Image generation method and device, equipment, medium and program

Abstract

The disclosed embodiment discloses an image generation method and apparatus, device, medium and program, which obtains an image generation task input by a user, outputs a requirement prompt message, obtains a requirement reply message input by the user based on the requirement prompt message, and then determines the image generation requirement based on the requirement reply message, and then determines an image display scheme based on the image generation requirement and outputs the description information of the image display scheme, generates an image based on the image display scheme confirmed by the user in response to receiving a confirmation message of the image display scheme from the user, and outputs the image. As a result, the disclosed method can generate an image for the user without the user having to express clear ideas, design schemes, and prompts submitted to the model for the desired image, thereby improving the image generation efficiency and user experience.

Description

Technical Field

[0001] The present disclosure relates to artificial intelligence technology, natural language technology and data processing technology, and in particular to an image generation method and apparatus, device, medium and program. Background Art

[0002] With the development of artificial intelligence (AI) technology, AI generative models have great potential in content creation. In the art and design industry, users hope to use AI generative models to perform content creation related work, for example, by submitting text prompts to the generative model, the generative model generates various types of images such as product design, illustrations, animations, etc. Summary of the invention

[0003] The embodiments of the present disclosure provide an image generation method and apparatus, a device, a medium and a program to generate an image.

[0004] One aspect of an embodiment of the present disclosure provides an image generation method, including:

[0005] Get the image generation task input by the user;

[0006] Outputting a demand prompt message, and obtaining a demand reply message input by the user based on the demand prompt message;

[0007] Determining an image generation requirement based on the requirement reply message;

[0008] Determine an image display scheme based on the image generation requirement, and output description information of the image display scheme;

[0009] In response to receiving a confirmation message from the user regarding the image presentation plan, an image is generated based on the image presentation plan confirmed by the user, and the image is output.

[0010] Optionally, in any method embodiment of the present disclosure, after obtaining the image generation task input by the user, the method further includes:

[0011] Determine a requirement prompt message corresponding to the image generation task;

[0012] Output demand prompt messages, including:

[0013] Output a requirement prompt message corresponding to the image generation task.

[0014] Optionally, in any method embodiment of the present disclosure, the requirement prompt message includes any one or more of the following information related to the image generation task: task type, target audience, expression theme, style, color, shooting angle, brightness effect, expressed visual feeling, expressed emotion, expressed information, and expressed environment.

[0015] Optionally, in any method embodiment of the present disclosure, determining an image display scheme based on the image generation requirement includes:

[0016] Determine at least one image display scheme based on the image generation requirement, and output description information of the at least one image display scheme, wherein each image display scheme in the at least one image display scheme includes any one or more of the following scheme information: overall image description information, image theme, image presentation environment, main visual elements, and presentation style;

[0017] In response to receiving a confirmation message from a user regarding the image display scheme, generating an image based on the image display scheme confirmed by the user, including:

[0018] In response to receiving a confirmation message sent by a user for a target image presentation scheme among the at least one image presentation scheme, an image is generated based on the target image presentation scheme.

[0019] Optionally, in any method embodiment of the present disclosure, the method further includes:

[0020] In response to receiving a scheme modification message sent by a user for a target image display scheme in the at least one image display scheme, obtaining a scheme modification requirement in the scheme modification message;

[0021] Determining a modified image display scheme based on the target image display scheme and the scheme modification requirement, and outputting description information of the modified image display scheme;

[0022] In response to receiving a confirmation message sent by the user for the modified image display scheme, taking the modified image display scheme as the image display scheme confirmed by the user, performing the operation of generating an image based on the image display scheme confirmed by the user, and outputting the image;

[0023] In response to receiving a scheme modification message sent by a user for the modified image display scheme, the target image display scheme is replaced with the modified image display scheme, and the operation of obtaining the scheme modification requirement in the scheme modification message is iteratively performed.

[0024] Optionally, in any method embodiment of the present disclosure, in response to receiving a confirmation message from a user regarding the image display scheme, generating an image based on the image display scheme confirmed by the user includes:

[0025] In response to receiving a confirmation message from the user regarding the image display scheme, determining scheme details for the image display scheme confirmed by the user, and outputting prompt words and description information of the scheme details;

[0026] In response to receiving a confirmation message of the solution details from the user, an image is generated based on the image presentation solution confirmed by the user and the solution details confirmed by the user.

[0027] Optionally, in any method embodiment of the present disclosure, the prompt words of the solution details include any one or more of the following details and at least one attribute value of each detail: solution refinement points and implementation methods of the solution refinement points, image shape, image size, image resolution, image direction;

[0028] In response to receiving a confirmation message of the solution details from the user, generating an image based on the image display solution confirmed by the user and the solution details confirmed by the user, including:

[0029] In response to receiving a confirmation message sent by a user regarding a target attribute value for each detail determined based on at least one attribute value of each detail, the determined target attribute value for each detail is used as the solution details confirmed by the user, and an image is generated based on the image display solution confirmed by the user and the solution details confirmed by the user.

[0030] Optionally, in any method embodiment of the present disclosure, when the scheme refinement key points include a presentation style, the attribute value of the presentation style includes a text identifier of the presentation style and / or a style representative image.

[0031] Optionally, in any method embodiment of the present disclosure, in response to receiving a confirmation message from a user regarding the image display scheme, generating an image based on the image display scheme confirmed by the user, further comprising:

[0032] In response to receiving an adjustment message sent by a user for the solution details, obtaining an adjustment requirement in the adjustment message;

[0033] Determine adjusted plan details based on the plan details and the adjustment requirements, and output prompt words and description information of the adjusted plan details;

[0034] In response to receiving a confirmation message sent by the user regarding the adjusted solution details, taking the adjusted solution details as the solution details confirmed by the user, performing the operation of generating an image based on the image display solution confirmed by the user and the solution details confirmed by the user, and outputting the image;

[0035] In response to receiving an adjustment message sent by a user for the adjusted solution details, the operation of obtaining the adjustment requirements in the adjustment message is iteratively performed for the adjusted solution details.

[0036] Optionally, in any method embodiment of the present disclosure, generating an image based on the image display scheme confirmed by the user and the scheme details confirmed by the user includes:

[0037] Inputting scheme information of the image display scheme confirmed by the user and prompt words of scheme details confirmed by the user into an image generation model, so that the image generation model generates an image based on the scheme information of the image display scheme confirmed by the user and the prompt words of scheme details confirmed by the user;

[0038] An image output by the image generation model is received.

[0039] Optionally, in any method embodiment of the present disclosure, the image generation model generates an image based on the solution information of the image display solution confirmed by the user and the prompt words of the solution details confirmed by the user, including:

[0040] The image generation model generates an initial image based on the image display scheme confirmed by the user, and adjusts the initial image based on the prompt words of the scheme details confirmed by the user to obtain an optimized image.

[0041] Optionally, in any method embodiment of the present disclosure, after generating an image based on the image display solution confirmed by the user, the method further includes:

[0042] displaying the image;

[0043] In response to receiving a first modification message of the image from the user, determining a first image modification scheme based on the first modification message, the first image modification scheme including a modification scheme of the image display scheme and / or a modification scheme of scheme details, and outputting description information of the first image modification scheme;

[0044] In response to receiving a confirmation message sent by a user regarding the first image modification scheme, modifying the image display scheme confirmed by the user and / or the scheme details confirmed by the user based on the first image modification scheme, and generating an image with the modified image display scheme and scheme details;

[0045] In response to receiving a second modification message sent by a user for the image modification solution, taking the second modification message as a new first modification message, iteratively performing the operation of determining the first image modification solution based on the first modification message;

[0046] Outputting the image includes:

[0047] In response to receiving an output instruction message from a user for the image, the image is output.

[0048] Optionally, in any method embodiment of the present disclosure, the image generation task includes a task text for generating an image.

[0049] Optionally, in any method embodiment of the present disclosure, the image generation task includes: a basic image and a task text for the basic image;

[0050] After obtaining the image generation task of user input, it also includes:

[0051] Performing image recognition on the basic image to obtain an image recognition result;

[0052] Determining an image display solution based on the image generation requirement includes:

[0053] Determine an image display solution based on the image generation requirement and the image recognition result;

[0054] Generate an image based on the image display scheme confirmed by the user, including:

[0055] An image is generated based on the basic image and the image display scheme confirmed by the user.

[0056] Another aspect of the embodiments of the present disclosure provides an image generating device, including:

[0057] An acquisition module is used to acquire the image generation task input by the user;

[0058] Output module, used for outputting demand prompt messages;

[0059] The acquisition module is further used to acquire a demand reply message input by the user based on the demand prompt message;

[0060] A first determining module, configured to determine an image generation requirement based on the requirement reply message;

[0061] A second determination module, used to determine an image display solution based on the image generation requirement;

[0062] The output module is further used to output description information of the image display scheme;

[0063] The acquisition module is further used to receive a confirmation message from the user regarding the image display solution;

[0064] an image generating module, configured to generate an image based on the image display scheme confirmed by the user in response to the obtaining module receiving a confirmation message of the user regarding the image display scheme;

[0065] The output module is also used to output the image.

[0066] Another aspect of the embodiments of the present disclosure provides another image generating device, including:

[0067] An interactive module is used to obtain an image generation task input by a user, call a language model to determine a requirement prompt message corresponding to the image generation task, and output the requirement prompt message; obtain a requirement reply message input by the user based on the requirement prompt message, call the language model to determine an image generation requirement based on the requirement reply message, and determine an image display scheme and description information of the image display scheme based on the image generation requirement, and output description information of the image display scheme; in response to receiving a confirmation message from the user for the image display scheme, call the image generation model to generate an image based on the image display scheme confirmed by the user, and output the image;

[0068] The language model is used to determine a requirement prompt message corresponding to the image generation task, determine the image generation requirement based on the requirement reply message, and determine an image display scheme and description information of the image display scheme based on the image generation requirement;

[0069] The image generation model is used to generate an image based on an image display solution confirmed by a user.

[0070] Another aspect of the embodiments of the present disclosure provides an electronic device, including:

[0071] Memory for storing computer programs;

[0072] The processor is used to execute the computer program stored in the memory, and when the computer program is executed, the method described in any embodiment of the present disclosure is implemented.

[0073] Another aspect of the embodiments of the present disclosure provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the method described in any embodiment of the present disclosure is implemented.

[0074] Another aspect of the embodiments of the present disclosure provides a computer program product, including computer program instructions, which implement the method described in any embodiment of the present disclosure when executed by a processor.

[0075] Based on the image generation method, apparatus, device, medium and program provided by the above-mentioned embodiments of the present disclosure, when the user only inputs the image generation task, the user can be guided to input the requirement reply message by outputting the requirement prompt message, thereby determining the image generation requirement of this image generation task, and then determining the corresponding image display scheme based on the image generation requirement, and outputting the description information of the image display scheme. After the user confirms the image display scheme, the image is generated and output based on the image display scheme confirmed by the user. During the entire image generation process, the user does not need to express clear ideas, design schemes, and desired design elements for the desired image and convert them into clear prompts that can be submitted to the model, and the image can be generated for the user, thereby improving the image generation efficiency and the user experience. The requirement reply message input by the user is used to confirm the image display scheme. Determining the image generation requirements of this image generation task, thereby determining the corresponding image display plan to generate images, is to generate images according to the actual needs of users under the condition of understanding the user's needs, rather than simply relying on prompts input by users to generate images, which can make the generated images more in line with the expression effects desired by users, and help to improve the quality and efficiency of image generation; because users have clear ideas, design plans, and desired design elements for the desired images, and convert them into clear prompts that can be submitted to the model, they need to have an in-depth understanding of professional knowledge such as art, design, and photography. The embodiments of the present disclosure break through the usage restrictions of users who are not familiar with professional knowledge such as art, design, and photography, lower the usage threshold for image generation based on AI technology, and expand the application scope of image generation based on AI technology.

[0076] The technical solution of the present disclosure is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0077] The accompanying drawings, which constitute a part of the specification, illustrate embodiments of the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0078] The present disclosure may be more clearly understood from the following detailed description with reference to the accompanying drawings, in which:

[0079] Figure 1 A flowchart of an embodiment of the image generation method disclosed herein;

[0080] Figure 2 A flowchart of another embodiment of the image generating method disclosed herein;

[0081] Figure 3 A flowchart of another embodiment of the image generating method disclosed herein;

[0082] Figure 4 A flowchart of another embodiment of the image generating method disclosed herein;

[0083] Figure 5 A flowchart of another embodiment of the image generating method disclosed herein;

[0084] Figure 6 A flowchart of another embodiment of the image generating method disclosed herein;

[0085] Figure 7 It is a structural schematic diagram of an embodiment of the image generating device disclosed in the present invention;

[0086] Figure 8 is a structural schematic diagram of another embodiment of the image generating device disclosed in the present invention;

[0087] Fig. 9 It is a structural schematic diagram of another embodiment of the image generating device disclosed in the present invention;

[0088] Fig.10 It is a structural schematic diagram of another embodiment of the image generating device disclosed in the present invention;

[0089] Fig.11 The figure is a schematic diagram of the structure of an application embodiment of the electronic device disclosed in the present invention. DETAILED DESCRIPTION

[0090] Various exemplary embodiments of the present disclosure will now be described in detail with reference to the accompanying drawings. It should be noted that the relative arrangement of components and steps, numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the present disclosure unless otherwise specifically stated.

[0091] Those skilled in the art can understand that the terms "first" and "second" in the embodiments of the present disclosure are only used to distinguish different steps, devices or modules, etc., and neither represent any specific technical meaning nor indicate the necessary logical order between them.

[0092] It should also be understood that in the embodiments of the present disclosure, “plurality” may refer to two or more than two, and “at least one” may refer to one, two, or more than two.

[0093] It should also be understood that any component, data or structure mentioned in the embodiments of the present disclosure can generally be understood as one or more, unless explicitly limited or otherwise indicated in the context.

[0094] In addition, the term "and / or" in the present disclosure is only a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in the present disclosure generally indicates that the associated objects before and after are in an "or" relationship.

[0095] It should also be understood that the description of the various embodiments in the present disclosure focuses on the differences between the various embodiments, and the same or similar aspects thereof can be referenced to each other, and for the sake of brevity, they will not be described one by one.

[0096] At the same time, it should be understood that for the convenience of description, the sizes of the various parts shown in the drawings are not drawn according to the actual proportional relationship.

[0097] The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the present disclosure, its application, or uses.

[0098] Technologies, methods, and equipment known to ordinary technicians in the relevant art may not be discussed in detail, but where appropriate, the technologies, methods, and equipment should be considered as part of the specification.

[0099] It should be noted that like reference numerals and letters refer to similar items in the following figures, and therefore, once an item is defined in one figure, it need not be further discussed in subsequent figures.

[0100] The embodiments of the present disclosure can be applied to electronic devices such as terminal devices, computer systems, servers, etc., which can operate with many other general or special computing system environments or configurations. Examples of well-known terminal devices, computing systems, environments and / or configurations suitable for use with electronic devices such as terminal devices, computer systems, servers, etc. include, but are not limited to: personal computer systems, server computer systems, thin clients, thick clients, handheld or laptop devices, microprocessor-based systems, set-top boxes, programmable consumer electronics, network personal computers, small computer systems, large computer systems, and distributed cloud computing technology environments including any of the above systems, etc.

[0101] Electronic devices such as terminal devices, computer systems, servers, etc. can be described in the general context of computer system executable instructions (such as program modules) executed by computer systems. Generally, program modules can include routines, programs, object programs, components, logic, data structures, etc., which perform specific tasks or implement specific abstract data types. Computer systems / servers can be implemented in distributed cloud computing environments, where tasks are performed by remote processing devices linked through a communication network. In a distributed cloud computing environment, program modules can be located on local or remote computing system storage media including storage devices.

[0102] In the related art, when users generate images through generative models, they need to have clear ideas or design plans for the images they want to generate, clearly express the desired design elements, and convert them into clear text prompts that can be submitted to the generative model. This requires an in-depth understanding of professional knowledge such as art, design, and photography. Such a threshold limits the widespread application of image generation technology. For ordinary non-professional users, they usually lack the ability to design solutions. When there is a clear demand, it is difficult to imagine what design elements to use to express the image, and it is difficult to use the generative model to obtain good image generation effects. For example, a user wants to generate a Chinese-style game character, but may not think of using a text prompt "a warrior wearing gorgeous ancient armor, holding a long, jade-decorated sword in his hand, and the background is a magnificent traditional Chinese building with complex carvings and a quiet courtyard" to express the design elements he wants.

[0103] Figure 1 FIG. 1 is a flow chart of an embodiment of the image generation method disclosed in the present invention. Figure 1 As shown, the image generation method of this embodiment includes:

[0104] 102, obtaining an image generation task input by a user.

[0105] In the disclosed embodiment, the image generation task may also be referred to as the image generation purpose, which may be obtained from the image generation task message input by the user. For example, in a specific example, the user inputs the image generation task message "I want to make a library poster", and the image generation task message may be identified and the preset task keywords may be extracted to obtain the image generation task "library poster".

[0106] In addition, in a specific implementation, the user can directly input the image generation task message in text form, in which case the preset task keywords can be directly extracted from the text image generation task message to obtain the image generation task. Alternatively, the image generation task message in voice form can be input, in which case the voice image generation task message in voice form can be firstly voice recognized to obtain the voice recognition result text, and then the preset task keywords can be extracted from the voice recognition result text to obtain the image generation task.

[0107] The above are only examples of possible implementation methods, and the embodiments of the present disclosure do not limit the specific implementation method of the image generation task of obtaining user input.

[0108] 104 , output a demand prompt message, and obtain a demand reply message input by the user based on the demand prompt message.

[0109] The demand prompt message is used to prompt the user of the specific demand for the image to be generated. The user can reply to the specific demand by inputting a demand reply message based on the demand prompt message.

[0110] 106. Determine the image generation requirement based on the requirement reply message.

[0111] 108 , determining an image display scheme based on the above image generation requirement, and outputting description information of the image display scheme.

[0112] The image display scheme is the overall information or main design elements expressed by the image, which is used to determine the main visual content of the image.

[0113] 110 , in response to receiving a confirmation message from a user regarding the image display scheme, generating an image based on the image display scheme confirmed by the user, and outputting the image.

[0114] Optionally, in some of the implementations, operations 102-108 can be performed through a pre-trained language model, such as a large language model (LLM), and an image can be generated based on an image display scheme confirmed by a user through a pre-trained image generation model; or, operations 102-110 can be performed through an AI model (i.e., the entire image generation method flow is implemented), which is not limited in the embodiments of the present disclosure. In the following embodiments, unless otherwise specified, operations 102-108 are performed by a language model and images are generated by an image generation model as examples. The same is true for the specific implementation of the entire image generation method flow implemented through an AI model (which can be understood as including a language model and an image generation model), which will not be repeated.

[0115] In the disclosed embodiment, the language model can, through a lot of learning and training, be able to deeply understand each message input by the user in combination with the context of the interaction, accurately understand the image generation task input by the user, reply to the message based on the needs input by the user, accurately understand the image generation needs, the user's feedback on the image display plan, and the generated image; the language model can learn a lot of professional knowledge such as art, design and photography during the training stage, can determine the corresponding image display plan for various image generation needs, and through the training of a large amount of corpus, it has the ability to express and organize in natural language, and can express the explanatory information of the image display plan in natural language for the image display plan.

[0116] In the disclosed embodiment, the user can describe the image he wants to generate through natural language. The AI ​​model or language model will understand the task requirements input by the user and provide a set of preliminary image display solutions. After the user confirms, the image is generated based on the image display solution confirmed by the user. This is to generate the image according to the user's actual needs while understanding the user's needs, rather than simply relying on prompts input by the user to generate the image, so that the generated image is more in line with the user's actual needs.

[0117] Based on this embodiment, when the user only inputs an image generation task, the user can be guided to input a demand reply message by outputting a demand prompt message, thereby determining the image generation requirement of this image generation task, and then determining the corresponding image display plan based on the image generation requirement, and outputting the description information of the image display plan. After the user confirms the image display plan, the image is generated and output based on the image display plan confirmed by the user. During the entire image generation process, the user does not need to express clear ideas, design plans, and desired design elements for the desired image, and the user does not need to convert them into clear prompts that can be submitted to the model, and the image can be generated for the user, thereby improving the image generation efficiency and the user experience; the image generation task is determined based on the demand reply message input by the user The image generation needs are determined based on the corresponding image display plan to generate images. This is to generate images according to the actual needs of users while understanding the user needs, rather than simply relying on prompts input by users to generate images. This can make the generated images more in line with the expression effects desired by users, and help improve the quality and efficiency of image generation. Since users have clear ideas, design plans, and desired design elements for the desired images, and convert them into clear prompts that can be submitted to the model, they need to have an in-depth understanding of professional knowledge such as art, design, and photography. The embodiments of the present disclosure break through the usage restrictions for users who are not familiar with professional knowledge such as art, design, and photography, lower the usage threshold for image generation based on AI technology, and expand the application scope of image generation based on AI technology.

[0118] In actual implementation, different image generation tasks may have different image generation requirements, so corresponding output requirement prompt messages are required. For example, when the image generation task is a poster, the image generation requirements may need to clarify the project type (i.e., brand, event, website, social media, etc.), target audience (design goals, age, gender, interests, etc.), brand style (painting, illustrations, etc.), information content (message, feeling, etc.), etc.; when the image generation task is an avatar, the image generation requirements may need to clarify age, gender, face shape, hairstyle, decoration, color, etc.

[0119] Optionally, in some implementations, after obtaining the image generation task input by the user in operation 102, a requirement prompt message corresponding to the image generation task or a requirement prompt message for the image generation task may be determined. Accordingly, in operation 104, the requirement prompt message corresponding to the image generation task is output.

[0120] Optionally, in some of the implementations, the demand prompt message may include, for example, but is not limited to, any one or more of the following information related to the image generation task: task type, target audience, expression theme, style (i.e., presentation style), color, shooting angle, brightness effect, visual sense of expression, emotion of expression, information of expression, environment of expression, etc. The specific information of the demand prompt message needs to be determined according to the requirements of the image generation task, and the embodiments of the present disclosure do not limit the information specifically included in the demand prompt message.

[0121] In the disclosed embodiment, the language model learns a large amount of professional knowledge such as art, design, and photography during the training phase, and can determine the information that needs to be clarified for various image generation tasks, and generate corresponding requirement prompt messages so that users can provide requirement reply messages to determine the image generation requirements through the requirement reply messages.

[0122] In the disclosed embodiment, the language model can interact with the user in a conversational manner. After obtaining the user's image generation task, the language model will output a demand prompt message, for example, to whom the image is to be shown (i.e., the target audience), what theme and information the image wants to express (i.e., the expressed theme, the expressed information), what kind of visual feeling is hoped to be expressed (i.e., the expressed visual feeling), what style preference is there (i.e., style), etc. By conversing with the user, the language model can understand the user's needs based on the content of the conversation, that is, reply to the message based on the user's needs to determine the image generation needs.

[0123] Optionally, in some implementations, at least one image display scheme may be determined based on the above image generation requirements, and description information of the at least one image display scheme may be output in operation 108. Each image display scheme in the at least one image display scheme may include, but is not limited to, any one or more of the following scheme information: overall image description information, image theme, image presentation environment, main visual elements, presentation style, etc.

[0124] After determining the image generation requirements, the language model can use pre-learned professional knowledge such as art, design, and photography to determine the image display plan for this image generation task and image generation requirements, such as the overall description of the image, the theme of the image, the environment, the main visual elements used, the style characteristics of the presentation, etc., and use the pre-learned natural language expression and organization capabilities to generate and output the description information of the image display plan. If the user is satisfied with the image display plan, the image can be generated using the image display plan; if the user believes that the image display plan needs further improvement or optimization, the language model can continue to be guided to modify the image display plan through dialogue until the user is satisfied, and then the image display plan confirmed by the user is used to generate the image.

[0125] Accordingly, in operation 110, in response to receiving a confirmation message sent by the user for a target image display scheme in the above-mentioned at least one image display scheme, an image is generated based on the target image display scheme. The target image display scheme here is an image display scheme confirmed by the user in the above-mentioned at least one image display scheme. For example, the user can select an image display scheme from the above-mentioned at least one image display scheme as the image display scheme that he / she confirms to adopt, or the user can also enter the scheme identifier (ID) of an image display scheme that he / she confirms to adopt to clarify the image display scheme that he / she confirms to adopt, wherein each scheme ID is used to uniquely identify an image display scheme in the above-mentioned at least one image display scheme. In a specific implementation, the scheme ID can be the scheme number, scheme order, scheme title, and other information of an image display scheme in the above-mentioned at least one image display scheme, and the embodiments of the present disclosure are not limited to this.

[0126] Figure 2 FIG. 1 is a flow chart of another embodiment of the image generation method disclosed in the present invention. Figure 2 As shown, the image generation method of this embodiment includes:

[0127] 202, obtaining an image generation task input by a user.

[0128] 204 , output a demand prompt message, and obtain a demand reply message input by the user based on the demand prompt message.

[0129] 206 , determining the image generation requirement based on the requirement reply message.

[0130] 208 , determining at least one image display scheme based on the image generation requirement, and outputting description information of the at least one image display scheme.

[0131] In response to receiving a confirmation message sent by the user for the target image display scheme in the at least one image display scheme, the target image display scheme is used as the image display scheme confirmed by the user, and operation 210 is performed. Otherwise, in response to receiving a scheme modification message sent by the user for the target image display scheme in the at least one image display scheme, operation 212 is performed.

[0132] 210 , generating an image based on the image display scheme confirmed by the user, and outputting the image.

[0133] 212, obtaining the solution modification requirement in the solution modification message.

[0134] 214 , determining a modified image display scheme based on the target image display scheme and the scheme modification requirement, and outputting description information of the modified image display scheme.

[0135] In response to receiving a confirmation message sent by the user for the modified image display scheme, the modified image display scheme is used as the image display scheme confirmed by the user, and operation 210 is performed. Otherwise, in response to receiving a scheme modification message sent by the user for the modified image display scheme, operation 212 is iteratively performed.

[0136] In the disclosed embodiment, the language model can accurately understand the scheme modification requirements in the scheme modification message, and can use the professional knowledge of art, design, photography, etc. learned in the training phase to redetermine the modified image display scheme based on the target image display scheme and the scheme modification requirements.

[0137] In the disclosed embodiment, one or more image display schemes can be determined based on the image generation requirements. The user can directly select one from the at least one image display scheme as a confirmed image display scheme to generate an image, or can select an image display scheme from the at least one image display scheme to modify a message to express his or her modification opinion. The language model will modify the image display scheme selected by the user until the user is satisfied, and then the image display scheme confirmed by the user will be used to generate the image.

[0138] Figure 3 FIG. 1 is a flowchart of another embodiment of the image generation method disclosed in the present invention. Figure 3 As shown, based on any of the above-mentioned embodiments of the image generation method, generating an image based on the image display scheme confirmed by the user may include:

[0139] 302 , determining the details of the image display solution confirmed by the user, and outputting prompt words and description information of the details of the solution.

[0140] In response to receiving a confirmation message from the user regarding the solution details, operation 304 is performed.

[0141] Optionally, in some implementations, operation 302 may be performed by a language model.

[0142] 304 , generating an image based on the image display solution confirmed by the user and the solution details confirmed by the user.

[0143] Optionally, in some implementations, operation 304 may be performed by an image generation model.

[0144] When an image generation model generates an image, in order to improve the image generation quality, the text prompts submitted to the generation model require professional knowledge of art, design and photography. Ordinary users lack relevant professional knowledge and may not be able to give professional text prompts. In this way, even if the user thinks of a design plan, it is still difficult to obtain a more ideal image generation effect.

[0145] In this embodiment, the language model can learn a large amount of professional knowledge such as art, design, and photography during the training stage. After the user confirms the image display plan, the language model is further called to refine the image display plan confirmed by the user, determine the plan details based on the image display plan confirmed by the user, and output prompt words and description information of the plan details. The prompt words and description information include the expression of professional terms. For example, the description of the picture style in the description information of a plan detail is "digital illustration, using high contrast and bright colors to emphasize the exquisite design of armor and buildings". After the user confirms the plan details according to the prompt words and description information, the image generation model can be used to generate the image. In this way, the image generation quality can be effectively improved, so that the generated image is more in line with the expression effect desired by the user, thereby improving the image generation efficiency and user experience.

[0146] Optionally, in some of the implementations, the prompt words of the solution details may include, but are not limited to, any one or more of the following details and at least one attribute value of each detail: at least one solution refinement point and the implementation method of each solution refinement point, image shape, image size, image resolution, image direction, etc. The at least one solution refinement point may include, but are not limited to, any one or more of the following: expression theme, presentation style, color, shooting angle, brightness effect, expression visual feeling, expression information, expression environment, etc. The embodiments of the present disclosure do not limit the specific details, solution refinement points and other specific contents.

[0147] Accordingly, in operation 304, in response to receiving a confirmation message sent by the user regarding the target attribute values ​​of each detail determined based on at least one attribute value of each detail, the target attribute values ​​of each detail determined by the user are used as the scheme details confirmed by the user, and an image is generated based on the image display scheme confirmed by the user and the scheme details confirmed by the user.

[0148] Taking the scheme refinement key point as the presentation style as an example, the presentation style may include, but is not limited to: photography, painting, illustration, sculpture, artwork, paper product, 3D, etc. Accordingly, the implementation method of the scheme refinement key point is a detailed description of how the style is implemented, for example, when the presentation style is photography, the photography mode (such as macro, fisheye style, portrait, etc.), the camera model used, the camera settings, etc.; when the presentation style is painting, the materials and the working materials used are described in detail; when the presentation style is rendering, the engine settings used; when the presentation style is illustration, the type of illustration (such as digital illustration, etc.); when the presentation style is artwork, the material of the artwork (such as wooden artwork, etc.); and other information that may be defined as output type. Accordingly, the attribute value of the detail is the specific parameter value of the detail, for example, when the presentation style is photography, the specific parameter value of the photography mode (such as macro, fisheye style, portrait, etc.), the specific camera model used, the camera setting parameter value, etc.; when the presentation style is rendering, the specific parameter value of the engine setting used. The disclosed embodiment does not limit this.

[0149] The image shape, i.e., the shape that the image appears to be, may include, but is not limited to, horizontal, vertical, square, circular, horizontal elliptical, vertical elliptical, etc. The image size is the image size that is consistent with the image shape. Thus, suitable image shapes and image sizes can be recommended to users.

[0150] In a specific implementation, when the key points of the solution include a presentation style, the attribute value of the presentation style includes any one or more of the following: a text ID of the presentation style, and a style representative image. The text ID of the presentation style is the text name of the presentation style, such as photography, painting, illustration, etc. The style representative image is an image example of the presentation style, such as a specific photography example, painting example, illustration example, etc.

[0151] In the disclosed embodiment, after determining the solution details, multiple details and at least one attribute value thereof can be fed back to the user for the solution details. The user can select the attribute value he / she wants from at least one attribute value of each detail as the target attribute value of each detail. For each solution refinement point, the implementation method and attribute value of the solution refinement point he / she wants can be selected as the target attribute value of each detail determined by the user for generating an image. If there is only one attribute value for each solution refinement point and only one implementation method for each solution refinement point, the user does not need to select the attribute value and the implementation method of the solution refinement point, and can directly feed back a confirmation message.

[0152] Since the user's choice of presentation style depends to a certain extent on the observation of images of the style of this type of program rather than just imagination based on the dialogue, the disclosed embodiment can provide style representative images for various presentation styles through a human-computer interaction interface. The user can view the style representative images and select the presentation style he wants as the target presentation style, which helps the user to intuitively and quickly select the image style he wants, and helps to improve user-friendliness and image generation efficiency.

[0153] Figure 4 FIG. 1 is a flow chart of another embodiment of the image generation method disclosed in the present invention. Figure 4 As shown, based on any of the above-mentioned embodiments of the image generation method, generating an image based on the image display scheme confirmed by the user may include:

[0154] 402 , determining the details of the image display solution confirmed by the user, and outputting prompt words and description information of the details of the solution.

[0155] In response to receiving a confirmation message from the user regarding the solution details, operation 404 is performed. Otherwise, in response to receiving an adjustment message from the user regarding the solution details, operation 406 is performed.

[0156] 404 , generating an image based on the image display solution confirmed by the user and the solution details confirmed by the user.

[0157] 406: Obtain the adjustment requirement in the adjustment message.

[0158] 408 , determining adjusted solution details based on the solution details and adjustment requirements, and outputting prompt words and description information of the adjusted solution details.

[0159] In response to receiving a confirmation message sent by the user for the adjusted solution details, the adjusted solution details are used as the solution details confirmed by the user, and operation 404 is performed. Otherwise, in response to receiving an adjustment message sent by the user for the adjusted solution details, operation 406 is iteratively performed for the adjusted solution details.

[0160] In the disclosed embodiment, after determining the details of the scheme for the image display scheme confirmed by the user, the prompt words and description information of the scheme details can be output. After the user confirms the details of the scheme according to the prompt words and description information, the image can be generated by the image generation model. If the user is not satisfied with the details of the scheme, the details of the scheme can be further optimized by interacting with the language model in a conversational manner (for example, selecting a presentation style that he or she prefers) to make it more in line with his or her needs until the details of the scheme satisfying the user are obtained. Then, the image is generated by the image generation model based on the image display scheme confirmed by the user and the details of the scheme confirmed by the user. The conversational interaction allows the user to adjust the details of the scheme in real time and optimize the prompt words to guide the image generation model to generate images with more precise and professional language. As a result, the image generation quality can be effectively improved, so that the generated image is more in line with the expression effect desired by the user, thereby improving the image generation efficiency and the user experience.

[0161] Optionally, in some of the implementations, in operation 304 or 404, the solution information of the image display solution confirmed by the user and the prompt words of the solution details confirmed by the user can be input into the image generation model, so that the image generation model generates an image based on the solution information of the image display solution confirmed by the user and the prompt words of the solution details confirmed by the user, and receives the image output by the image generation model.

[0162] In this embodiment, after the user confirms the image display plan and plan details, the pre-trained image generation model can be called to fully utilize the deep learning capabilities of the image generation model to generate a corresponding image based on the plan information of the image display plan confirmed by the user and the prompt words of the plan details confirmed by the user, thereby improving the quality and efficiency of image generation.

[0163] In the disclosed embodiment, the image generation model may be trained in advance using a plurality of image generation samples, wherein each image generation sample includes solution information of an image display solution and prompt words for solution details.

[0164] In one implementation, a generative adversarial network (GAN) can be used to train an image generation model, wherein the generative adversarial network includes a generator and a discriminator. The scheme information and prompt words in each image generation sample are encoded into vectors and input into the generative adversarial network. The generator and the discriminator compete with each other. The generator generates images from random noise based on the input vector. The discriminator determines whether the image generated by the generator is true or false. The generator adapts to the feedback of the discriminator to learn and continuously improves the generated image. The discriminator becomes more accurate as the generator improves. Through the adversarial learning of the generator and the discriminator, the image generated by the generator is closer to reality. In the adversarial learning of the generator and the discriminator, the generator can use the diffusion technology to gradually add more details to the initially generated low-resolution sketch to make it close to the effect of the real image. Through this gradual diffusion process, the details of the image are enriched and more realistic. Through the mutual competition and adversarial learning of the generative adversarial network, it can be ensured that the refined image closely matches the scheme information and prompt words in each image generation sample, and the diffusion technology is used to gradually add more details to make the low-resolution sketch close to the effect of the real image.

[0165] After the generative adversarial network training is completed, the generator therein can be used as an image generation model to utilize the solution information of the image display solution and the prompt words of the solution details to generate an image that closely matches the solution information and the prompt words, has rich details, is more realistic, and is close to the real image effect.

[0166] Optionally, in some of the implementations, when the image generation model generates an image based on the scheme information of the image display scheme confirmed by the user and the prompt words of the scheme details confirmed by the user, the image can be directly generated based on the scheme information of the image display scheme confirmed by the user and the prompt words of the scheme details confirmed by the user; or the initial image can be first generated based on the image display scheme confirmed by the user, and then the initial image can be adjusted based on the prompt words of the scheme details confirmed by the user to obtain an optimized image. The embodiments of the present disclosure are not limited to this.

[0167] Optionally, in a specific implementation, when the image generation model generates an image based on the scheme information of the image display scheme confirmed by the user and the prompt words of the scheme details confirmed by the user, the image generation model can first preliminarily generate at least one preview image and display it to the user. After the user selects a preview image as the confirmed preview image, the preview image confirmed by the user is enhanced, for example, the image resolution is improved, the image is optimized in detail, etc., to improve the image quality of the final output. If the image generation model can preliminarily generate a preview image first, the user can directly determine whether to adopt the preview image. If the user is not satisfied with the preview image preliminarily generated, the image display scheme and the scheme details can be adjusted through the following embodiments to regenerate the preview image for the user, which can avoid the time-consuming direct generation of high-quality images, which leads to poor user examinations, and the computing resources and video memory resources consumed by directly generating high-quality images that the user is not satisfied with.

[0168] Figure 5 FIG. 1 is a flow chart of another embodiment of the image generation method disclosed in the present invention. Figure 5 As shown, based on any of the above-mentioned embodiments of the image generation method, after the image is generated, the following steps may also be included:

[0169] 502, display the image.

[0170] The image here may be one image or multiple images. If there are multiple images, the user can select one from the multiple images to send an output indication message or modify the message.

[0171] In response to receiving the output instruction message of the user for the image, the operation of outputting the image is performed. Otherwise, in response to receiving the first modification message of the user for the image, operation 504 is performed.

[0172] 504. Determine a first image modification scheme based on the first modification message, and output description information of the first image modification scheme.

[0173] Among them, the first image modification plan includes a modification plan for the image display plan and / or a modification plan for the plan details, that is, the first image modification plan can be a modification plan for the image display plan, or a modification plan for the plan details, or can also include a modification plan for the image display plan and / or a modification plan for the plan details at the same time. The specific modification plan is determined according to the content of the modification message sent by the user (that is, the modification requirements).

[0174] In response to receiving a confirmation message sent by the user for the first image modification solution, operation 506 is performed. Otherwise, in response to receiving a second modification message sent by the user for the image modification solution, operation 508 is performed. Here, the first modification message and the second modification message are only used to refer to different modification messages.

[0175] 506. Modify the image display scheme confirmed by the user and / or the scheme details confirmed by the user based on the first image modification scheme, and generate an image with the modified image display scheme and scheme details, that is, generate an image with the modified image display scheme and scheme details as the image display scheme confirmed by the user this time and the scheme details confirmed by the user.

[0176] Among them, the specific implementation method of generating an image with the modified image display scheme and scheme details can refer to the specific implementation of generating an image based on the image display scheme confirmed by the user and the scheme details confirmed by the user in the above-mentioned embodiment of the present disclosure, and will not be repeated here.

[0177] 508 , using the second modification message as a new first modification message, and iteratively executing operation 504 .

[0178] In this embodiment, after the image is generated, the image can be displayed (it can be a high-quality image generated directly or the preview image mentioned above). If the user is satisfied with the displayed image, an output instruction message for the image can be sent to output the image. If the image is a high-quality image directly generated by the image generation model, it can be directly output and downloaded, saved or forwarded by the user for other applications; if the image is a preview image initially generated by the image generation model, the preview image can be enhanced and then output and downloaded, saved or forwarded by the user for other applications. If the user is not satisfied with the displayed image, the image can be modified through natural language dialogue, which greatly improves the user experience.

[0179] Optionally, in the image generation method of any embodiment of the present disclosure, the image generation task may be a task text that requires image generation. Alternatively, the image generation task may also include a base image and a task text for the base image, where the base image is an image provided by a user and requires reference or processing.

[0180] Figure 6 FIG. 1 is a flow chart of another embodiment of the image generation method disclosed in the present invention. Figure 6 As shown, when the image generation task includes a basic image and a task text for the basic image, the image generation method of this embodiment includes:

[0181] 602, obtaining an image generation task input by a user.

[0182] The image generation task includes a base image and a task text for the base image. For example, the base image is a user's photo, and the task text for the base image is "generate an anime avatar".

[0183] Thereafter, operations 604 - 606 and operation 608 may be performed respectively.

[0184] 604 , output a demand prompt message, and obtain a demand reply message input by the user based on the demand prompt message.

[0185] 606 , determining the image generation requirement based on the requirement reply message.

[0186] 608, performing image recognition on the basic image to obtain an image recognition result.

[0187] The image recognition result may be an image recognition result associated with the task text. For example, if the task text of the base image is “generate an anime avatar”, then the image recognition result may be the user avatar and related information (such as position, pixel area, etc.) in the base image; if the task text of the base image is “add a bouquet of flowers on the table in the image”, then the image recognition result may be the table in the base image and related information (such as color, position, pixel area, etc.); and so on. The present disclosed embodiments do not limit this.

[0188] There is no restriction on the execution order between operations 604-606 and operation 608, and the two can be executed simultaneously, or in any sequence or any time difference, and the embodiment of the present disclosure does not impose any restriction on this.

[0189] 610 , determining an image display scheme based on the above-mentioned image generation requirement and image recognition result, and outputting description information of the image display scheme.

[0190] 612 , in response to receiving a confirmation message from the user regarding the image display scheme, generating an image based on the basic image and the image display scheme confirmed by the user, and outputting the image.

[0191] Based on this embodiment, multimodal data including images and texts can be processed to generate the image desired by the user based on the basic image provided by the user. For example, an animated avatar can be generated based on the real avatar provided by the user (as the basic image), and some elements can be added to the basic image provided by the user, or some elements can be replaced or removed, and so on.

[0192] The following uses a specific application example to further illustrate the image generation method of the embodiment of the present disclosure:

[0193] S11, the user inputs a task message through the human-computer interaction interface, for example: I want to make a library poster.

[0194] S12, the language model obtains the image generation task "library poster" input by the user based on the task message sent by the user, determines that the demand prompt message corresponding to the image generation task needs to include the project type, target audience, brand style, and information content, and outputs the demand prompt message to the user, for example: Hello, I am happy to help you. First, I need more specific information about your project. Can you provide the following details:

[0195] Project type: Is it for a brand, an event, a website, social media, or something else?

[0196] Target audience: Who is your design for? What is their age, gender, interests, etc.?

[0197] Brand Style: If you already have a brand style, can you describe it? Alternatively, do you have a favorite color or pattern?

[0198] Message content: What message or feeling do you want to convey in your design?

[0199] S13, the user inputs a demand reply message based on the demand prompt message: I want to make a library poster, the target audience is students, and the content is the last check-in activity before graduation.

[0200] S14, the language model determines the image generation requirement based on the above requirement reply message, determines the image display scheme based on the image generation requirement, and outputs description information of the image display scheme, for example:

[0201] Great, here is a basic library poster image display solution I created for you:

[0202] Graphic elements: An abstract library illustration can be designed to look like a pile of books, creating an interesting and academic visual focal point. Below the illustration, a capitalized title can be placed, such as "The last time to check in, let knowledge leave a mark", to highlight the importance of the activity.

[0203] Text elements: In the center of the poster, you can write specific information about the event, including the date, time, and location. To make it easy to read, choose a clear, easy-to-read font, such as a sans serif font. Choose a dark color for the font (such as navy or black) so that it is clearly visible on a light background.

[0204] S15, the user inputs a confirmation message through the human-computer interaction interface, for example: OK, let’s use this solution, please add a style.

[0205] S16, the language model determines the solution details according to the image display solution confirmed by the user, and outputs prompt words and description information of the solution details.

[0206] Among them, prompt words, such as: presentation style, art illustration; image shape, vertical; image size, A2.

[0207] Description information, such as:

[0208] Great, let’s set the visual style of this design scheme to a unique artistic illustration style, which will help your poster stand out from many other posters. This style can bring a creative and artistic visual effect.

[0209] Design style: Art illustration. We can use an art illustration style to design the image of the library. Stack the books to form a creative and eye-catching shape. This shape can be a giant graduation cap or a diploma, which will represent graduation and remind students that this is their last chance to check in at the library. In addition, art illustration allows you to use colors more freely, making the poster more attractive.

[0210] Posters are usually oriented vertically, so we will design a vertical poster. A common poster size is A2 size (420mm × 594mm), which should be large enough to make the poster look clear and crisp from a distance. At the same time, this size can also be easily reduced to A3 or A4 size to suit different printing needs.

[0211] S17, the user inputs a confirmation message through the human-computer interaction interface, for example: Very good, please help me generate it.

[0212] S18, the language model inputs the solution information of the image display solution confirmed by the user and the prompt words of the solution details confirmed by the user into the image generation model.

[0213] S19, the image generation model generates an image based on the solution information of the image display solution confirmed by the user and the prompt words of the solution details confirmed by the user, and displays the generated image through the human-computer interaction interface.

[0214] S20, the user inputs a first modification message for the image through the human-computer interaction interface, for example: I hope it will be more sunny.

[0215] In the disclosed embodiments, the language model can, through extensive learning and training, gain an in-depth understanding of each message input by the user in combination with the context of the interaction, accurately understand the user's needs, and can utilize the professional knowledge such as art, design, and photography learned during the training phase to determine corresponding solutions that meet the user's needs.

[0216] S21, the language model determines a first image modification scheme based on the first modification message, including a modification scheme of the image display scheme and a modification scheme of scheme details, and outputs description information of the first image modification scheme, for example:

[0217] Of course, let's adjust the design to a brighter and more sunny style. This will help create a more vibrant and enthusiastic atmosphere and spark students' enthusiasm for the graduation card event. Here are some modification suggestions:

[0218] 1. Color selection: We can use brighter tones to brighten the design. For example, adjust the background color from soft yellow and orange to brighter and more lively yellow and orange. At the same time, the book colors in the illustrations can also use brighter colors, such as bright blue, bright green, etc., to increase vitality and visual impact.

[0219] 2. Graphic elements: Adjust our library illustration to be more light and lively. We could design the books to look like they are flying, or bursting out of graduation caps, creating a celebratory visual effect.

[0220] 3. Picture elements: If possible, use some sunny library photos. For example, some students reading books in the sun, or the appearance of the library in bright sunshine. These pictures can bring a pleasant and positive feeling to people and enhance the brightness of the overall design.

[0221] S22, the user inputs a confirmation message for the first image modification scheme through the human-computer interaction interface, for example: Very good, help me generate it.

[0222] S23, the language model modifies the image display scheme confirmed by the above user and / or the scheme details confirmed by the above user based on the first image modification scheme, obtains the modified image display scheme and scheme details, and inputs the scheme information of the modified image display scheme and the prompt words of the scheme details into the image generation model.

[0223] S24, generating an image of the scheme information of the modified image display scheme and the prompt words of the scheme details, and displaying the generated image through the human-computer interaction interface.

[0224] S25, the user enters a confirmation message for the image (for example: I am satisfied) through the human-computer interaction interface; or saves the image; or shares the image with friends in the application or with a third-party application, etc.

[0225] Any image generation method provided in the embodiments of the present disclosure may be executed by any appropriate device with data processing capabilities, including but not limited to: a terminal device and a server, etc. Alternatively, any image generation method provided in the embodiments of the present disclosure may be executed by a processor, such as the processor executing any image generation method mentioned in the embodiments of the present disclosure by calling corresponding instructions stored in a memory. This will not be described in detail below.

[0226] A person of ordinary skill in the art can understand that all or part of the steps of implementing the above method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiment; and the aforementioned storage medium includes: ROM, RAM, magnetic disk or optical disk, etc., various media that can store program codes.

[0227] Figure 7 FIG. 1 is a schematic diagram of the structure of an embodiment of the image generation device of the present disclosure. The image generation device of this embodiment can be used to implement the above-mentioned various image generation method embodiments of the present disclosure. Figure 7 As shown, the image generation device of this embodiment includes: an acquisition module 702, an output module 704, a first determination module 706, a second determination module 708 and an image generation module 710. Among them:

[0228] The acquisition module 702 is used to acquire the image generation task input by the user.

[0229] The output module 704 is used to output the demand prompt message.

[0230] The acquisition module 702 is further used to acquire a demand reply message input by the user based on the demand prompt message.

[0231] The first determining module 706 is configured to determine an image generation requirement based on the requirement reply message.

[0232] The second determination module 708 is used to determine an image display solution based on the image generation requirement.

[0233] The output module 704 is also used to output description information of the image display solution.

[0234] The acquisition module 702 is further used to receive a confirmation message from the user regarding the image display solution.

[0235] The image generation module 710 is configured to generate an image based on the image display solution confirmed by the user in response to the acquisition module 702 receiving a confirmation message of the user regarding the image display solution.

[0236] The output module 704 is also used to output images.

[0237] Based on this embodiment, when the user only inputs the image generation task, the user can be guided to input the requirement reply message by outputting the requirement prompt message, thereby determining the image generation requirement of this image generation task, and then determining the corresponding image display plan based on the image generation requirement, and outputting the description information of the image display plan. After the user confirms the image display plan, the image is generated and output based on the image display plan confirmed by the user. During the entire image generation process, the user does not need to express clear ideas, design plans, and desired design elements for the desired image and convert them into clear prompts that can be submitted to the model, and the image can be generated for the user, thereby improving the image generation efficiency and the user experience. The image of this image generation task is determined based on the requirement reply message input by the user. Generate needs, thereby determining the corresponding image display plan to generate images, is to generate images according to the actual needs of users under the condition of understanding user needs, rather than simply relying on prompts input by users to generate images, which can make the generated images more in line with the expression effects desired by users, and help improve the quality and efficiency of image generation; because users have clear ideas, design plans, and desired design elements for the desired images, and convert them into clear prompts that can be submitted to the model, they need to have an in-depth understanding of professional knowledge such as art, design and photography. The embodiments of the present disclosure break through the usage restrictions of users who are not familiar with professional knowledge such as art, design and photography, lower the usage threshold of image generation based on AI technology, and expand the application scope of image generation based on AI technology.

[0238] Figure 8 FIG. 1 is a schematic diagram of the structure of another embodiment of the image generating device disclosed in the present invention. Figure 8 As shown, in Figure 7 Based on the embodiment shown, the image generation device of this embodiment further includes: a third determination module 712, which is used to determine the requirement prompt message corresponding to the image generation task. Accordingly, the output module 704 is specifically used to output the requirement prompt message corresponding to the image generation task.

[0239] Optionally, in some of the implementations, the demand prompt message may include, for example, but is not limited to, any one or more of the following information related to the image generation task: task type, target audience, expression theme, style (i.e., presentation style), color, shooting angle, brightness effect, visual sense of expression, emotion of expression, information of expression, environment of expression, etc. The specific information of the demand prompt message needs to be determined according to the requirements of the image generation task, and the embodiments of the present disclosure do not limit the information specifically included in the demand prompt message.

[0240] Optionally, in some of the implementations, the second determination module 708 is specifically used to determine at least one image display scheme based on the image generation requirements, and each image display scheme in the at least one image display scheme may include, but is not limited to, any one or more of the following scheme information: overall image description information, image theme, image presentation environment, main visual elements, presentation style, etc. Correspondingly, the output module 704 is specifically used to output the description information of at least one image display scheme. The image generation module 710 is specifically used to generate an image based on the target image display scheme in response to the acquisition module 702 receiving a confirmation message sent by the user for the target image display scheme in the at least one image display scheme.

[0241] Optionally, in another embodiment of the image generating device disclosed herein, the acquisition module 702 may also be used to, in response to receiving a scheme modification message sent by a user for a target image display scheme in at least one image display scheme, acquire a scheme modification requirement in the scheme modification message; determine a modified image display scheme based on the target image display scheme and the scheme modification requirement, and output description information of the modified image display scheme through the output module 704; in response to receiving a confirmation message sent by a user for the modified image display scheme, use the modified image display scheme as the image display scheme confirmed by the user, instruct the image generating module 710 to generate an image based on the image display scheme confirmed by the user, and output the image through the output module 704; in response to receiving a scheme modification message sent by a user for the modified image display scheme, replace the target image display scheme with the modified image display scheme, and iteratively execute the operation of acquiring the scheme modification requirement in the scheme modification message.

[0242] Optionally, in some of the implementations, when the acquisition module 702, in response to receiving a user confirmation message for the image display scheme, instructs the image generation module 710 to generate an image based on the image display scheme confirmed by the user, it is specifically used to: in response to receiving a user confirmation message for the image display scheme, determine the scheme details for the image display scheme confirmed by the user, and output prompt words and explanatory information of the scheme details; in response to receiving a user confirmation message for the scheme details, instruct the image generation module 710 to generate an image based on the image display scheme confirmed by the user and the scheme details confirmed by the user.

[0243] Optionally, in some of the implementations, the prompt words of the above-mentioned solution details may include, for example, but are not limited to, any one or more of the following details and at least one attribute value of each detail: solution refinement points and implementation methods of solution refinement points, image shape, image size, image resolution, image direction, etc. When the acquisition module 702 instructs the image generation module 710 to generate an image based on the image display solution confirmed by the user and the solution details confirmed by the user in response to receiving a confirmation message for the solution details from the user, it is specifically used to: in response to receiving a confirmation message sent by the user in which the target attribute value of each detail is determined based on at least one attribute value of each detail, use the determined target attribute value of each detail as the solution details confirmed by the user, and instruct the image generation module 710 to generate an image based on the image display solution confirmed by the user and the solution details confirmed by the user.

[0244] Optionally, in some of the implementations, when the solution refinement points include a presentation style, the attribute value of the presentation style may include a text identifier of the presentation style and / or a style representative image.

[0245] Optionally, in other implementations, when the acquisition module 702, in response to receiving a user confirmation message for the image display scheme, instructs the image generation module 710 to generate an image based on the image display scheme confirmed by the user, it is specifically used to: in response to receiving an adjustment message sent by the user for the scheme details, acquire the adjustment requirements in the adjustment message; determine the adjusted scheme details based on the scheme details and the adjustment requirements, and output prompt words and explanatory information of the adjusted scheme details; in response to receiving a confirmation message sent by the user for the adjusted scheme details, use the adjusted scheme details as the scheme details confirmed by the user, instruct the image generation module 710 to generate an image based on the image display scheme confirmed by the user and the scheme details confirmed by the user, and output the image through the output module 704; in response to receiving an adjustment message sent by the user for the adjusted scheme details, iteratively execute the operation of acquiring the adjustment requirements in the adjustment message for the adjusted scheme details.

[0246] Optionally, in some of the implementations, the image generation module 710 is specifically an image generation model, and when the acquisition module 702 instructs the image generation module 710 to generate an image based on the image display scheme confirmed by the user and the scheme details confirmed by the user, it is specifically used to: input the scheme information of the image display scheme confirmed by the user and the prompt words of the scheme details confirmed by the user into the image generation model, so that the image generation model generates an image based on the scheme information of the image display scheme confirmed by the user and the prompt words of the scheme details confirmed by the user; and receive the image output by the image generation model.

[0247] Optionally, in some of the implementations, the image generation model is specifically used to: generate an initial image based on the image display solution confirmed by the user, and adjust the initial image based on prompt words of the solution details confirmed by the user to obtain an optimized image.

[0248] Optionally, see Figure 8 In another embodiment of the image generation device disclosed in the present invention, it may further include: a display module 714, which is used to display an image. Accordingly, the output module 704 is specifically used to output an image in response to the acquisition module 702 receiving an output instruction message from the user for the image displayed by the display module 714. The acquisition module 702 is also used to: in response to receiving a first modification message from the user for the image, determine a first image modification scheme based on the first modification message, the first image modification scheme including a modification scheme of the image display scheme and / or a modification scheme of the scheme details, and output the description information of the first image modification scheme through the output module 704; in response to receiving a confirmation message sent by the user for the first image modification scheme, modify the image display scheme confirmed by the user and / or the scheme details confirmed by the user based on the first image modification scheme, and instruct the image generation module 710 to generate an image with the modified image display scheme and scheme details; in response to receiving a second modification message sent by the user for the image modification scheme, use the second modification message as a new first modification message, and iteratively perform the operation of determining the first image modification scheme based on the first modification message.

[0249] Optionally, in some implementations, the above-mentioned image generation task includes a task text for generating an image.

[0250] Optionally, in some other implementations, the above-mentioned image generation task includes: a basic image and a task text for the basic image. Accordingly, the image generation device in the above-mentioned embodiment may also include: an image recognition module 716, which is used to perform image recognition on the basic image to obtain an image recognition result. An acquisition module 702 is specifically used to determine an image display scheme based on image generation requirements and image recognition results. An image generation module 710 is specifically used to generate an image based on the basic image and the image display scheme confirmed by the user.

[0251] Fig. 9 FIG. 2 is a schematic diagram of the structure of another embodiment of the image generating device of the present disclosure. The image generating device of this embodiment can be used to implement the above-mentioned various image generating method embodiments of the present disclosure. Fig. 9 As shown, the image generation device of this embodiment includes: an interaction module 802, a language model 804 and an image generation model 806. Among them:

[0252] The interaction module 802 is used to obtain the image generation task input by the user, and call the language model 804 to determine the requirement prompt message corresponding to the image generation task, and output the requirement prompt message; obtain the requirement reply message input by the user based on the requirement prompt message, and call the language model 804 to determine the image generation requirement based on the requirement reply message, and determine the image display plan and the description information of the image display plan based on the image generation requirement, and output the description information of the image display plan; in response to receiving the user's confirmation message for the image display plan, call the image generation model 806 to generate an image based on the image display plan confirmed by the user, and output the image.

[0253] The language model 804 is used to determine the requirement prompt message corresponding to the image generation task, determine the image generation requirement based on the requirement reply message, and determine the image display scheme and the description information of the image display scheme based on the image generation requirement.

[0254] The image generation model 806 is used to generate an image based on the image display solution confirmed by the user.

[0255] Based on this embodiment, when the user only inputs the image generation task, the user can be guided to input the requirement reply message by outputting the requirement prompt message, thereby determining the image generation requirement of this image generation task, and then determining the corresponding image display plan based on the image generation requirement, and outputting the description information of the image display plan. After the user confirms the image display plan, the image is generated and output based on the image display plan confirmed by the user. During the entire image generation process, the user does not need to express clear ideas, design plans, and desired design elements for the desired image and convert them into clear prompts that can be submitted to the model, and the image can be generated for the user, thereby improving the image generation efficiency and the user experience. The image of this image generation task is determined based on the requirement reply message input by the user. Generate needs, thereby determining the corresponding image display plan to generate images, is to generate images according to the actual needs of users under the condition of understanding user needs, rather than simply relying on prompts input by users to generate images, which can make the generated images more in line with the expression effects desired by users, and help improve the quality and efficiency of image generation; because users have clear ideas, design plans, and desired design elements for the desired images, and convert them into clear prompts that can be submitted to the model, they need to have an in-depth understanding of professional knowledge such as art, design and photography. The embodiments of the present disclosure break through the usage restrictions of users who are not familiar with professional knowledge such as art, design and photography, lower the usage threshold of image generation based on AI technology, and expand the application scope of image generation based on AI technology.

[0256] Optionally, in some implementations, the language model 804 is further used to determine a requirement prompt message corresponding to the image generation task. Accordingly, the interaction module 802 is specifically used to output the requirement prompt message corresponding to the image generation task.

[0257] Optionally, in some of the implementations, the demand prompt message may include, for example, but is not limited to, any one or more of the following information related to the image generation task: task type, target audience, expression theme, style (i.e., presentation style), color, shooting angle, brightness effect, visual sense of expression, emotion of expression, information of expression, environment of expression, etc. The specific information of the demand prompt message needs to be determined according to the requirements of the image generation task, and the embodiments of the present disclosure do not limit the information specifically included in the demand prompt message.

[0258] Optionally, in some of the implementations, the language model 804 is specifically used to determine at least one image display scheme based on image generation requirements, and each image display scheme in the at least one image display scheme may include, but is not limited to, any one or more of the following scheme information: overall image description information, image theme, image presentation environment, main visual elements, presentation style. Accordingly, the interaction module 802 is specifically used to output description information of at least one image display scheme, and receive a confirmation message sent by the user for a target image display scheme in at least one image display scheme. The image generation model 806 is specifically used to generate an image based on the target image display scheme.

[0259] Optionally, in some of the implementations, the interaction module 802 is also used to receive a scheme modification message sent by a user for a target image display scheme in at least one image display scheme. Accordingly, the language model 804 is also used to obtain the scheme modification requirements in the scheme modification message, determine the modified image display scheme based on the target image display scheme and the scheme modification requirements, and output the description information of the modified image display scheme through the interaction module 802; the interaction module 802 is also used to receive a confirmation message sent by the user for the modified image display scheme. Accordingly, the language model 804 is specifically used to use the modified image display scheme as the image display scheme confirmed by the user, instruct the image generation model 806 to generate an image based on the image display scheme confirmed by the user, and output the image through the interaction module 802; in response to the interaction module 802 receiving the scheme modification message sent by the user for the modified image display scheme, the target image display scheme is replaced with the modified image display scheme, and the operation of obtaining the scheme modification requirements in the scheme modification message is iteratively performed.

[0260] Optionally, in some of the implementations, in response to the interaction module 802 receiving a user confirmation message for an image display plan, the language model 804 determines plan details for the image display plan confirmed by the user, and outputs prompt words and explanatory information for the plan details; in response to the interaction module 802 receiving a user confirmation message for the plan details, the image generation model 806 is instructed to generate an image based on the image display plan confirmed by the user and the plan details confirmed by the user.

[0261] Optionally, in some implementations, the prompt words of the above solution details may include, for example, but are not limited to, any one or more of the following details and at least one attribute value of each detail: solution refinement points and implementation methods of solution refinement points, image shape, image size, image resolution, image direction, etc. Wherein, when the solution refinement points include presentation style, the attribute value of the presentation style may include a text mark of the presentation style and / or a style representative image.

[0262] The language model 804 is specifically used to: in response to the interaction module 802 receiving a confirmation message sent by the user regarding the target attribute value of each detail determined based on at least one attribute value of each detail, use the determined target attribute value of each detail as the solution details confirmed by the user, and instruct the image generation model 806 to generate an image based on the image display solution confirmed by the user and the solution details confirmed by the user.

[0263] Optionally, the language model 804 can also be used to: in response to the interaction module 802 receiving an adjustment message sent by the user for the solution details, obtain the adjustment requirements in the adjustment message; determine the adjusted solution details based on the solution details and the adjustment requirements, and output the prompt words and description information of the adjusted solution details through the interaction module 802; in response to the interaction module 802 receiving a confirmation message sent by the user for the adjusted solution details, use the adjusted solution details as the solution details confirmed by the user, instruct the image generation model 806 to generate an image based on the image display solution confirmed by the user and the solution details confirmed by the user, and output the image through the interaction module 802; in response to the interaction module 802 receiving an adjustment message sent by the user for the adjusted solution details, iteratively execute the operation of obtaining the adjustment requirements in the adjustment message for the adjusted solution details.

[0264] Optionally, in some of the implementations, the language model 804 is specifically used to input the solution information of the image display solution confirmed by the user and the prompt words of the solution details confirmed by the user into the image generation model 806, so that the image generation model 806 generates an image based on the solution information of the image display solution confirmed by the user and the prompt words of the solution details confirmed by the user; the interaction module 802 is specifically used to receive the image output by the image generation model 806.

[0265] Optionally, in some implementations, the image generation model 806 is specifically configured to generate an initial image based on the image display solution confirmed by the user, and adjust the initial image based on prompt words of the solution details confirmed by the user to obtain an optimized image.

[0266] Optionally, in some of the implementations, the interaction module 802 is further used to display an image; and in response to receiving an output indication message from a user for an image, output an image; and receive a first modification message from a user for an image; accordingly, the language model 804 is further used to determine a first image modification scheme based on the first modification message, the first image modification scheme including a modification scheme of an image display scheme and / or a modification scheme of scheme details, and the interaction module 802 outputs description information of the first image modification scheme. The interaction module 802 is further used to receive a confirmation message sent by a user for the first image modification scheme; accordingly, the language model 804 is further used to modify the image display scheme confirmed by the user and / or the scheme details confirmed by the user based on the first image modification scheme, and instruct the image generation model 806 to generate an image with the modified image display scheme and scheme details. The interaction module 802 is further used to receive a second modification message sent by a user for the image modification scheme; accordingly, the language model 804 is further used to iteratively perform the operation of determining the first image modification scheme based on the first modification message using the second modification message as a new first modification message.

[0267] Optionally, in some implementations, the above-mentioned image generation task includes a task text for generating an image.

[0268] Optionally, in some other implementations, the above-mentioned image generation task includes a basic image and a task text for the basic image. Fig.10 FIG. 1 is a schematic diagram of the structure of another embodiment of the image generating device disclosed in the present invention. Fig.10 As shown, in Fig. 9 Based on the embodiment shown, the image generation device of this embodiment further includes: an image recognition module 808, which is used to perform image recognition on the basic image in the image generation task to obtain an image recognition result. Accordingly, the language model 804 is specifically used to determine the image display scheme based on the image generation requirement and the image recognition result; the image generation model 806 is specifically used to generate an image based on the basic image and the image display scheme confirmed by the user.

[0269] The image generating device and the image generating method of the embodiments of the present disclosure correspond to each other in terms of specific implementations, and the corresponding contents can be referenced to each other and will not be described in detail.

[0270] In addition, an embodiment of the present disclosure further provides an electronic device, including:

[0271] Memory for storing computer programs;

[0272] The processor is used to execute the computer program stored in the memory, and when the computer program is executed, the image generation method described in any of the above embodiments of the present disclosure is implemented.

[0273] Fig.11 This is a schematic diagram of the structure of an application embodiment of the electronic device disclosed in the present invention. Fig.11 The electronic device according to the embodiment of the present disclosure is described. The electronic device may be any one or both of the first device and the second device, or a stand-alone device independent of them, and the stand-alone device may communicate with the first device and the second device to receive the collected input signals from them.

[0274] like Fig.11 As shown, the electronic device includes one or more processors and memory.

[0275] The processor may be a central processing unit (CPU) or other forms of processing units having data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device to perform desired functions.

[0276] The memory may store one or more computer program products, and the memory may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, a random access memory (RAM) and / or a cache memory (cache), etc. The non-volatile memory may include, for example, a read-only memory (ROM), a hard disk, a flash memory, etc. One or more computer program products may be stored on the computer-readable storage medium, and the processor may run the computer program product to implement the image generation method of each embodiment of the present disclosure described above and / or other desired functions.

[0277] In one example, the electronic device may further include: an input device and an output device, and these components are interconnected via a bus system and / or other forms of connection mechanisms (not shown).

[0278] In addition, the input device may also include, for example, a keyboard, a mouse, and the like.

[0279] The output device can output various information to the outside, including determined distance information, direction information, etc. The output device can include, for example, a display, a speaker, a printer, a communication network and a remote output device connected thereto, and the like.

[0280] Of course, to simplify, Fig.11Only some of the components related to the present disclosure in the electronic device are shown, and components such as a bus, an input / output interface, etc. are omitted. In addition, according to specific application situations, the electronic device may further include any other appropriate components.

[0281] In addition to the above-mentioned methods and devices, an embodiment of the present disclosure may also be a computer program product, which includes computer program instructions, which, when executed by a processor, enable the processor to execute the steps of the image generation method according to various embodiments of the present disclosure described in the above part of this specification.

[0282] The computer program product may be written in any combination of one or more programming languages ​​to write program code for performing the operations of the disclosed embodiments, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0283] In addition, an embodiment of the present disclosure may also be a computer-readable storage medium having computer program instructions stored thereon, which, when executed by a processor, enables the processor to execute the steps of the image generation method according to various embodiments of the present disclosure described in the above part of this specification.

[0284] The computer readable storage medium can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can include, for example, but is not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0285] The basic principles of the present disclosure are described above in conjunction with specific embodiments. However, it should be noted that the advantages, strengths, effects, etc. mentioned in the present disclosure are only examples and not limitations, and it cannot be considered that these advantages, strengths, effects, etc. are required by each embodiment of the present disclosure. In addition, the specific details disclosed above are only for the purpose of illustration and ease of understanding, and are not limitations. The above details do not limit the present disclosure to the necessity of adopting the above specific details to be implemented.

[0286] Each embodiment in this specification is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the system embodiment, since it basically corresponds to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0287] The block diagrams of the devices, apparatuses, equipment, and systems involved in this disclosure are only illustrative examples and are not intended to require or imply that they must be connected, arranged, and configured in the manner shown in the block diagrams. As will be appreciated by those skilled in the art, these devices, apparatuses, equipment, and systems can be connected, arranged, and configured in any manner. Words such as "including," "comprising," "having," and the like are open words, referring to "including but not limited to," and can be used interchangeably therewith. The words "or" and "and" used herein refer to the words "and / or," and can be used interchangeably therewith, unless the context clearly indicates otherwise. The word "such as" used herein refers to the phrase "such as but not limited to," and can be used interchangeably therewith.

[0288] The method and apparatus of the present disclosure may be implemented in many ways. For example, the method and apparatus of the present disclosure may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above order of steps for the method is for illustration only, and the steps of the method of the present disclosure are not limited to the order specifically described above, unless otherwise specifically stated. In addition, in some embodiments, the present disclosure may also be implemented as a program recorded in a recording medium, which includes machine-readable instructions for implementing the method according to the present disclosure. Therefore, the present disclosure also covers a recording medium storing a program for executing the method according to the present disclosure.

[0289] It should also be noted that in the apparatus, device and method of the present disclosure, each component or each step can be decomposed and / or recombined. Such decomposition and / or recombination should be regarded as equivalent solutions of the present disclosure.

[0290] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present disclosure. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of the present disclosure. Therefore, the present disclosure is not intended to be limited to the aspects shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

[0291] The above description has been given for the purpose of illustration and description. In addition, this description is not intended to limit the embodiments of the present disclosure to the forms disclosed herein. Although multiple example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, changes, additions and sub-combinations thereof.

Claims

1. A method for generating an image, comprising: Get the image generation task input by the user; Output a demand prompt message according to the image generation task, and obtain a demand reply message input by the user based on the demand prompt message; wherein the demand prompt message is used to prompt the user of the specific demand for the image to be generated, and the demand prompt message includes any one or more of the following information involved in the image generation task: task type, target audience, expression theme, style, color, shooting angle, brightness effect, expression visual feeling, expression emotion, expression information, and expression environment; Determining an image generation requirement based on the requirement reply message; Determine an image display scheme based on the image generation requirement, and output description information of the image display scheme, where the image display scheme is the overall information or main design elements expressed by the image; In response to receiving a modification message from a user on the image display scheme, modifying and outputting the image display scheme and description information of the image display scheme; In response to receiving a confirmation message from a user regarding the image display scheme, generating an image based on the image display scheme confirmed by the user, and outputting the image; In response to receiving a confirmation message from a user regarding the image display scheme, generating an image based on the image display scheme confirmed by the user includes: In response to receiving a confirmation message from the user on the image display scheme, determining scheme details for the image display scheme confirmed by the user, and outputting prompt words and description information of the scheme details, wherein the prompt words of the scheme details include any one or more of the following details and at least one attribute value of each detail: scheme refinement points and implementation methods of the scheme refinement points, image shape, image size, image resolution, and image direction; In response to receiving a confirmation message of the solution details from the user, an image is generated based on the image presentation solution confirmed by the user and the solution details confirmed by the user.

2. The method according to claim 1, wherein: After obtaining the image generation task of user input, it also includes: Determine a requirement prompt message corresponding to the image generation task; Output demand prompt messages, including: Output a requirement prompt message corresponding to the image generation task.

3. The method according to claim 1, wherein: Determining an image display scheme based on the image generation requirement and outputting description information of the image display scheme includes: Determine at least one image display scheme based on the image generation requirement, and output description information of the at least one image display scheme, wherein each image display scheme in the at least one image display scheme includes any one or more of the following scheme information: overall image description information, image theme, image presentation environment, main visual elements, and presentation style; In response to receiving a confirmation message from a user regarding the image display scheme, generating an image based on the image display scheme confirmed by the user, including: In response to receiving a confirmation message sent by a user for a target image presentation scheme among the at least one image presentation scheme, an image is generated based on the target image presentation scheme.

4. The method according to claim 3, wherein: In response to receiving a modification message of the image display scheme from a user, modifying and outputting the image display scheme and description information of the image display scheme, including: In response to receiving a scheme modification message sent by a user for a target image display scheme in the at least one image display scheme, obtaining a scheme modification requirement in the scheme modification message; Determining a modified image display scheme based on the target image display scheme and the scheme modification requirement, and outputting description information of the modified image display scheme; The method further comprises: In response to receiving a confirmation message sent by the user for the modified image display scheme, taking the modified image display scheme as the image display scheme confirmed by the user, performing the operation of generating an image based on the image display scheme confirmed by the user, and outputting the image; In response to receiving a scheme modification message sent by a user for the modified image display scheme, the target image display scheme is replaced with the modified image display scheme, and the operation of obtaining the scheme modification requirement in the scheme modification message is iteratively performed.

5. The method according to any one of claims 1 to 4, wherein: In response to receiving a confirmation message of the solution details from the user, generating an image based on the image display solution confirmed by the user and the solution details confirmed by the user, including: In response to receiving a confirmation message sent by a user regarding a target attribute value for each detail determined based on at least one attribute value of each detail, the determined target attribute value for each detail is used as the solution details confirmed by the user, and an image is generated based on the image display solution confirmed by the user and the solution details confirmed by the user.

6. The method according to claim 5, wherein: When the scheme refinement key points include a presentation style, the attribute value of the presentation style includes at least one of a text identifier of the presentation style and a style representative image.

7. The method according to any one of claims 1 to 4, wherein: In response to receiving a confirmation message from a user regarding the image display scheme, generating an image based on the image display scheme confirmed by the user, further comprising: In response to receiving an adjustment message sent by a user for the solution details, obtaining an adjustment requirement in the adjustment message; Determine adjusted plan details based on the plan details and the adjustment requirements, and output prompt words and description information of the adjusted plan details; In response to receiving a confirmation message sent by the user regarding the adjusted solution details, taking the adjusted solution details as the solution details confirmed by the user, performing the operation of generating an image based on the image display solution confirmed by the user and the solution details confirmed by the user, and outputting the image; In response to receiving an adjustment message sent by a user for the adjusted solution details, the operation of obtaining the adjustment requirements in the adjustment message is iteratively performed for the adjusted solution details.

8. The method according to any one of claims 1 to 4, wherein: Generate an image based on the image display scheme confirmed by the user and the scheme details confirmed by the user, including: Inputting scheme information of the image display scheme confirmed by the user and prompt words of scheme details confirmed by the user into an image generation model, so that the image generation model generates an image based on the scheme information of the image display scheme confirmed by the user and the prompt words of scheme details confirmed by the user; An image output by the image generation model is received.

9. The method according to claim 8, wherein: The image generation model generates an image based on the solution information of the image display solution confirmed by the user and the prompt words of the solution details confirmed by the user, including: The image generation model generates an initial image based on the image display scheme confirmed by the user, and adjusts the initial image based on the prompt words of the scheme details confirmed by the user to obtain an optimized image.

10. The method according to any one of claims 1 to 4, wherein: After the image is generated based on the image display solution confirmed by the user, it also includes: displaying the image; In response to receiving a first modification message of the image from the user, determining a first image modification scheme based on the first modification message, the first image modification scheme including at least one of a modification scheme of the image display scheme and a modification scheme of scheme details, and outputting description information of the first image modification scheme; In response to receiving a confirmation message sent by a user for the first image modification scheme, modifying at least one of the image display scheme confirmed by the user and the scheme details confirmed by the user based on the first image modification scheme, and generating an image with the modified image display scheme and the scheme details; In response to receiving a second modification message sent by a user for the image modification solution, taking the second modification message as a new first modification message, iteratively performing the operation of determining the first image modification solution based on the first modification message; Outputting the image includes: In response to receiving an output instruction message from a user for the image, the image is output.

11. The method according to any one of claims 1 to 4, wherein: The image generation task includes a task text for generating an image.

12. The method according to any one of claims 1 to 4, wherein: The image generation task includes: a basic image and a task text for the basic image; After obtaining the image generation task of user input, it also includes: Performing image recognition on the basic image to obtain an image recognition result; Determining an image display solution based on the image generation requirement includes: Determine an image display solution based on the image generation requirement and the image recognition result; Generate an image based on the image display scheme confirmed by the user, including: An image is generated based on the basic image and the image display scheme confirmed by the user.

13. An image generating device, comprising: An acquisition module is used to acquire the image generation task input by the user; An output module is used to output a demand prompt message according to the image generation task, wherein the demand prompt message is used to prompt the user of the specific demand for the image to be generated, and the demand prompt message includes any one or more of the following information involved in the image generation task: task type, target audience, expression theme, style, color, shooting angle, brightness effect, visual feeling of expression, emotion of expression, information of expression, and environment of expression; The acquisition module is further used to acquire a demand reply message input by the user based on the demand prompt message; A first determining module, configured to determine an image generation requirement based on the requirement reply message; A second determination module is used to determine an image display scheme based on the image generation requirement, where the image display scheme is the overall information or main design elements expressed by the image; The output module is further used to output description information of the image display scheme; The acquisition module is further used to receive a confirmation message from the user regarding the image display solution, and receive a confirmation message from the user regarding the solution details; An image generation module is used to generate an image based on the image display scheme confirmed by the user in response to the acquisition module receiving a confirmation message of the user on the image display scheme; wherein, when the image generation module generates an image based on the image display scheme confirmed by the user, it is specifically used to: determine the scheme details for the image display scheme confirmed by the user, and output the prompt words and description information of the scheme details through the output module, and generate an image based on the image display scheme confirmed by the user and the scheme details confirmed by the user, wherein the prompt words of the scheme details include any one or more of the following details and at least one attribute value of each detail: scheme refinement points and implementation methods of the scheme refinement points, image shape, image size, image resolution, and image direction; The output module is further used to output the image; The acquisition module is further configured to modify the image display scheme and the description information of the image display scheme in response to receiving a modification message of the image display scheme from the user; The output module is also used to output description information of the modified image display solution.

14. An image generating device, comprising: An interactive module is used to obtain an image generation task input by a user, and call a language model to determine a demand prompt message corresponding to the image generation task, wherein the demand prompt message is used to prompt the user of specific requirements for the image to be generated, and the demand prompt message includes any one or more of the following information involved in the image generation task: task type, target audience, expression theme, style, color, shooting angle, brightness effect, visual feeling of expression, emotion of expression, information of expression, and environment of expression; and output the demand prompt message; Obtaining a demand reply message input by the user based on the demand prompt message, calling the language model to determine an image generation requirement based on the demand reply message, and determining an image display scheme and description information of the image display scheme based on the image generation requirement, and outputting description information of the image display scheme, wherein the image display scheme is the overall information or main design elements expressed by the image; in response to receiving a confirmation message from the user for the image display scheme, calling the image generation model to generate an image based on the image display scheme confirmed by the user, and outputting the image; In response to receiving a modification message from a user on the image display scheme, modifying and outputting the image display scheme and description information of the image display scheme; The language model is used to determine a requirement prompt message corresponding to the image generation task, determine the image generation requirement based on the requirement reply message, and determine an image display scheme and description information of the image display scheme based on the image generation requirement; In response to the interactive module receiving a confirmation message of the user on the image display scheme, the interactive module determines the scheme details for the image display scheme confirmed by the user, and outputs prompt words and description information of the scheme details, wherein the prompt words of the scheme details include any one or more of the following details and at least one attribute value of each detail: scheme refinement points and implementation methods of the scheme refinement points, image shape, image size, image resolution, and image direction; The image generation model is used to generate an image based on an image display scheme confirmed by a user, and is specifically used to: in response to the interaction module receiving a confirmation message from the user on the scheme details, generate an image based on the image display scheme confirmed by the user and the scheme details confirmed by the user.

15. An electronic device, comprising: A memory for storing a computer program product; A processor, configured to execute a computer program product stored in the memory, wherein when the computer program product is executed, the method described in any one of claims 1 to 12 is implemented.

16. A computer-readable storage medium having computer program instructions stored thereon, wherein when the computer program instructions are executed by a processor, the method according to any one of claims 1 to 12 is implemented.

17. A computer program product, comprising computer program instructions, which implement the method according to any one of claims 1 to 12 when executed by a processor.

Images