is determined according to the vibration path and vibration amplitude, thereby determining a frame with lower picture quality, which effectively reduces the monitoring complexity and reduces interference to other images, thereby effectively improving the positioning accuracy of the material correction system.

[0020] Furthermore, by utilizing the phenomenon of image distortion that may be caused by model jitter, the number of image recognitions for material correction is effectively reduced while improving the targeting of the corresponding positions of the distorted images, thereby further improving the positioning accuracy of the material correction system.

[0021] Furthermore, by setting a reliable and stable jitter interval, the repair of unobservable images that affect the overall progress of the repair work is avoided. At the same time, the overfitting problem caused by the single factor material of the correction system is avoided. While effectively improving the efficiency of material correction, the display quality of the material correction is improved.

[0022] Furthermore, the material restoration effect is verified by reproducing the path of the material movement, and the material is optimized accordingly based on the verification result, which effectively improves the accuracy of the material restoration system for video material restoration while improving the display quality of the material. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 It is a connection diagram of the creative material correction system based on AIGC of the present invention; Figure 2 This is an operation flow chart of the creative material correction system based on AIGC of the present invention; Figure 3 A schematic diagram of model definition of an active model and a follower model according to an embodiment of the present invention; Figure 4 A schematic diagram of the collision between the active model and the follower model according to an embodiment of the present invention; Among them: 1, active model; 11, active model core; 12, active model moving direction; 13, active model radial direction; 14, active model torsional direction; 2, follow-up model; 21, follow-up model core; 22, follow-up model moving direction; 23, follow-up model radial direction; 24, follow-up model torsional direction; 3, model boundary; 31, abnormal model boundary. DETAILED DESCRIPTION

[0024] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0025] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0026] It should be noted that, in the description of the present invention, terms such as "up", "down", "left", "right", "inside" and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the drawings. This is merely for the convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it cannot be understood as a limitation on the present invention.

[0027] In addition, it should be noted that in the description of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0028] See also Figure 1 and Figure 2 As shown, it is a connection schematic diagram of the creative material correction system based on AIGC of the present invention, and an operation flow chart of the creative material correction system based on AIGC of the present invention. Before correcting the AIGC creative material, it collects the original image material of AIGC, and corrects the material according to the input corresponding text instruction, including: A model disassembler determines the corresponding active model core and several follower model cores according to the structure of the original image, and determines several running paths of the active model and / or the follower model according to the text instructions; A path builder determines the corresponding test path and stable jitter interval according to the running path of the active model, and According to the coordinate system of each follower model, the directions of radial vibration and torsional vibration corresponding to the collision between the follower model and the active model in the test path are determined; A defect diagnostic device for collecting radial jitter corresponding to radial vibration and torsional jitter corresponding to torsional vibration, and determining a sudden change phase and a sudden change path according to a test path, and, Determine the potential fault frame of the active model or the follower model in response to the sudden phase change, or, The potential fault displacement of the active model is determined in response to the mutation path; A material corrector, which determines the actual fault frame according to the potential fault frame and / or the potential fault displacement, determines the corresponding smooth running path according to the previous frame and / or the next frame of the actual fault frame, and repairs the corresponding fault frame; The stable jitter interval is related to the accuracy of the original image, and is mapped to the jitter bandwidth of the radial jitter or the torsional jitter.

[0029] In practice, jitter is an image blurring phenomenon caused by vibration in a corresponding direction or a rotational direction, specifically a "ghost image" consisting of several overlapping images at a certain position.

[0030] By detecting the vibration of the original image and each follower model, the contact status of each follower model with the active model is determined according to the vibration path and vibration amplitude, thereby determining a frame with lower image quality. This effectively reduces the monitoring complexity and reduces interference to other images, thereby effectively improving the positioning accuracy of the material correction system.

[0031] For example, in AR advertising production, the original image material may contain product models and real-world backgrounds. The model disassembler will identify the product model as the active model core and the background elements as the follower model core.

[0032] The path builder determines the test path and stable jitter intervals based on the movement path of the product model in the advertisement, and calculates the collision and vibration between the product model and the background elements.

[0033] The Defect Diagnoser monitors jitter in the fusion of product models and backgrounds to ensure that ads look natural and appealing. If abnormal jitter is detected, it determines the phase and path of the sudden change, identifying potential faulty frames or displacements.

[0034] The material corrector will determine the actual fault location based on the identified faulty frames and displacements, and repair or optimize the fusion of the product model and the background to ensure the visual effect of the advertisement.

[0035] Specifically, the path builder determines the number of collision events of the original image according to the number of frames of the active model and each follower model, and determines the collision path of each follower model according to the number of collision events; The maximum amplitude of the radial vibration or torsional vibration of each follow-up model is recorded according to the collision path as the radial jitter or torsional jitter of a single collision event; Among them, the amplitude of radial jitter is the maximum vibration distance between the core of the follower model and the core of the active model; The amplitude of torsional jitter is the maximum vibration distance that the core of the follower model deviates during operation.

[0036] By utilizing the phenomenon of image distortion that may be caused by model jitter, the number of image recognitions for material correction is effectively reduced while improving the targeting of the corresponding positions of the distorted images, thereby further improving the positioning accuracy of the material correction system.

[0037] Example 1 In an advertisement, there is a scene where the protagonist (active model) runs in the forest and avoids falling rocks (follower model). This scene has 300 frames, each representing a moment of action, 30 frames per second.

[0038] The path builder analyzes the running path of the main character and the falling path of the falling rock and determines that there are 20 potential collision events in 300 frames.

[0039] For each collision event, the path builder records the maximum radial maximum vibration distance between the falling rock (follower model) and the main body (active model). For example, at frame 150, the maximum amplitude of the distance between a falling rock and the main body is 5 pixels, which is considered to be the radial vibration amplitude of this collision event.

[0040] Example 2 In the simulation of a robot soccer game, a robot (active model) tries to dribble past the opposing defensive robot (follower model). The entire breakthrough process is simulated at 120 frames, 24 frames per second.

[0041] The path builder analyzes the path of the ball-carrying robot and the movements of the defending robot and determines that there are 15 potential collision events in 120 frames.

[0042] For each collision event, the path builder records the maximum radial maximum vibration distance between the defending robot and the ball-carrying robot. For example, in frame 75, the maximum radial maximum vibration distance of a collision is 3 cm, which is considered to be the radial vibration amplitude of this collision event.

[0043] Example 3 In an aerospace simulation, a satellite (active model) moves in space and needs to avoid collisions with other space junk (follower model). The simulation consists of 500 frames, at 16 frames per second.

[0044] The path builder analyzed the satellite's orbit and the trajectory of space junk and identified 30 potential collision events in 500 frames.

[0045] For each collision event, the path builder records the maximum radial maximum vibration distance between the space debris and the satellite. For example, at frame 250, the maximum amplitude of the distance between a piece of space debris and the satellite is 0.5 meters, which is considered to be the radial vibration amplitude of the collision event.

[0046] Specifically, the model disassembler sets the active model core corresponding to the active model according to the geometric position of the active model, and determines the corresponding follower model core according to the position and angle corresponding to the follower model; In a single collision, the model disassembler sets the follower model coordinate system of each follower model based on the contact position between the active model and each follower model and the follower model core.

[0047] Compared with the above-mentioned embodiment 1, the corresponding active model core is the center of mass of the main character, and the follower model core is the center of mass of each rockfall; For the above-mentioned embodiment 2, the corresponding active model core is the geometric center of the ball, and the follower model core is the center of mass of each robot; For the above-mentioned embodiment 3, the corresponding active model core is the center of the satellite, and the follower model core is the geometric center of each space debris; It can be understood that the core of the active model and the core of the follower model should be changed accordingly according to the subject in the AIGC-generated image, and the one with a higher frequency of appearance in the entire material should be selected as the active model, and the remaining models should be used as follower models.

[0048] See also Figure 3 As shown, it is a schematic diagram of model definition of the active model and the follower model of an embodiment of the present invention. In the figure, the active model 1 and the follower model 2 are both ellipsoids, and their centers of gravity are respectively the active model core 11 and the follower model core 21; The active model moving direction 12 of the active model 1 is mapped on the active model core 11 as the active model radial direction 13, and the rotation direction around the active model 1 is the active model torsion direction 14; The mapping of the follower model moving direction 22 of the follower model 2 on the follower model core 21 is the follower model radial direction 23, and the rotation direction around the follower model 2 is the follower model torsion direction 24; It is not difficult to understand that by specifying the above parameters, the movement modes of the active model 1 and the follower model 2 in a continuous process can be described, and the effects produced when they collide can also be better reflected.

[0049] Specifically, the defect diagnostic device is provided with a stable jitter interval, and a number of jitters exceeding the stable jitter interval are set as sudden jitters; According to the position of each sudden jitter on the follower model, the projection of the sudden jitter on the corresponding surface where the line connecting the follower model core and the active model core is located is determined as the sudden phase of the sudden jitter.

[0050] The Defect Diagnoser determines the sudden change phase of the creative based on its performance on different platforms. It is not difficult to understand that the sudden change phase is caused by the image processing capabilities and display performance of different platforms: For example, on mobile platforms, most mobile phone screens are 3.5-6.8 inches. At this time, when the ad is displayed, the image details that users can observe are relatively small, but more elements can be stacked; For example, on the PC (personal computer) platform, the conventional display size is 19-35 inches. At this time, when the advertisement is displayed, the user can observe more image details and the elements that can be stacked are moderate; It is not difficult to see that the number of mutation phases of the same material on the mobile platform is smaller, and the number of mutation phases on the PC platform is larger; In implementation, the stable jitter range associated with the abrupt phase change can be set according to the resolution, such as: For an advertisement with a size of 1m×0.6m, it contains a 0.25m×0.25m material. For a 720P resolution, the corresponding stable jitter interval can be 10cm; For 1080P resolution, the corresponding stable jitter interval can be 8cm; The clearer the display is, the abnormal movement of the material will be magnified. Therefore, the higher the resolution of the advertising material, the smaller the corresponding stable jitter range.

[0051] Specifically, for a single mutation path, the defect diagnostic device also determines the equivalent mutations of each follow-up model according to the mutation phase, and determines the corresponding path for the recurrence of each equivalent mutation, and records it as the mutation path of the mutation phase.

[0052] By setting a reliable and stable jitter interval, we can avoid repairing unobservable images and thus affecting the overall progress of the repair work. At the same time, we can avoid the overfitting problem caused by the single factor material of the correction system. While effectively improving the efficiency of material correction, we can also improve the display quality of the material correction.

[0053] Specifically, the defect diagnostic device compares the mutation path with the test path to form a corresponding mutation fit, determines the active model boundary of the active model and the follower model boundary of the follower model according to the mutation fit, and records the active model boundary and the follower model boundary as potential fault displacements.

[0054] Specifically, the defect diagnostic device maps the mutation path onto the test path and forms a corresponding mutation mapping relationship, and based on the mutation mapping relationship, records several frames where the follower model contacts the active model in the collision path where the mutation jitter occurs as potential fault frames.

[0055] In practice, the use of AI big models can optimize the delivery effect of advertising materials: In the dynamic analysis of ad creatives, the Defect Diagnoser sets a stable jitter range to identify normal and abnormal performance of creatives on different delivery platforms. Performance exceeding this range is marked as sudden jitter.

[0056] Specifically, the material trimmer responds to the overlap of the potential fault frame and the potential fault displacement in several test paths, and determines the corresponding potential fault frame of the active model as the actual fault frame, or, The response potential fault frame and the potential fault displacement do not overlap in any test path, and it is determined that the follower model fails; A single test includes at least two consecutive test paths.

[0057] In implementation, when an active model or a follower model fails, the boundary definition of the active model or the follower model is determined to be abnormal, and the corresponding boundary is regenerated. Figure 4 As shown, it is a schematic diagram of the collision between the active model and the follower model of an embodiment of the present invention. In the figure, the active model 1 and the follower model 2 collide in a certain frame. When the collision is generated, an abnormal model boundary 31 is generated. At this time, the abnormal model boundary 31 is corrected and smoothed to form a model boundary 3.

[0058] Specifically, if the mutation path does not overlap with the test path in any test path, the model disassembler determines that the collision path is abnormal and adjusts the structure of the original image.

[0059] Specifically, when determining the actual fault frame, the defect diagnostic device performs fault frame verification and performs tests on at least three test paths; Each test path marks the actual fault frame, and when running to each follower model, performs verification according to the interaction between each follower model and the active model.

[0060] The material restoration effect is verified by reproducing the path of the material movement, and the material is optimized accordingly based on the verification results. This effectively improves the accuracy of the material restoration system for video material restoration while improving the display quality of the material.

[0061] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

[0062] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A creative material correction system based on AIGC, which collects original image materials of AIGC and corrects the materials according to input corresponding text instructions, characterized in that: include: A model disassembler determines the corresponding active model core and several follower model cores according to the structure of the original image, and determines several running paths of the active model and / or the follower model according to the text instructions; A path builder determines the corresponding test path and stable jitter interval according to the running path of the active model, and According to the coordinate system of each follower model, the directions of radial vibration and torsional vibration corresponding to the collision between the follower model and the active model in the test path are determined; A defect diagnostic device, which is used to collect radial jitter corresponding to radial vibration and torsional jitter corresponding to torsional vibration, and determine the mutation phase and mutation path according to the test path, and, determining a potential fault frame of an active model or a follower model in response to the sudden phase change, or, determining a potential fault displacement of an active model in response to the mutation path; A material corrector, which determines an actual fault frame according to the potential fault frame and / or the potential fault displacement, determines a corresponding smooth running path according to a previous frame and / or a subsequent frame of the actual fault frame, and repairs the corresponding fault frame; The stable jitter interval is related to the accuracy of the original image, and is mapped to the jitter bandwidth of the radial jitter or the torsional jitter.

2. The creative material correction system based on AIGC according to claim 1, characterized in that: The path builder determines the number of collision events of the original image according to the number of frames of the active model and each follower model, and determines the collision path of each follower model according to the number of collision events; The maximum amplitude of the radial vibration or torsional vibration of each follow-up model is recorded according to the collision path as the radial jitter or torsional jitter of a single collision event; Wherein, the amplitude of the radial jitter is the maximum vibration distance between the follower model core and the active model core; The amplitude of the torsional vibration is the maximum vibration distance of the follower model core during operation.

3. The creative material correction system based on AIGC according to claim 1, characterized in that: The model disassembler sets an active model core corresponding to the active model according to the geometric position of the active model, and determines a corresponding follower model core according to the position and angle corresponding to the follower model; In a single collision, the model disassembler sets the follower model coordinate system of each follower model based on the follower model core according to the contact position between the active model and each follower model.

4. The AIGC-based creative material correction system according to claim 2 or 3, characterized in that: The defect diagnostic device is provided with a stable jitter interval, and sets a number of jitters exceeding the stable jitter interval as sudden jitters; According to the position of each sudden jitter on the follower model, the projection of the sudden jitter on the corresponding surface where the line connecting the follower model core and the active model core is located is determined as the sudden phase of the sudden jitter.

5. The AIGC-based creative material correction system according to claim 4, characterized in that: For a single mutation path, the defect diagnostic device further determines the equivalent mutations of each follow-up model according to the mutation phase, and determines the corresponding path for the recurrence of each equivalent mutation, and records it as the mutation path of the mutation phase.

6. The AIGC-based creative material correction system according to claim 5, characterized in that: The defect diagnostic device compares the mutation path with the test path to form a corresponding mutation fit, determines an active model boundary of the active model and a follower model boundary of the follower model according to the mutation fit, and records the active model boundary and the follower model boundary as potential fault displacements.

7. The creative material correction system based on AIGC according to claim 5, characterized in that: The defect diagnostic device maps the mutation path onto the test path and forms a corresponding mutation mapping relationship, and based on the mutation mapping relationship, records several frames in which the follower model contacts the active model in the collision path where the mutation jitter occurs as potential fault frames.

8. The creative material correction system based on AIGC according to claim 6 or 7, characterized in that: The material trimmer determines the potential fault frame of the corresponding active model as an actual fault frame in response to the potential fault frame and the potential fault displacement overlapping in a plurality of test paths, or, In response to the potential fault frame and the potential fault displacement not overlapping in any test path, determining that the follower model fails; A single test includes at least two consecutive test paths.

9. The creative material correction system based on AIGC according to claim 8, characterized in that: If the mutation path does not overlap with the test path in any test path, the model disassembler determines that the collision path is abnormal and adjusts the structure of the original image.

10. The creative material correction system based on AIGC according to claim 9, characterized in that: When determining the actual fault frame, the defect diagnostic device performs fault frame verification and performs tests on at least three test paths; Each test path marks the actual fault frame, and when running to each follower model, performs verification according to the interaction between each follower model and the active model.

Images