Workflow conversion system and method for converting native nodes into cloud nodes

Abstract

The invention relates to a workflow conversion system and method for converting a native node into a cloud node. The conversion system comprises a native workflow acquisition component for acquiring a native workflow to be used by a user based on a request of the user; the native node traversal component is used for traversing and analyzing the acquired native nodes in the native workflow, determining the native nodes without independence as non-transferable native nodes and determining the native nodes with independence as transferable native nodes by determining independence of the native nodes to local attributes; the cloud node conversion component is used for converting the transferable native node into a cloud node, and the converted cloud node keeps the node upstream and downstream relationship of the native node; and the workflow regeneration component is used for combining the converted cloud nodes and unconverted native nodes in the native workflow into a new workflow based on an upstream and downstream relationship, so that the new workflow comprises a local part deployed on the local equipment and a cloud part deployed on the cloud end.

Description

Technical Field

[0001] The present disclosure relates to the field of computer information processing, and in particular to a workflow conversion system and method for converting native nodes into cloud nodes. Background Art

[0002] With the rapid development of artificial intelligence, models that generate images or videos from text are becoming increasingly popular. However, due to insufficient local computing power, these models often run very slowly, resulting in a poor user experience. Therefore, leveraging network computing power and public computing power to quickly run models and obtain results has become a common user need.

[0003] ComfyUI is a commonly used workflow tool that uses a graphical interface to lower the barrier to entry for AI image generation. However, while regular users know they can leverage public computing power to accelerate AI image generation, they often don't know which ComfyUI native nodes can be converted to cloud nodes and deployed in the cloud. Furthermore, some cloud node developers have deployed numerous cloud nodes as plugins to accelerate AI image generation. However, the relationship between these native nodes and specific cloud nodes is often unknown to average users, making direct application difficult. Furthermore, in some specific workflows, multiple native nodes can be deployed simultaneously on a single cloud node. However, if deployed separately as multiple cloud nodes, since cloud nodes rely on network calls, multiple network calls may be generated. Consequently, even after converting to cloud nodes, the workflow will still require multiple separate calls to the same network computing power, reducing network call efficiency. Therefore, overall, both regular workflow tools and their corresponding plugins are not user-friendly.

[0004] Therefore, people need a workflow conversion system and method for converting native nodes into cloud nodes, which can enable ordinary users to directly and clearly understand the native nodes that can be converted into cloud nodes and select cloud nodes easily.

[0005] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not form the prior art that is already known to a person of ordinary skill in the art. Summary of the Invention

[0006] In view of this, the present disclosure provides a workflow conversion system, which can facilitate ordinary users to simply implement the AI ​​image generation process directly through the system conversion plug-in of some workflow tools.

[0007] Other features and advantages of the present disclosure will become apparent from the following detailed description, or may be learned in part by practice of the present disclosure.

[0008] According to one aspect of the present disclosure, a workflow conversion system for converting native nodes into cloud nodes is proposed, including: a native workflow acquisition component, which acquires the native workflow to be used by the user based on the user's request; a native node traversal component, which traverses and analyzes the native nodes in the acquired native workflow, and determines the independence of the native nodes to local attributes, determines that the native nodes without independence are non-migratable native nodes, and determines that the native nodes with independence are migratable native nodes; a cloud node conversion component, which converts the migratable native nodes into cloud nodes, wherein the converted cloud nodes retain the upstream and downstream node relationships of the native nodes themselves; and a workflow regeneration component, which combines the converted cloud nodes with the unconverted native nodes in the native workflow into a new workflow based on the upstream and downstream relationships, so that the new workflow includes a local part deployed on the local device and a cloud part deployed on the cloud.

[0009] The workflow conversion system for converting native nodes into cloud nodes according to the present disclosure further includes: a workflow visualization component for traversing and analyzing the native nodes in the acquired native workflow after the native node traversal component, connecting the nodes in the workflow order, configuring properties for each node, and displaying the migration ability of the native nodes.

[0010] According to the workflow conversion system for converting native nodes into cloud nodes disclosed in the present invention, the native nodes that do not have independence include: native nodes that rely on local dedicated hardware, native nodes that rely on local file paths, native nodes directly connected to intranet databases, native nodes for interacting with legacy systems without open APIs, native nodes for shared memory communication, native nodes for fixed-path file operations, and native nodes for calling local services that are not containerized.

[0011] The workflow conversion system for converting native nodes into cloud nodes according to the present disclosure further includes: a node fusion component, which is used to determine that consecutive adjacent migratable native nodes are fusionable nodes after traversing and analyzing the native nodes in the acquired native workflow after the native node traversal component, so that the cloud node conversion component selects multiple adjacent fusionable nodes to convert into one cloud node when converting the migratable native nodes into cloud nodes.

[0012] The workflow conversion system for converting a native node into a cloud node according to the present disclosure also includes a cloud node conversion guide component, which has a drop-down menu on the native node displayed as a migratable native node in the visual workflow, displaying selectable cloud nodes. The selectable cloud nodes point to the cloud nodes in the cloud node library corresponding to the migratable native node, so that the user can directly select the cloud node to convert the native node to the cloud node.

[0013] According to another aspect of the present disclosure, a workflow conversion method for converting a native node into a cloud node is also provided, including: obtaining a native workflow to be used by a user based on a user's request through a native workflow acquisition component; traversing and analyzing the native nodes in the obtained native workflow through a native node traversal component, and determining the independence of the native nodes to local attributes, determining that the native nodes without independence are non-migratable native nodes, and determining that the native nodes with independence are migratable native nodes; converting the migratable native nodes into cloud nodes through a cloud node conversion component, wherein the converted cloud nodes retain the upstream and downstream node relationships of their native nodes; and combining the converted cloud nodes with the unconverted native nodes in the native workflow into a new workflow based on the upstream and downstream relationships through a workflow regeneration component, so that the new workflow includes a local part deployed on a local device and a cloud part deployed on the cloud.

[0014] The workflow conversion method for converting native nodes into cloud nodes according to the present disclosure also includes: after traversing and analyzing the native nodes in the acquired native workflow after the native node traversal component, connecting the nodes in the workflow order through the workflow visualization component, configuring properties for each node, and displaying the migration ability of the native nodes.

[0015] According to the workflow conversion method for converting native nodes into cloud nodes disclosed in the present invention, the native nodes that do not have independence include: native nodes that rely on local dedicated hardware, native nodes that rely on local file paths, native nodes directly connected to intranet databases, native nodes for interacting with legacy systems without open APIs, native nodes for shared memory communication, native nodes for fixed-path file operations, and native nodes for calling local services that are not containerized.

[0016] The workflow conversion method for converting a native node into a cloud node according to the present disclosure further includes: a node fusion component, which is used to traverse and analyze the native nodes in the acquired native workflow after the native node traversal component, and determine that consecutive adjacent migratable native nodes are fusion-capable nodes, so that when the cloud node conversion component converts the migratable native node into a cloud node, it selects multiple adjacent fusion-capable nodes to convert into one cloud node.

[0017] The workflow conversion method for converting a native node into a cloud node according to the present disclosure also includes: displaying selectable cloud nodes in a drop-down menu of a migratable native node displayed in a visual workflow through a cloud node conversion guide component, wherein the selectable cloud nodes point to cloud nodes in a cloud node library corresponding to the migratable native nodes, so that users can directly select cloud nodes to convert native nodes into cloud nodes.

[0018] According to the workflow conversion system and method disclosed in the present invention, by determining the independence of native nodes, migratable native nodes are displayed, and through the cloud node library provided by the system for various native nodes that can be converted into cloud nodes, selectable cloud nodes are provided to users, and integration guidance is automatically provided to users based on the adjacent series relationship between native nodes, thereby providing ordinary users with a user-friendly workflow conversion interface. As a result, it is greatly convenient for users to use network or cloud computing power based on common workflow tools to improve the speed and efficiency of AI generation processing, thereby bringing practical convenience of smart life to users.

[0019] It should be understood that the foregoing general description and the following detailed description are exemplary only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The above and other objects, features and advantages of the present disclosure will become more apparent by describing in detail exemplary embodiments thereof with reference to the accompanying drawings. The drawings described below are only some embodiments of the present disclosure, and it is clear to those skilled in the art that other drawings can be derived from these drawings without inventive effort.

[0021] Figure 1 It is a block diagram showing a first embodiment of a workflow conversion system for converting a native node into a cloud node according to the present disclosure, according to an exemplary embodiment.

[0022] Figure 2 2 is a block diagram illustrating a second embodiment of a workflow conversion system for converting a native node into a cloud node according to the present disclosure, according to an exemplary embodiment.

[0023] Figure 3 3 is a block diagram showing a third embodiment of a workflow conversion system for converting a native node into a cloud node according to the present disclosure, according to an exemplary embodiment.

[0024] Figure 4 4 is a block diagram showing a fourth embodiment of a workflow conversion system for converting a native node into a cloud node according to the present disclosure, according to an exemplary embodiment.

[0025] Figure 5 The flowchart of the workflow conversion method for converting a native node into a cloud node according to the present disclosure is shown according to an exemplary embodiment. DETAILED DESCRIPTION

[0026] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be embodied in many forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete and will fully convey the concepts of the example embodiments to those skilled in the art. Like reference numerals in the drawings represent like or similar parts, and thus repetitive description thereof will be omitted.

[0027] In addition, the described features, structures or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present disclosure. However, those skilled in the art will appreciate that the technical solutions of the present disclosure can be practiced without one or more of the specific details, or other methods, components, devices, steps, etc. can be adopted. In other cases, well-known methods, devices, implementations or operations are not shown or described in detail to avoid blurring various aspects of the present disclosure.

[0028] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically separate entities. That is, these functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0029] The flowcharts shown in the accompanying drawings are for illustrative purposes only and do not necessarily include all contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may be decomposed, while others may be combined or partially combined. Therefore, the actual execution order may vary depending on the actual situation.

[0030] It should be understood that although the terms first, second, third, etc. may be used herein to describe various components, these components should not be limited by these terms. These terms are used to distinguish one component from another. Thus, the first computing device discussed below can be referred to as the second computing device without departing from the teachings of the present disclosure. As used herein, the term "and / or" includes any one and all combinations of one or more of the associated listed items.

[0031] Those skilled in the art will understand that the drawings are merely schematic diagrams of example embodiments, and the modules or processes in the drawings are not necessarily necessary for implementing the present disclosure, and therefore cannot be used to limit the scope of protection of the present disclosure.

[0032] Figure 1 FIG. 1 is a block diagram of an embodiment of a workflow conversion system 100 for converting a native node into a cloud node according to the present disclosure, according to an exemplary embodiment. Figure 1As shown, the workflow conversion system 100 includes a native workflow acquisition component 110, a native node traversal component 120, a cloud node conversion component 130, and a workflow regeneration component 140. Generally speaking, the workflow conversion system 100, which converts native nodes to cloud nodes, is similar to installing a conversion system or conversion plug-in on a workflow tool such as ComfyUI. This replaces some nodes in the native workflow with corresponding cloud nodes, completing the "cloudification" of computing resources while maintaining the functionality of the workflow.

[0033] Specifically, the native workflow acquisition component 110 retrieves the native workflow the user intends to use based on the user's request. Subsequently, the native node traversal component 120 traverses and analyzes the native nodes in the retrieved native workflow. By determining the independence of the native nodes with respect to local properties, it identifies those without independence as non-migratable native nodes and those with independence as migratable native nodes. Non-independent native nodes include: native nodes that rely on local dedicated hardware, native nodes that rely on local file paths, native nodes that directly connect to intranet databases, native nodes that interact with legacy systems without open APIs, native nodes that use shared memory communication, native nodes that perform fixed-path file operations, and native nodes that call local services without containerization. Native nodes that rely on local dedicated hardware include industrial control device drivers, local dongles, or nodes with specific physical interfaces. Registry nodes or non-virtualized local service nodes are also non-migratable nodes. Real-time control nodes with millisecond-level response times, such as high-frequency trading engines, and nodes that are deeply coupled to local systems, such as nodes using shared memory communication, are also non-migratable.

[0034] Taking a ComfyUI workflow for generating images from text as an example, a native workflow contains seven native ComfyUI nodes. The entire workflow includes: a load checkpoint node (LOADCHECKPOINT), which is used to load the pre-trained model weights and configuration to ensure that the model has initialized parameters when generating images; and two CLIP Text Encode nodes (CLIP Text Encode), which are used to encode text prompts into vectors for alignment with image features. It utilizes the CLIP (Contrastive Language-Image Pre-training) model to convert text into the model's input format. The Empty Latent node generates an empty latent space vector, which is typically used as the initial latent representation for generating an image. The KSampler node samples from the latent space to generate multiple latent vectors, which are then used to generate diverse images. The VAE decodes the latent space vector into an image. The VAE uses an encoder to encode the image into a latent space representation and a decoder to restore it back to an image. Finally, the Save Image node saves the generated image to a specified path or format for subsequent processing or display. Together, these nodes form a complete workflow for generating images from text descriptions, enabling the transition from text descriptions to image generation. A traversal analysis revealed that the Save Image and Empty Latent nodes are non-migratable native nodes, while the other nodes are cloud-compatible.

[0035] Next, the cloud node conversion component 130 converts the migratable native nodes into cloud nodes, preserving the native node's inherent upstream and downstream relationships. Alternatively, the cloud node conversion component 130 can directly convert all migratable native nodes into cloud nodes. For example, to convert a native ComfyUI workflow JSON-formatted node into a JSON-formatted cloud node, one typically first needs to understand the specific structure and functionality of the native ComfyUI workflow JSON node. This includes the node's input and output ports, parameter settings, and the logical processing relationships between them. Next, the component maps the node to the cloud node structure: Based on the functionality of the native JSON node, a corresponding cloud node structure is designed. The cloud node's required input parameters, output data format, and logical processing flow are determined, ensuring consistency with the native node. Finally, a cloud node JSON description is created: a new JSON-formatted description file is compiled based on the designed cloud node structure. This file should contain the cloud node's metadata (such as the node ID and type), input and output port definitions, parameter settings, and processing logic. This is a conventional technical approach and will not be elaborated here. Dedicated cloud node service providers pre-generate a number of cloud nodes from standard native nodes as plug-in cloud node databases for users to choose from. When providing a commonly used cloud node database, after the cloud nodes in the database are written, the pre-written cloud node JSON description files are imported into the target cloud platform or tool for testing. This verifies that the cloud nodes can correctly receive input data, execute logical processing, and output the expected results. These pre-written cloud nodes are typically optimized and tuned to improve performance, enhance error handling, or adjust parameter settings to ensure optimal performance. These cloud nodes are documented in detail, documenting their functions, usage instructions, parameter descriptions, and any precautions. These optimized cloud nodes are then deployed to the cloud platform or related systems to ensure easy access and use. The specific writing method is not detailed here; conventional methods can be used. Therefore, on current cloud node platforms, most cloud node conversion processes are completed by selecting existing cloud nodes.

[0036] Finally, the workflow regeneration component 140 combines the converted cloud nodes with the unconverted native nodes in the native workflow based on upstream and downstream relationships to form a new workflow. This new workflow thus includes both a local portion deployed on the local device and a cloud portion deployed in the cloud. In this way, by replacing some nodes in a native workflow like ComfyUI with corresponding cloud nodes, the computing resources are "cloudified" while maintaining the workflow's functionality. In other words, the native workflow is converted to a workflow that can utilize cloud nodes on the cloud platform, while maintaining its functionality.

[0037] Figure 21 is a block diagram of a second embodiment of a workflow conversion system for converting a native node to a cloud node according to the present disclosure, according to an exemplary embodiment. Figure 1 compared to, Figure 2 Only a workflow visualization component 150 is added. In some cases, users need to independently select which native nodes need to be converted into cloud nodes according to their own preferences, but the users themselves do not have the ability to read the code. Therefore, in order to facilitate the user's operation, the workflow conversion system for converting native nodes into cloud nodes disclosed in the present invention also includes a workflow visualization component 150, which is used to connect the nodes in the workflow order after the native node traversal component 120 traverses and analyzes the native nodes in the acquired native workflow, configure attributes for each node, and display the migration ability of the native nodes. In this way, users can independently select migratable native nodes. Typically, for example, using ComfyUI, the workflow visualization component 150 accesses a node library based on the native workflow and drags and drops nodes from the library corresponding to the native nodes of the workflow onto the canvas. Select the desired node from the library (e.g., LOADCHECKPOINT, CLIP Text Encode, KSampler), drag it onto the canvas, and connect the node logic, connecting the nodes in the workflow sequence (e.g., text input → CLIP encoding → empty latent space → KSampler → VAE decoding → save image), ensuring the correct data flow direction (e.g., KSampler output connected to VAE Decode input). The connections between nodes represent the data transfer path and are the core of workflow visualization. Node parameters are then configured. After forming a basic workflow graph, users can double-click a node in the canvas to open the parameter panel and set properties as needed. For the example above, for LOADCHECKPOINT: select the cloud storage or local model file path. For CLIP Text Encode: enter a prompt to define the generated content. KSampler: Adjust generation parameters such as the number of sampling steps and seed. Save Image: Set the output path (such as a cloud storage bucket s3: / / output / or a local folder). After generating a visual workflow, you can run and debug it in advance, viewing progress, logs, and error messages in real time, making it easier to debug node connection or parameter issues. After the visualization is complete, you can export the current workflow as a JSON file (containing all node configurations and connection relationships).

[0038] Figure 3 1 is a block diagram of a third embodiment of a workflow conversion system for converting a native node to a cloud node according to the present disclosure, according to an exemplary embodiment. Figure 2 compared to, Figure 3Only a cloud node conversion guidance component 160 has been added. It should be noted that when users independently select conversions, selecting a cloud node is very difficult for ordinary users. Therefore, the workflow conversion system for converting native nodes to cloud nodes disclosed herein also includes a cloud node conversion guidance component 160. On the native node displayed as a migratable node in the visual workflow, a drop-down menu is set to display selectable cloud nodes. The selectable cloud nodes point to the cloud nodes in the cloud node library corresponding to the migratable native node, so that the user can directly select a cloud node to convert the native node to a cloud node. In this way, the user does not need to have the knowledge or experience of the correspondence between the native node and the cloud node to be converted. In this way, the cloud node conversion component 130 can complete the cloud node conversion based on the user's simple selection of the corresponding cloud node in the cloud node library under the guidance of the cloud node conversion guidance component 160, bringing great simplicity and ease of use to the user in AI image generation. Generally, when the cloud node conversion component 130 selects the cloud node corresponding to the native node to be converted in the cloud node library, it will attach the upstream and downstream link relationships of the native node to the selected cloud node.

[0039] Figure 4 1 is a block diagram of a fourth embodiment of a workflow conversion system for converting a native node to a cloud node according to the present disclosure, according to an exemplary embodiment. Figure 3 In comparison, only a cloud node fusion component 170 is added. It should be pointed out that cloud nodes are completed through network calls, and multiple cloud nodes may generate multiple network calls, but for some cloud nodes in series, their network calls can be merged and completed through another "fused" cloud node. How to select a "fused" cloud node to replace multiple cloud nodes in series also requires more experience, which is not friendly to ordinary users. Therefore, further, the workflow conversion system for converting native nodes to cloud nodes disclosed in the present invention also includes a cloud-cloud node fusion component 170, which is used to determine that consecutive adjacent migratable native nodes are fusible nodes after the native node traversal component 120 traverses and analyzes the native nodes in the acquired native workflow, so that the cloud node conversion component 130 selects multiple adjacent fusible nodes to convert into one cloud node when converting the migratable native node to a cloud node. Optionally, the cloud node fusion component 170 may also traverse and analyze the new workflow after the workflow regeneration component 140 generates the new workflow, obtain the adjacent serial relationship between the cloud nodes deployed on the cloud platform in the new workflow, and fuse the cloud nodes in the adjacent serial relationship to obtain the optimized new workflow again.

[0040] Figure 5 FIG is a flowchart of a workflow conversion method for converting a native node into a cloud node according to the present disclosure, according to an exemplary embodiment. Figure 5As shown, at step S210, the native workflow acquisition component 110 acquires the native workflow the user intends to use based on the user's request. Subsequently, at step S220, the native node traversal component 120 traverses and analyzes the native nodes in the acquired native workflow. By determining the independence of the native nodes with respect to local properties, native nodes that lack independence are identified as non-migratable native nodes, while native nodes that possess independence are identified as migratable native nodes. Non-independent native nodes include: native nodes that rely on local dedicated hardware, native nodes that rely on local file paths, native nodes that directly connect to intranet databases, native nodes that interact with legacy systems without open APIs, native nodes that use shared memory communication, native nodes that perform fixed-path file operations, and native nodes that call local services without containerization. Native nodes that rely on local dedicated hardware include industrial control device drivers, local dongles, or nodes with specific physical interfaces. Registry nodes or non-virtualized local service nodes are also non-migratable nodes. Real-time control nodes with millisecond-level response times, such as high-frequency trading engines, and nodes that are deeply coupled to local systems, such as nodes using shared memory communication.

[0041] Taking a ComfyUI workflow for generating images from text as an example, a native workflow contains seven native ComfyUI nodes. The entire workflow includes: a load checkpoint node (LOADCHECKPOINT), which is used to load the pre-trained model weights and configuration to ensure that the model has initialized parameters when generating images; and two CLIP Text Encode nodes (CLIP Text Encode), which are used to encode text prompts into vectors for alignment with image features. It utilizes the CLIP (Contrastive Language-Image Pre-training) model to convert text into the model's input format. The Empty Latent node generates an empty latent space vector, which is typically used as the initial latent representation for generating an image. The KSampler node samples from the latent space to generate multiple latent vectors, which are then used to generate diverse images. The VAE decodes the latent space vector into an image. The VAE uses an encoder to encode the image into a latent space representation and a decoder to restore it back to an image. Finally, the Save Image node saves the generated image to a specified path or format for subsequent processing or display. Together, these nodes form a complete workflow for generating images from text descriptions, enabling the transition from text descriptions to image generation. A traversal analysis revealed that the Save Image and Empty Latent nodes are non-migratable native nodes, while the other nodes are cloud-compatible.

[0042] Subsequently, at step S230, the cloud node conversion component 130 converts the migratable native nodes into cloud nodes, where the converted cloud nodes retain their native node upstream and downstream relationships. Alternatively, the cloud node conversion component 130 can directly convert all migratable native nodes into cloud nodes. For example, if converting a native ComfyUI workflow JSON-formatted node into a JSON-formatted cloud node, one typically first needs to understand the specific structure and functionality of the native ComfyUI workflow JSON node. This includes the node's input and output ports, parameter settings, and the logical processing relationships between them. Next, the cloud node structure is mapped to the cloud node structure: Based on the functionality of the native JSON node, a corresponding cloud node structure is designed. The cloud node's required input parameters, output data format, and logical processing flow are determined, ensuring consistency with the native node. A cloud node JSON description is then written: a new JSON-formatted description file is created based on the designed cloud node structure. This file should contain the cloud node's metadata (such as the node ID and type), input and output port definitions, parameter settings, and processing logic. This is a conventional technical approach and will not be elaborated here. Dedicated cloud node service providers pre-generate a number of cloud nodes from standard native nodes as plug-in cloud node databases for users to choose from. When providing a commonly used cloud node database, after the cloud nodes in the database are written, the pre-written cloud node JSON description files are imported into the target cloud platform or tool for testing. This verifies that the cloud nodes can correctly receive input data, execute logical processing, and output the expected results. These pre-written cloud nodes are typically optimized and tuned to improve performance, enhance error handling, or adjust parameter settings to ensure optimal performance. These cloud nodes are documented in detail, documenting their functions, usage instructions, parameter descriptions, and any precautions. These optimized cloud nodes are then deployed to the cloud platform or related systems to ensure easy access and use. The specific writing method is not detailed here; conventional methods can be used. Therefore, on current cloud node platforms, most cloud node conversion processes are completed by selecting existing cloud nodes.

[0043] Finally, the workflow regeneration component 140 combines the converted cloud nodes with the unconverted native nodes in the native workflow based on upstream and downstream relationships to form a new workflow. This new workflow thus includes both a local portion deployed on the local device and a cloud portion deployed in the cloud. In this way, by replacing some nodes in a native workflow like ComfyUI with corresponding cloud nodes, the computing resources are "cloudified" while maintaining the workflow's functionality. In other words, the native workflow is converted to a workflow that can utilize cloud nodes on the cloud platform, while maintaining its functionality.

[0044] However, in some cases, users need to independently select which native nodes need to be converted to cloud nodes based on their own preferences, but the users themselves do not have the ability to read code. Therefore, to facilitate user operations, the workflow conversion system for converting native nodes to cloud nodes disclosed in this disclosure also includes a workflow visualization component 150, which is used to connect the nodes in the workflow order after traversing and analyzing the native nodes in the acquired native workflow in step S220, configure properties for each node, and display the migration ability of the native nodes. In this way, users can independently select the native nodes that can be migrated. Typically, for example, using ComfyUI, the workflow visualization component 150 accesses a node library based on the native workflow and drags and drops nodes from the library corresponding to the native nodes of the workflow onto the canvas. Select the desired node from the library (e.g., LOADCHECKPOINT, CLIP Text Encode, KSampler), drag it onto the canvas, and connect the node logic, connecting the nodes in the workflow sequence (e.g., text input → CLIP encoding → empty latent space → KSampler → VAE decoding → save image), ensuring the correct data flow direction (e.g., KSampler output connected to VAE Decode input). The connections between nodes represent the data transfer path and are the core of workflow visualization. Node parameters are then configured. After forming a basic workflow graph, users can double-click a node in the canvas to open the parameter panel and set properties as needed. For the example above, for LOADCHECKPOINT: select the cloud storage or local model file path. For CLIP Text Encode: enter a prompt to define the generated content. KSampler: Adjust generation parameters such as the number of sampling steps and seed. Save Image: Set the output path (such as a cloud storage bucket s3: / / output / or a local folder). After generating a visual workflow, you can run and debug it in advance, viewing progress, logs, and error messages in real time, making it easier to debug node connection or parameter issues. After the visualization is complete, you can export the current workflow as a JSON file (containing all node configurations and connection relationships).

[0045] It should be noted that when the user independently selects the conversion, the selection of the cloud node is very difficult for ordinary users. Therefore, the workflow conversion system for converting native nodes to cloud nodes disclosed in the present invention also includes a cloud node conversion guide component 160. On the native node displayed as a migratable native node in the visual workflow, a drop-down menu is set to display the selectable cloud nodes. The selectable cloud nodes point to the cloud nodes in the cloud node library corresponding to the migratable native node, so that the user can directly select the cloud node to convert the native node to the cloud node. In this way, the user does not need to have the knowledge or experience of the correspondence between the native node and the cloud node to be converted. In this way, the cloud node conversion component 130 can complete the cloud node conversion based on the user's simple selection of the corresponding cloud node in the cloud node library under the guidance of the cloud node conversion guide component 160, bringing great simplicity and ease of use to the user in AI image generation. Usually, when the cloud node conversion component 130 selects the cloud node corresponding to the native node to be converted in the cloud node library, it will attach the upstream and downstream link relationship of the native node to the selected cloud node.

[0046] It should be noted that cloud nodes are established through network calls, and multiple cloud nodes may generate multiple network calls. However, for some serially connected cloud nodes, their network calls can be merged and completed through another "fused" cloud node. Selecting a "fused" cloud node to replace multiple serially connected cloud nodes requires considerable experience and is not user-friendly. Therefore, further, the disclosed workflow conversion system for converting native nodes to cloud nodes also includes a node fusion component 170, which is configured to, after traversing and analyzing the native nodes in the acquired native workflow in step S120, determine that consecutive, adjacent, migratable native nodes are fused nodes. This allows the cloud node conversion component 130 to select multiple adjacent, fused nodes to convert into one cloud node when converting the migratable native nodes to cloud nodes. Optionally, after generating the new workflow in step S240, the node fusion component 170 can also traverse and analyze the new workflow, obtain the adjacent serial relationships between the cloud nodes deployed on the cloud platform in the new workflow, and fuse the cloud nodes in the adjacent serial relationships to obtain the optimized new workflow.

[0047] In summary, according to the workflow conversion system and method disclosed in the present invention, by determining the independence of native nodes, migratable native nodes are displayed, and through the cloud node library provided by the system for various native nodes that can be converted into cloud nodes, selectable cloud nodes are provided to users, and the system automatically provides users with fusible guidance based on the adjacent series relationship between native nodes, thereby providing ordinary users with a user-friendly workflow conversion interface. As a result, it is greatly facilitated for users to use network or cloud computing power based on commonly used workflow tools to improve the speed and efficiency of AI generation processing, thereby bringing practical convenience of smart life to users.

[0048] Those skilled in the art will appreciate that the modules described above can be distributed in the device according to the description of the embodiment, or can be modified accordingly to be used in one or more devices that are different from the embodiment. The modules of the above embodiment can be combined into one module or further divided into multiple submodules.

[0049] Through the description of the above embodiments, it will be readily understood by those skilled in the art that the example embodiments described herein can be implemented via software or via a combination of software and necessary hardware. Therefore, the technical solutions according to the embodiments of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, or mobile hard drive) or on a network and includes several instructions for enabling a computing device (such as a personal computer, server, mobile terminal, or network device) to execute the methods according to the embodiments of the present disclosure.

[0050] While the exemplary embodiments of the present disclosure have been specifically illustrated and described above, it should be understood that the present disclosure is not limited to the detailed structures, configurations, or implementations described herein; rather, the present disclosure is intended to encompass various modifications and equivalent configurations within the spirit and scope of the appended claims.

Claims

1. A workflow conversion system for converting native nodes into cloud nodes, comprising: The native workflow acquisition component obtains the native workflow that the user wants to use based on the user's request; The native node traversal component traverses and analyzes the native nodes in the obtained native workflow, and determines the independence of the native nodes to the local attributes, and determines the native nodes without independence as non-migratable native nodes, and determines the native nodes with independence as migratable native nodes; The cloud node conversion component converts the migratable native nodes into cloud nodes, where the converted cloud nodes retain the upstream and downstream node relationships of the native nodes; as well as The workflow regeneration component combines the converted cloud nodes and the unconverted native nodes in the native workflow into a new workflow based on the upstream and downstream relationships, so that the new workflow includes a local part deployed on the local device and a cloud part deployed in the cloud.

2. The workflow conversion system for converting a native node to a cloud node according to claim 1, further comprising: The workflow visualization component is used to connect the nodes in the workflow order after the native nodes in the native workflow obtained by the native node traversal component traverse and analyze, configure properties for each node, and display the portability of the native nodes.

3. The workflow conversion system for converting a native node into a cloud node according to claim 1, wherein: The native nodes that do not have independence include: native nodes that rely on local dedicated hardware, native nodes that rely on local file paths, native nodes that are directly connected to the intranet database, native nodes that interact with legacy systems without open APIs, native nodes for shared memory communication, native nodes for fixed-path file operations, and native nodes for non-containerized local service calls.

4. The workflow conversion system for converting a native node to a cloud node according to claim 1 or 2, further comprising: The node fusion component is used to determine that consecutive adjacent migratable native nodes are fusion-capable nodes after the native node traversal component traverses and analyzes the native nodes in the acquired native workflow, so that the cloud node conversion component can select multiple adjacent fusion-capable nodes to convert into one cloud node when converting the migratable native nodes into cloud nodes.

5. The workflow conversion system for converting a native node into a cloud node according to claim 2 further includes a cloud node conversion guide component, which has a drop-down menu on the native node displayed as a migratable native node in the visual workflow, displaying selectable cloud nodes, and the selectable cloud nodes point to the cloud nodes in the cloud node library corresponding to the migratable native node, so that the user can directly select the cloud node to convert the native node into a cloud node.

6. A workflow conversion method for converting a native node to a cloud node, comprising: The native workflow acquisition component obtains the native workflow that the user wants to use based on the user's request; Traversing and analyzing the native nodes in the native workflow obtained by the native node traversal component, determining the independence of the native nodes to local attributes, determining the native nodes without independence as non-migratable native nodes, and determining the native nodes with independence as migratable native nodes; The cloud node conversion component converts the migratable native node into a cloud node, where the converted cloud node retains the upstream and downstream node relationships of the native node. as well as The converted cloud nodes and the unconverted native nodes in the native workflow are combined into a new workflow based on the upstream and downstream relationships through the workflow regeneration component, so that the new workflow includes a local part deployed on the local device and a cloud part deployed in the cloud.

7. The workflow conversion method for converting a native node to a cloud node according to claim 6, further comprising: After the native node traversal component traverses and analyzes the native nodes in the obtained native workflow, the workflow visualization component connects the nodes in the workflow order, configures properties for each node, and displays the portability of the native nodes.

8. The workflow conversion method for converting a native node into a cloud node according to claim 6, wherein: The native nodes that do not have independence include: native nodes that rely on local dedicated hardware, native nodes that rely on local file paths, native nodes that are directly connected to the intranet database, native nodes that interact with legacy systems without open APIs, native nodes for shared memory communication, native nodes for fixed-path file operations, and native nodes for non-containerized local service calls.

9. The workflow conversion method for converting a native node to a cloud node according to claim 6 or 7, further comprising: The node fusion component is used to determine that consecutive adjacent migratable native nodes are fusion-capable nodes after the native node traversal component traverses and analyzes the native nodes in the acquired native workflow, so that the cloud node conversion component can select multiple adjacent fusion-capable nodes to convert into one cloud node when converting the migratable native nodes into cloud nodes.

10. The workflow conversion method for converting a native node to a cloud node according to claim 7, further comprising: The cloud node conversion guide component displays selectable cloud nodes in a drop-down menu of migratable native nodes in a visual workflow. The selectable cloud nodes point to cloud nodes in a cloud node library corresponding to the migratable native nodes, so that users can directly select cloud nodes to convert native nodes to cloud nodes.

Images