Biological avatar display method, electronic device, cloud server, and storage medium

Abstract

The present application discloses a biological avatar display method, an electronic device, a cloud server, and a storage medium. In the present application, the electronic device may obtain a user image, then obtain a second avatar on the basis of the user image and an existing first avatar, and display the second avatar. The second avatar comprises a second outfit, and the second outfit has one or more features among at least one outfit feature of a first outfit in the user image. Hence, in the present application, the outfit of the second avatar displayed on the basis of the existing first avatar can correspond to the outfit of the user in the user image. On the basis of the foregoing, as the outfit of the user in user images obtained by the electronic device changes, the outfit of the displayed avatar will correspondingly change. In this way, the diversity of the outfits of the displayed avatar and their correlation with the outfits of the user are enhanced, thereby enhancing the attention of the user to the biological avatar, and further improving the willingness of the user to use biological avatar-related products.

Description

Biological image display method, electronic device, cloud server and storage medium

[0001] The present application claims priority to the Chinese patent application No. 202410437806.0, filed on April 11, 2024, and entitled "Biological image display method, electronic device, cloud server and storage medium", the content of which is incorporated herein by reference in its entirety. TECHNICAL FIELD

[0002] The present application relates to the technical field of terminal software, and in particular to a biological image display method, an electronic device, a cloud server and a storage medium. BACKGROUND

[0003] With the development of Internet technology and the wide popularity of electronic devices such as smart phones and tablet computers, the functions of electronic devices are becoming more and more powerful. For example, in order to improve the interest, a virtual biological image such as an animal or a cartoon character can be displayed on the desktop of an electronic device, and the biological image can periodically move according to a preset rule. Alternatively, a virtual assistant in an electronic device can also have a corresponding biological image, and when a user uses the virtual assistant, the electronic device displays the corresponding biological image. In this type of scenario, the biological images displayed by the electronic device are often fixed. Based on this, as time goes on, the user will lose the freshness of the displayed biological image, thereby reducing the willingness to use. SUMMARY

[0004] The present application provides a biological image display method, an electronic device, a cloud server and a storage medium, which can improve the diversity of the displayed biological image clothing, and the biological image clothing is closely related to the user's clothing, thereby improving the user's attention to the biological image.

[0005] To achieve the above-mentioned purpose, the present application adopts the following technical solutions:

[0006] In a first aspect, a biological image display method is provided, applied to an electronic device, and the method comprises: obtaining a user image, the user image comprising a first clothing, the first clothing having at least one clothing feature; obtaining a second image based on the user image and a first image, the second image comprising a second clothing, the second clothing having one or more features of the at least one clothing feature; and displaying the second image.

[0007] The first image and the second image can both be virtual images, for example, both being virtual human images or virtual animal images. Alternatively, the first image and the second image can also be other virtual biological images. Alternatively, the first image and the second image can also be real images, for example, real human images or animal images. In addition, the first image and the second image can be the same biological image, specifically, the second image is an image in which the first image is updated in terms of clothing or the first image is added with clothing. Alternatively, the second image can have a different posture or action from the first image, or the second image can have the same posture or action as the first image.

[0008] In the present application, an electronic device can obtain a user image, and then obtain a second image based on the user image and an existing first image, and display the second image. The second image includes a second clothing, and the second clothing has one or more features of at least one clothing feature in the first clothing in the user image. Therefore, the second clothing of the second image displayed in the present application based on the existing first image can correspond to the first clothing in the user image. On this basis, when the user changes the clothing, the clothing of the displayed biological image will also change accordingly as the user image obtained by the electronic device changes. In this way, the diversity of the clothing of the displayed biological image and the relevance to the user's clothing are enhanced, so as to better improve the user's attention to the displayed biological image, and thus improve the user's willingness to use the biological image related product.

[0009] Alternatively, the at least one clothing feature includes one or more of a clothing color feature, a clothing style feature, a clothing pattern feature, a clothing material feature, a clothing style feature, a jewelry material feature, a jewelry shape feature, a jewelry color feature, and a jewelry style feature.

[0010] Alternatively, when the second clothing has a clothing color feature in the at least one clothing feature, the clothing color of the second clothing is the same as or opposite to the clothing color of the first clothing, or the clothing shade of the second clothing is the same as or opposite to the clothing shade of the first clothing, or the color of the clothing at the first body part in the second clothing is the same as or opposite to the color of the clothing at the first body part in the first clothing.

[0011] The color scheme of the second item of clothing being the same as the color scheme of the first item of clothing may mean that the second item of clothing and the first item of clothing contain the same or similar hues. Any two same or similar hues may mean that the angle between the two hues on the hue circle is within a first angle range, for example, the first angle range may be -30 degrees to 30 degrees, in which case the visual difference between the two hues is small. For example, if the first item of clothing contains red and yellow, the second item of clothing may also contain red or yellow; alternatively, the second item of clothing may contain a hue similar to red and a hue similar to yellow, for example, the second item of clothing may contain orange-red and yellow-green.

[0012] Alternatively, the color scheme of the second item of clothing being the same as the color scheme of the first item of clothing may also mean that the hue of the second item of clothing is the same as or similar to the primary color of the first item of clothing. The primary color of clothing refers to the color that occupies the largest area of ​​the clothing. For example, if the primary color of the first item of clothing is yellow, the primary color of the second item of clothing may be yellow-green.

[0013] The second item of clothing having a color scheme opposite to that of the first item of clothing may mean that the second item of clothing and the first item of clothing have opposite hues. Any two opposite hues may mean that the angle between the two hues on the hue circle is within a second angle range, for example, the second angle range is from -120 degrees to 120 degrees. In this case, the two hues are visually significantly different. For example, if the first item of clothing includes red and yellow, the second item of clothing may include cyan, the opposite hue of red, and blue, the opposite hue of yellow.

[0014] Alternatively, the second item of clothing having a color scheme opposite to the first item of clothing may also mean that the primary colors of the second item of clothing and the first item of clothing have opposite hues. For example, the primary color of the first item of clothing has a hue of red, while the primary color of the second item of clothing has a hue of cyan, which is the opposite of red.

[0015] The color of the second article of clothing located on the first body part is the same as the color of the first article of clothing located on the first body part. This may mean that the primary colors of the second article of clothing and the first article of clothing located on the same body part have the same or similar hues. Alternatively, this may mean that the second article of clothing and the first article of clothing located on the same body part have the same or similar hues.

[0016] The color of the second garment located at the first body part is opposite to the color of the first garment located at the first body part, which may mean that the main colors of the second garment and the first garment located at the same body part have opposite hues.

[0017] The color tone of the garment refers to the overall summary of the color of the garment, that is, the basic tendency of the color of the garment. Specifically, according to the hue and the lightness of the color, the color tone can include cold tone, intermediate tone and warm tone. For example, when the proportion of red, yellow or orange in the garment is large, the color tone of the garment is warm, and in this case, the higher the lightness, the warmer the color tone. When the proportion of blue in the garment is large, the color tone of the garment is cold, and the lower the lightness, the colder the color tone. When the proportion of green or white in the garment is large, the color tone of the garment is intermediate.

[0018] Optionally, when the second garment has the garment pattern feature in the at least one garment feature, the second garment includes part or all of the garment pattern of the first garment, or the garment pattern in the second garment is similar to the garment pattern in the first garment.

[0019] If the garment pattern of the first garment can be completely identified, the garment pattern of the second garment can include the largest pattern in the garment pattern of the first garment. If the garment pattern of the first garment is partially identified and the part that is blocked cannot be identified, the garment pattern of the second garment can be the identified part of the garment pattern of the user. In addition, it can also include the part that is intelligently supplemented based on the identified part, that is, the garment pattern of the second garment is a complete pattern obtained by intelligently supplementing based on the identified part of the garment pattern of the user.

[0020] Alternatively, the garment pattern of the second garment can be similar to the garment pattern of the first garment. For example, the garment pattern in the second garment can be redrawn, sketched or regenerated according to the garment pattern feature of the first garment, so that the garment pattern of the second garment has visual similarity with the garment pattern of the first garment. For example, the garment pattern in the second garment and the garment pattern in the first garment are both plaid, but the plaid of the two can be plaid of different shapes or sizes.

[0021] Optionally, when the second garment has at least one of the accessory material feature, the accessory shape feature, the accessory color feature and the accessory style feature in the at least one garment feature, the second garment includes at least one accessory with the at least one feature.

[0022] The accessory material feature can represent the material of the accessory, for example, the accessory material feature can include metal, pearl, jade, plastic, etc. The accessory shape feature can represent the shape of the accessory, for example, the shape of the watch dial, the shape of the glasses lens, etc. The accessory color feature can refer to the garment color feature introduced above. The accessory style feature can represent the style of the accessory, for example, it can include modern style, classical style, minimalist style, etc.

[0023] Optionally, the at least one clothing feature of the first clothing further comprises a type of accessory. Based on this, any accessory included in the second clothing is an accessory that matches the type of the second image.

[0024] Optionally, the at least one clothing feature of the first clothing further comprises a wearing position of an accessory. Based on this, the wearing position of any accessory in the second clothing corresponds to the wearing position of the corresponding accessory in the first clothing.

[0025] Optionally, when the second clothing has a clothing style feature in the at least one clothing feature, the clothing style of the second clothing is the same as the clothing style of the first clothing. For example, the first clothing includes a first accessory, and the second clothing includes a second accessory having the accessory feature of the first accessory. In this case, the wearing position of the first accessory on the user and the wearing position of the second accessory on the second image can be the same.

[0026] Optionally, when the second clothing has a clothing material feature in the at least one clothing feature, the clothing material of the second clothing is the same as the clothing material of the first clothing.

[0027] Optionally, when the second clothing has a clothing style feature in the at least one clothing feature, the clothing style of the second clothing is the same as the clothing style of the first clothing.

[0028] In the present application, the second image obtained by the electronic device includes one or more of the clothing color, clothing style, clothing pattern, clothing material, clothing style, and accessory of the second clothing, which can be in harmony with the first clothing, so that the clothing of the second image is associated with the clothing of the user.

[0029] Optionally, the second image further includes a decoration element corresponding to current scene data, the scene data being used to indicate an external scene and / or an internal scene of the electronic device.

[0030] In the present application, the second image can further include a decoration element that is adapted to the current scene. For example, if the current external scene is a rainy day, the second image can further include a decoration element that is adapted to the rainy day, such as an umbrella, rain boots, raindrops, etc. In this way, by adding a decoration element that is adapted to the current scene to the second image, the second image can be combined with the real scene, and be closer to the user's life and more interesting.

[0031] Optionally, the implementation process of obtaining the second image based on the user image and the first image can comprise: sending user clothing information and the first image to a cloud server, so that the cloud server generates the second image based on the user clothing information and the first image, the user clothing information comprising the user image or a first clothing description text, the first clothing description text being obtained based on the user image and used to describe at least one clothing feature of the user clothing; receiving the second image sent by the cloud server.

[0032] In the present application, the electronic device can generate the second image through the cloud server, so that the occupation of the processing resources of the electronic device can be reduced, and the processing pressure of the electronic device can be reduced.

[0033] Optionally, the implementation process of obtaining the user image can comprise: in response to a first operation of the user, obtaining first interface information to be displayed; if the first interface information comprises the first image, capturing the user image through a camera.

[0034] In the present application, the electronic device can capture the user image through the camera when detecting the first operation of the user and determining that the interface information to be displayed contains the image, so as to generate a new image based on the user clothing in the user image and the image to be displayed and display the new image, so that the clothing of the image to be displayed can change with the change of the user clothing, thereby attracting the user and improving the attraction to the user.

[0035] Optionally, the first image is an image in a first wallpaper, and the implementation process of displaying the second image can comprise: displaying a second wallpaper based on the second image and the first wallpaper, the second wallpaper comprising the second image.

[0036] In the present application, the electronic device can display the desktop wallpaper based on the second image after obtaining the second image, so that the clothing of the image in the desktop wallpaper can change with the change of the user clothing in the interface of the desktop where the user stays frequently, thereby attracting the attention of the user and increasing the use intention of the user.

[0037] Optionally, the first wallpaper is a static wallpaper, and the implementation process of displaying the second wallpaper based on the second image and the first wallpaper can comprise: replacing the first image in the first wallpaper with the second image to obtain the second wallpaper; and displaying the second wallpaper.

[0038] Optionally, the first wallpaper is a dynamic wallpaper, and the implementation process of displaying the second wallpaper based on the second image and the first wallpaper can include: obtaining first composition data corresponding to the first wallpaper, the first composition data being used to represent a plurality of first postures of an image; generating the second wallpaper based on the first composition data and the second image, the second wallpaper including the second image corresponding to the plurality of first postures respectively; and displaying the second wallpaper.

[0039] In the present application, the electronic device can generate and display a dynamic wallpaper including a second image by using currently set composition data corresponding to a first image and the second image, so that the display of the desktop wallpaper is more vivid and the content is more abundant.

[0040] Optionally, the implementation process of obtaining the first composition data corresponding to the first wallpaper can include: obtaining current scene data, the scene data being used to indicate an external scene and / or an internal scene of the electronic device; and obtaining, from a plurality of reference composition data corresponding to the first wallpaper, composition data corresponding to the scene data, the first composition data including the composition data corresponding to the scene data.

[0041] In the present application, the electronic device can implement composition in combination with current scene data in the process of generating a dynamic wallpaper based on a second image, so that the posture of the second image in the dynamic wallpaper will be consistent with the current scene, and the dynamic wallpaper is more intelligent, more personalized, and more interesting.

[0042] Optionally, after displaying the second wallpaper, the method further includes: in response to an interaction signal of a user, obtaining, from a plurality of reference composition data corresponding to the first wallpaper, second composition data corresponding to the interaction signal, the second composition data being used to represent a plurality of second postures of an image; generating a third wallpaper based on the second composition data and the second image, the third wallpaper including the second image corresponding to the plurality of second postures; and displaying the third wallpaper.

[0043] In the present application, the user can also interact with the image in the dynamic wallpaper displayed by the electronic device, and the electronic device can update the posture of the image in the dynamic wallpaper based on the interaction signal of the user, so that the image in the dynamic wallpaper can make actions in response to the interaction signal of the user, which improves the interest of the dynamic wallpaper, provides the user with a more abundant interactive experience, and thus can enhance the user's willingness to use.

[0044] In a second aspect, a biological image display method is provided, applied to a cloud server, and the method comprises: receiving user clothing information and a first image sent by an electronic device, the user clothing information comprising a user image or a first clothing description text, the user image comprising a first clothing, the first clothing having at least one clothing feature, and the first clothing description text being obtained based on the user image and used to describe the at least one clothing feature; generating a second image based on the user clothing information and the first image, the second image comprising a second clothing, the second clothing having one or more features of the at least one clothing feature; and sending the second image to the electronic device to enable the electronic device to display the second image.

[0045] In the present application, the cloud server can receive user clothing information and a first image sent by an electronic device, and generate a new second image based on the user clothing information and the first image to enable the electronic device to display the second image. The second clothing comprises one or more features of the at least one clothing feature of the first clothing in the user image. As can be seen, the second clothing in the second image generated based on the first image in the present application can correspond to the first clothing in the user image. On this basis, as the clothing in the user image sent by the electronic device changes, the clothing of the biological image generated will also change accordingly. In this way, the diversity of the clothing of the biological image displayed by the electronic device and the relevance to the clothing in the user image are enhanced, thereby better improving the user's attention to the biological image and further improving the user's willingness to use the biological image related products.

[0046] Optionally, the first image is a virtual image, and the second image is a virtual image.

[0047] Optionally, the at least one clothing feature comprises one or more of a clothing color feature, a clothing style feature, a clothing pattern feature, a clothing material feature, a clothing style feature, a jewelry material feature, a jewelry shape feature, a jewelry color feature, and a jewelry style feature.

[0048] Optionally, when the second clothing has a clothing color feature of the at least one clothing feature, a main clothing color of the second clothing is the same as or opposite to a main clothing color of the first clothing, or a clothing shade of the second clothing is the same as or opposite to a clothing shade of the second clothing, or a color of a clothing located at a first body part in the second clothing is the same as a color of a clothing located at the first body part in the first clothing.

[0049] Optionally, when the second garment has a clothing pattern feature in the at least one garment feature, the second garment includes part or all of the clothing pattern of the first garment, or the clothing pattern in the second garment is similar to the clothing pattern in the first garment.

[0050] Optionally, when the second garment has at least one of a jewelry material feature, a jewelry shape feature, a jewelry color feature, and a jewelry style feature in the at least one garment feature, the second garment includes at least one jewelry having the at least one feature.

[0051] Optionally, when the second garment has a clothing style feature in the at least one garment feature, the clothing style of the second garment is the same as the clothing style of the first garment.

[0052] Optionally, when the second garment has a clothing material feature in the at least one garment feature, the clothing material of the second garment is the same as the clothing material of the first garment.

[0053] Optionally, when the second garment has a clothing style feature in the at least one garment feature, the clothing style of the second garment is the same as the clothing style of the first garment.

[0054] In this application, one or more of the clothing color matching, clothing style, clothing pattern, clothing material, clothing style, and jewelry of the second garment can be echoed with the first garment in the user image, so that the second image garment is associated with the user garment.

[0055] Optionally, the user garment information includes the user image, and the implementation process of generating the second image based on the user garment information and the first image can include: based on the user image, obtaining a second garment description text for describing at least one garment feature of the first garment; based on the first image, obtaining the first image corresponding to the composition data and the image description text; based on the second garment description text, the first image corresponding to the composition data and the image description text, and using a stable diffusion (SD) model to generate the second image.

[0056] Optionally, the implementation process of generating the second image based on the second garment description text, the first image corresponding to the composition data and the image description text, and using the stable diffusion (SD) model can include: based on the second garment description text and the first image corresponding to the image description text, generating a comprehensive description text; inputting the comprehensive description text and the first image corresponding to the composition data into the SD model, and outputting the second image through the SD model.

[0057] In the present application, the cloud server can utilize the SD model to fuse the user clothing information and the first image to obtain the second image, so that not only the second image can better inherit the image features of the first image, but also the clothing of the second image can better respond to the user clothing.

[0058] Optionally, the implementation process of obtaining the second clothing description text based on the user image can include: utilizing a clothing model to identify the user clothing in the user image to obtain the second clothing description text.

[0059] In the present application, the cloud server can utilize a separate clothing model to identify the user clothing in the user image to improve the accuracy of the obtained clothing description text, so that the clothing of the generated second image can better respond to the user clothing.

[0060] Optionally, the image description text corresponding to the first image is obtained by utilizing a bootstrapping language-image pre-training (BLIP) model to identify the first image, and the implementation process of obtaining the second clothing description text based on the user image can include: utilizing the BLIP model to identify the first clothing in the user image to obtain the second clothing description text.

[0061] In the present application, the BLIP model can not only be used to identify the image to obtain the image description text, but also be used to identify the user clothing in the user image to obtain the clothing description text, so that the model running in the cloud server can reduce the occupation of server resources.

[0062] In a third aspect, a biological image display device is provided, which includes at least one module for executing the biological image display method of the first aspect or the second aspect.

[0063] In a fourth aspect, an electronic device is provided, which includes a processor for executing at least one program instruction or code stored in a memory to implement the biological image display method of the first aspect.

[0064] In a fifth aspect, a cloud server is provided, which includes a processor for executing at least one program instruction or code stored in a memory to implement the biological image display method of the second aspect.

[0065] In a sixth aspect, a computer-readable storage medium is provided, and the computer-readable storage medium stores instructions. When the instructions are executed on a computer device, the computer device is caused to perform the biological figure display method in the first aspect or the second aspect.

[0066] In a seventh aspect, a computer program product is provided, and the computer program product stores instructions. When the computer program product is executed on a computer device, the computer device is caused to perform the biological figure display method in the first aspect or the second aspect.

[0067] The technical effects obtained by the third aspect to the seventh aspect are similar to the technical effects obtained by the corresponding technical means in the first aspect and the second aspect, and will not be described here. BRIEF DESCRIPTION OF DRAWINGS

[0068] FIG. 1 is an implementation architecture diagram of a biological figure display method provided by an embodiment of the present application;

[0069] FIG. 2 is a structural schematic diagram of an electronic device provided by an embodiment of the present application;

[0070] FIG. 3 is a structural schematic diagram of a server provided by an embodiment of the present application;

[0071] FIG. 4 is a flowchart of a biological figure display method provided by an embodiment of the present application;

[0072] FIG. 5 is a schematic diagram in which a user switches from a certain page of a desktop to a page containing a pet widget provided by an embodiment of the present application;

[0073] FIG. 6 is a flowchart of generating an initial figure by a cloud server provided by an embodiment of the present application;

[0074] FIG. 7 is a schematic diagram in which a cloud server generates an initial figure by using a model deployed by itself provided by an embodiment of the present application;

[0075] FIG. 8 is a flowchart of an electronic device acquiring a second figure by a cloud server provided by an embodiment of the present application;

[0076] FIG. 9 is a schematic diagram of a second figure generated based on a user image and a first figure provided by an embodiment of the present application;

[0077] FIG. 10 is a schematic diagram of a virtual figure in a rainy day scenario provided by an embodiment of the present application;

[0078] FIG. 11 is a schematic diagram of a virtual figure in a waiting-to-eat scenario provided by an embodiment of the present application;

[0079] FIG. 12 is a schematic diagram of a virtual figure in a listening-to-music scenario provided by an embodiment of the present application;

[0080] FIG. 13 is a flowchart of a method for updating a wallpaper based on a second image according to an embodiment of the present application;

[0081] FIG. 14 is a structural diagram of a biological image display device according to an embodiment of the present application;

[0082] FIG. 15 is a structural diagram of another biological image display device according to an embodiment of the present application. DETAILED DESCRIPTION

[0083] In order to make the objectives, technical solutions and advantages of the embodiments of the present application clearer, the embodiments of the present application will be further described in detail below with reference to the drawings.

[0084] Before the embodiments of the present application are explained in detail, the application scenarios involved in the embodiments of the present application are introduced.

[0085] With the development of Internet technology and the wide popularity of electronic devices, applications for implementing various functions are emerging in an endless stream. For example, there are many biological image-based applications at present, which can make electronic devices more intelligent and more interesting.

[0086] For example, at present, a user can add a cute pet widget on the desktop of an electronic device, through which the electronic device can display a virtual cute pet image on the desktop to implement the function of an online electronic pet. The electronic device can display an animation containing virtual cute pet images in different postures on the desktop at a specific time, so as to realize the periodic activities of the virtual cute pet image. For another example, a virtual assistant in an electronic device can have a corresponding virtual image, and when the user uses the virtual assistant, the electronic device can display the virtual image corresponding to the virtual assistant to improve the user's experience. In the above scenarios, the virtual image displayed by the electronic device is usually fixed, and therefore, as time goes on, the user will lose the freshness of the displayed virtual image and the attention will decrease, thereby affecting the user's willingness to use this type of application.

[0087] In addition, there are also some applications for implementing biological image dressing at present, in which an electronic device can provide a wardrobe material library to a user, and the user can select target clothes from the wardrobe material library to realize the dressing of a biological image. However, it takes a long time for the user to select clothes from the wardrobe material library to edit the combination and realize the dressing of the biological image. After dressing several times, the user's experience willingness may decrease.

[0088] Based on the problems existing in the applications related to the biological image as described above, the biological image display method provided in the embodiments of the present application is provided. In the method, the electronic device can obtain a user image, and then obtain a second image based on the user image and an existing first image, and display the second image. The user image includes a first clothing, and the first clothing has at least one clothing feature. The second image includes a second clothing, and the second clothing has one or more of the at least one clothing feature of the first clothing. As can be seen, the clothing of the second image displayed in the embodiments of the present application based on the existing first image can correspond to the user clothing in the user image. On this basis, as the user clothing in the user image obtained by the electronic device changes, the clothing of the displayed biological image will also change automatically. In this way, the diversity and relevance of the clothing of the displayed biological image are enhanced, so that the user's attention to the biological image can be better improved, and then the user's willingness to use the biological image related product is improved. Moreover, compared with the current biological image dressing application, the biological image display method provided in the embodiments of the present application can automatically change the clothing of the biological image according to the change of the user clothing in the user image, without the need for the user to manually select and edit the clothing for dressing, which is more convenient and fast.

[0089] It should be noted that the biological image display method provided in the embodiments of the present application can not only be applied to the above-mentioned several display biological image scenes, but also can be used in other display biological image scenes, for example, when the wallpaper displayed on the desktop contains a biological image, or when the biological image is displayed in the game application, or in other real biological image dressing scenes, the biological image display method provided in the embodiments of the present application can be used for display.

[0090] Next, the implementation architecture related to the embodiments of the present application is introduced.

[0091] FIG. 1 is a schematic diagram of an implementation architecture related to the biological image display method provided in the embodiments of the present application. As shown in FIG. 1, the implementation architecture includes an electronic device 11 and a cloud server 12. The electronic device 11 and the cloud server 12 establish a communication connection.

[0092] In the embodiments of the present application, the electronic device 11 is configured to obtain a user image, and send user clothing information and a first image to the cloud server 12. The user image includes a first clothing, and the first clothing has at least one clothing feature. The user clothing information can include a user image or a first clothing description text obtained based on the user image, and the first clothing description text is used to describe at least one clothing feature of the first clothing.

[0093] The cloud server 12 is configured to generate a second image based on the first image and the user clothing information sent by the electronic device 11, and send the second image to the electronic device 11. The electronic device 11 receives and displays the second image. The second image includes a second clothing, and the second clothing has one or more characteristics of the at least one clothing characteristic of the first clothing.

[0094] For example, referring to FIG. 1, the cloud server 12 is deployed with a cloud large model 13, and the cloud server 12 can use the cloud large model 13 to generate a second image based on the user clothing information and the first image.

[0095] Specifically, the cloud large model 13 can include a control network (controlnet) model 131, a BLIP model 132, and an SD model 133.

[0096] The control network model 131 can be used to generate the composition data corresponding to the first image.

[0097] The BLIP model 132 is configured to obtain the image description text corresponding to the first image, and in the case that the user clothing information sent by the electronic device 11 includes a user image, the BLIP model 132 is further configured to obtain a second clothing description text based on the user image.

[0098] The SD model 133 is configured to generate a second image based on the first clothing description text sent by the electronic device 11 or the second clothing description text generated by the BLIP model.

[0099] Optionally, the cloud large model 13 can further include a clothing model 134. In this case, the user clothing information sent by the electronic device 11 can include a user image, and the clothing model 134 can be used to obtain a second clothing description text based on the user image.

[0100] Optionally, the cloud large model 13 can further include a low rank adaptation (LoRA) model 135. The LoRA model 135 can provide a style parameter for the SD model 133 to indicate a certain image style. Based on this, the SD model 133 can use the style parameter provided by the LoRA model 135 to generate a second image conforming to the image style indicated by the style parameter based on the first clothing description text or the second clothing description text, and the composition data and the image description text corresponding to the first image.

[0101] It should be noted that the electronic device described above can be a smart phone, a tablet computer, or other smart terminal device. The cloud server described above can be implemented by a single physical server, or by a server cluster.

[0102] It is worth noting that in the implementation architecture described above, the display of the biological image is realized by the combination of the electronic device and the cloud server. In some possible cases, the biological image display method provided in the embodiments of the present application can also be realized by the electronic device alone. In this case, part or all of the models in the cloud model 13 described above can be deployed in the electronic device, and accordingly, the electronic device can use these models to realize the generation of the second image.

[0103] FIG. 2 is a structural schematic diagram of an electronic device 200 provided in an embodiment of the present application. The functions of the electronic device in the implementation architecture shown in FIG. 1 can be realized by the electronic device 200 shown in FIG. 2. Referring to FIG. 2, the electronic device 200 can include a processor 201, an external memory interface 202, an internal memory 203, an antenna 1, an antenna 2, a mobile communication module 204, a wireless communication module 205, a display screen 206, a camera 207, a sensor module 208, a charging management module 209, a power management module 210, a battery 211, a button 212, and the like. The sensor module 208 can include a pressure sensor 208A, a gyroscope sensor 208B, an acceleration sensor 208C, a touch sensor 208D, a proximity light sensor 208E, an ambient light sensor 208F, and the like.

[0104] The processor 201 can include one or more processing units, for example: the processor 201 can include an application processor (application processor, AP), a modem processor, a graphics processing unit (graphics processing unit, GPU), an image signal processor (image signal processor, ISP), a controller, a video codec, a digital signal processor (digital signal processor, DSP), a baseband processor, and / or a neural-network processing unit (neural-network processing unit, NPU), etc. The NPU is a neural-network (neural-network, NN) computing processor, which is derived from the structure of a biological neural network, for example, the transmission mode between human neurons, and can also constantly self-learn by quickly processing input information. Through the NPU, intelligent cognition and other applications of the electronic device 200 can be realized, for example: image recognition, face recognition, speech recognition, text understanding, etc. The different processing units described above can be independent devices, or can be integrated in one or more processors.

[0105] The processor 201 can also include a memory for storing instructions and data. In some embodiments, the memory in the processor 201 is a cache memory. The memory can hold instructions or data that the processor 201 has just used or is using repeatedly. If the processor 201 needs to use the instructions or data again, it can call them directly from the memory. This avoids repeated access and reduces the waiting time of the processor 201, thus improving the efficiency of the system.

[0106] In some embodiments, the processor 201 can include one or more interfaces. The interfaces can include an inter-integrated circuit (I2C) interface, an inter-integrated circuit sound (I2S) interface, a pulse code modulation (PCM) interface, a universal asynchronous receiver / transmitter (UART) interface, a mobile industry processor interface (MIPI), a general-purpose input / output (GPIO) interface, a subscriber identity module (SIM) interface, and / or a universal serial bus (USB) interface, etc.

[0107] The charging management module 209 is configured to receive a charging input from a charger. The charger can be a wireless charger or a wired charger. In some embodiments of wired charging, the charging management module 209 can receive a charging input from a wired charger through a USB interface. In some embodiments of wireless charging, the charging management module 209 can receive a wireless charging input through a wireless charging coil of the electronic device 200. The charging management module 209 can charge the battery 211 while also supplying power to the electronic device through the power management module 210.

[0108] The power management module 210 is configured to connect the battery 211 and the charging management module 209 to the processor 201. The power management module 210 receives input from the battery 211 and / or the charging management module 209 to power the processor 201, the internal memory 203, the display 206, the wireless communication module 205, and the like. The power management module 210 can also be configured to monitor parameters such as battery capacity, battery cycle count, battery health (leakage, impedance), and the like. In some embodiments, the power management module 210 can also be integrated into the processor 201. In some embodiments, the power management module 210 and the charging management module 209 can also be integrated into the same device.

[0109] The wireless communication function of the electronic device 200 can be implemented by the antenna 1, the antenna 2, the mobile communication module 204, the wireless communication module 205, the modem processor, and the baseband processor, and the like.

[0110] The antenna 1 and the antenna 2 are configured to transmit and receive electromagnetic wave signals. Each antenna in the electronic device 200 can be configured to cover a single or multiple communication frequency bands. Different antennas can also be multiplexed to improve the utilization of the antennas. For example, the antenna 1 can be multiplexed as a diversity antenna for a wireless local area network. In some embodiments, the antennas can be used in combination with a tuning switch.

[0111] The mobile communication module 204 can provide a solution for wireless communication including 2G / 3G / 4G / 5G and the like applied to the electronic device 200. The mobile communication module 204 can receive electromagnetic waves from the antenna 1, filter, amplify, and the like the received electromagnetic waves, and transmit the processed signals to the modem processor for demodulation. The mobile communication module 204 can also amplify signals modulated by the modem processor and convert the signals into electromagnetic waves to be radiated through the antenna 1. In some embodiments, at least part of the functions of the mobile communication module 204 can be integrated into the processor 201. In some embodiments, at least part of the functions of the mobile communication module 204 and at least part of the modules of the processor 201 can be integrated into the same device.

[0112] ​The wireless communication module 205 can provide solutions for wireless communication including wireless local area networks (WLAN) (e.g., wireless fidelity (Wi-Fi) networks), Bluetooth (BT), global navigation satellite system (GNSS), frequency modulation (FM), near field communication (NFC), infrared (IR) technology, etc. The wireless communication module 205 can be one or more devices that integrate at least one communication processing module. The wireless communication module 205 receives electromagnetic waves via the antenna 2, frequency-modulates and filters the electromagnetic wave signals, and transmits the processed signals to the processor 201. The wireless communication module 205 can also receive signals to be transmitted from the processor 201, frequency-modulate them, amplify them, and radiate them as electromagnetic waves via the antenna 2.

[0113] In some embodiments, the antenna 1 and the mobile communication module 204 of the electronic device 200 are coupled, and the antenna 2 and the wireless communication module 205 are coupled, so that the electronic device 200 can communicate with a network and other devices through wireless communication technology. The wireless communication technology can include global system for mobile communications (GSM), general packet radio service (GPRS), code division multiple access (CDMA), wideband code division multiple access (WCDMA), time-division code division multiple access (TD-SCDMA), long term evolution (LTE), etc.

[0114] The electronic device 200 implements a display function through a GPU, a display screen 206, and an application processor, etc. The GPU is a microprocessor for image processing, which is connected to the display screen 206 and the application processor. The GPU is used to perform mathematical and geometric calculations for graphics rendering. The processor 201 can include one or more GPUs that execute program instructions to generate or change display information.

[0115] The display screen 206 is configured to display images, videos, and the like. The display screen 206 includes a display panel. The display panel can be a liquid crystal display (LCD), an organic light-emitting diode (OLED), an active-matrix organic light-emitting diode (AMOLED), a flex light-emitting diode (FLED), a Miniled, a MicroLed, a Micro-oLed, a quantum dot light emitting diodes (QLED), or the like. In some embodiments, the electronic device 200 can include one or N display screens 206, where N is a positive integer greater than 1.

[0116] The electronic device 200 can implement a photographing function through an ISP, the camera 207, a video codec, a GPU, the display screen 206, and an application processor.

[0117] The camera 207 is configured to capture still images or videos. An object generates an optical image through a lens and projects the optical image to a photosensitive element. The photosensitive element converts the optical signal into an electrical signal, and then transmits the electrical signal to an ISP to convert the electrical signal into a digital image signal. The ISP outputs the digital image signal to a DSP for processing. The DSP converts the digital image signal into an image signal in a standard format, such as RGB, YUV, or the like. The focal length of the lens can be used to represent the field of view of the camera. The smaller the focal length of the lens, the larger the field of view of the lens. The photosensitive element can be a charge coupled device (CCD) or a complementary metal-oxide-semiconductor (CMOS) phototransistor. In the embodiments of the present application, the electronic device 200 can include two or more cameras 207 with different focal lengths.

[0118] The external memory interface 202 can be configured to connect an external memory card, such as a Micro SD card, to extend the storage capacity of the electronic device 200. The external memory card communicates with the processor 201 through the external memory interface 202 to implement a data storage function. For example, the external memory card can be used to store videos and the like.

[0119] The internal memory 203 can be used to store computer executable program codes including instructions. The internal memory 203 can include a program storage area and a data storage area. The program storage area can store an operating system, at least one application program required by a function (such as an image playing function, etc.), and the like. The data storage area can store data created during use of the electronic device 200 (such as a phone book, etc.), and the like. In addition, the internal memory 203 can include a high-speed random access memory, and can further include a non-volatile memory such as at least one magnetic disk storage device, a flash memory device, a universal flash storage (UFS), and the like. The processor 201 executes various function applications and data processing of the electronic device 200 by running instructions stored in the internal memory 203 and / or instructions stored in a memory disposed in the processor.

[0120] The pressure sensor 208A is used to sense a pressure signal, and can convert the pressure signal into an electrical signal. In some embodiments, the pressure sensor 208A can be disposed on the display screen 206. When a touch operation is applied to the display screen 206, the electronic device 200 detects the touch operation intensity according to the pressure sensor 208A. The electronic device 200 can also calculate the touch position according to the detection signal of the pressure sensor 208A. In some embodiments, touch operations applied to the same touch position but with different touch operation intensities can correspond to different operation instructions. For example, when a touch operation with a touch operation intensity less than a first pressure threshold is applied to a short message application icon, an instruction of viewing a short message is executed. When a touch operation with a touch operation intensity greater than or equal to the first pressure threshold is applied to the short message application icon, an instruction of creating a new short message is executed.

[0121] The gyroscope sensor 208B can be used to determine the motion posture of the electronic device 200. In some embodiments, the angular velocity of the electronic device 200 around three axes (i.e., x, y, and z axes) can be determined by the gyroscope sensor 208B. The gyroscope sensor 208B can be used for navigation and motion sensing game scenarios.

[0122] The acceleration sensor 208C can detect the acceleration of the electronic device 200 in various directions (generally three axes). When the electronic device 200 is stationary, the acceleration sensor 208C can detect the magnitude and direction of gravity. It can also be used to identify the electronic device posture, and applied to landscape / portrait screen switching, pedometer, and the like.

[0123] Touch sensor 208D, also referred to as "touch device". Touch sensor 208D can be disposed on display screen 206, and touch sensor 208D and display screen 206 together form a touch screen, also referred to as "touch panel". Touch sensor 208D is configured to detect a touch operation applied to or near the touch sensor 208D. The touch sensor 208D can pass the detected touch operation to the application processor to determine the touch event type. Visual output related to the touch operation can be provided through display screen 206. In other embodiments, touch sensor 208D can also be disposed on the surface of electronic device 200, which is different from the position where display screen 206 is located.

[0124] Proximity light sensor 208E can include a light emitting diode and a light detector. Electronic device 200 emits infrared light outwardly through the light emitting diode, and detects infrared reflected light from nearby objects using the light detector. When sufficient reflected light is detected, it can be determined that there is an object near electronic device 200. When insufficient reflected light is detected, it can be determined that there is no object near electronic device 200. Electronic device 200 can use proximity light sensor 208E to detect that a user is holding electronic device 200 close to the ear for a call, so as to automatically turn off the screen to achieve the purpose of power saving. Proximity light sensor 208E can also be used for automatic unlocking and locking in a holster mode or a pocket mode.

[0125] Ambient light sensor 208F is configured to sense ambient light brightness. Electronic device 200 can adaptively adjust the brightness of display screen 206 according to the sensed ambient light brightness. Ambient light sensor 208F can also be used to automatically adjust white balance when taking a picture, and can also be used in cooperation with proximity light sensor 208E to detect whether electronic device 200 is in a pocket to prevent accidental touch.

[0126] Keys 212 include power key, volume key, and the like. Keys 212 can be mechanical keys or touch keys. Electronic device 200 can receive key input and generate key signal input related to user settings and function control of electronic device 200.

[0127] It can be understood that the structure illustrated in the embodiments of the present application does not constitute a specific limitation on electronic device 200. In other embodiments of the present application, electronic device 200 can include more or fewer components than illustrated, or combine certain components, or split certain components, or different component arrangements. The illustrated components can be implemented in hardware, software, or a combination of software and hardware.

[0128] FIG. 3 is a structural schematic diagram of a server according to an embodiment of the present application. The functions of the cloud server shown in FIG. 1 can be implemented by one or more servers shown in FIG. 3. For example, referring to FIG. 3, the server 300 can include at least one processor 301, a communication bus 302, a memory 303, and at least one communication interface 304. It should be noted that the device structure shown in FIG. 3 does not limit the server 300, and the server 300 can include more or fewer components than those shown in the figure, or combine certain components, or different component arrangements, which are not limited in the embodiments of the present application. The components of the server 300 will be described in detail below in conjunction with FIG. 3.

[0129] The processor 301 is the control center of the server 300, which can be one processor or a combination of multiple processing elements. For example, the processor 301 can be a general-purpose central processing unit (CPU), or an application-specific integrated circuit (ASIC), or one or more integrated circuits for controlling the execution of programs of the present application, such as one or more digital signal processors (DSP), or one or more field programmable gate arrays (FPGA). The processor 301 can execute various functions of the server 300 by running or executing software programs stored in the memory 303 and calling data stored in the memory 303. For example, the actions of the cloud server in the embodiments below can be executed by the processor of the corresponding device calling the data in the memory.

[0130] As an embodiment, the processor 301 can include one or more CPUs, such as CPU0 and CPU1 shown in FIG. 3.

[0131] As an embodiment, the server 300 can include multiple processors, such as the processor 301 and the processor 305 shown in FIG. 3. Each of these processors can be a single-CPU processor or a multi-CPU processor. Here, the processor can refer to one or more devices, circuits, and / or processing cores for processing data (such as computer program instructions).

[0132] The communication bus 302 can include a path for transmitting information between the above-mentioned components. The communication bus 302 can be an industry standard architecture (ISA) bus, a peripheral component (PCI) bus, or an extended industry standard architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is shown in FIG. 3, but it does not mean that there is only one bus or only one type of bus.

[0133] The memory 303 can be a read-only memory (ROM) or other type of static storage device that can store static information and instructions, a random access memory (RAM) or other type of dynamic storage device that can store information and instructions, an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disk storage, a magneto-optical disk storage, a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer, but is not limited to this. The memory 303 can exist independently and be connected to the processor 301 through the communication bus 302. The memory 303 can also be integrated with the processor 301. The memory 303 is used to store software programs for executing the schemes provided by the embodiments of the present application, and the execution is controlled by the processor 301.

[0134] The communication interface 304 is used for communication with other devices or communication networks, such as Ethernet, RAN, wireless local area networks (WLAN), etc. The communication interface 304 can include a receiving unit to realize the receiving function, and a sending unit to realize the sending function.

[0135] As an example, the server 300 can also include an output device 306 and an input device 307. The output device 306 is in communication with the processor 301 and can display information in a variety of ways. For example, the output device 306 can be a liquid crystal display (LCD), a light emitting diode (LED) display device, a cathode ray tube (CRT) display device, or a projector, etc. The input device 307 is in communication with the processor 301 and can receive input in a variety of ways. For example, the input device 307 can be a mouse, a keyboard, a touch screen device, a sensor device, etc.

[0136] Next, the biological image display method provided by the embodiments of the present application will be explained in detail.

[0137] FIG. 4 is a flowchart of a biological image display method provided by an embodiment of the present application. Referring to FIG. 4, the process can include the following steps:

[0138] Step 401: An electronic device acquires a user image, the user image including a first clothing, the first clothing having at least one clothing feature.

[0139] In the embodiments of the present application, the electronic device can collect a user image of a current user through a camera, the user image including a first clothing. On this basis, at least one clothing feature of the first clothing can be obtained by image analysis on the user image. It should be noted that the process of obtaining information (such as clothing description text) of at least one clothing feature of the first clothing by image analysis on the user image can be performed by the electronic device or by a cloud server. The specific implementation process can be referred to the subsequent description of step 402.

[0140] The current user can be a current user of the electronic device or another user. The first clothing can include a garment worn by the current user, and can also include accessories worn by the current user.

[0141] In addition, the clothing feature can refer to a feature or attribute of the clothing.

[0142] For example, the at least one clothing feature of the first clothing can include one or more of a garment color feature, a garment style feature, a garment pattern feature, a garment material feature, a garment style feature, and an accessory feature.

[0143] The garment color feature can include garment color matching and garment color tone.

[0144] Specifically, the clothing color can refer to the color composition of the clothing. As an example, the clothing color can include the color composition of the whole body clothing and the area ratio of each color, in addition to the main color with the largest area ratio in the whole body clothing. As another example, according to different body parts, the clothing can be divided into different clothing areas. Based on this, the clothing color can include the color composition in at least one clothing area and the area ratio of each color in the corresponding clothing area. In addition, the clothing color can also include the main color with the largest area ratio in each clothing area.

[0145] For example, the clothing color can include the clothing color of the upper body of the human body. Among them, the clothing of the upper body includes green and white, and the area ratio of green in the upper body is more than 60%, which is larger than the area ratio of white, so green is the main color.

[0146] The clothing tone can refer to the overall summary of the clothing color, that is, the basic tendency of the clothing color, for example, the clothing tone can be warm tone, intermediate tone or cold tone. For example, when the red, yellow or orange color in the clothing accounts for a large proportion, the clothing tone is warm, and in this case, the higher the brightness, the warmer the tone. When the blue color in the clothing accounts for a large proportion, the clothing tone is cold, and the lower the brightness, the colder the tone. When the green or white color in the clothing accounts for a large proportion, the clothing tone is intermediate tone.

[0147] The clothing style feature can be used to indicate the type of clothing worn by the user. For example, the clothing style feature can indicate that the clothing worn by the user is a coat, a lower garment or a dress, or the clothing style feature can also indicate a more detailed clothing type. For example, for the clothing of the upper body, the clothing style feature can indicate that the clothing is a shirt, a long coat, a short coat, etc. For the lower garment, the clothing style feature can indicate that the clothing is a skirt, trousers, etc.

[0148] The clothing pattern feature can be used to indicate the characteristics of the pattern on the clothing worn by the user. For example, the clothing pattern feature can include part or all of the pattern on the clothing worn by the user. For example, when the user wears a coat with a cartoon pattern, the clothing pattern feature can include part of the cartoon pattern or all of it. Or, the clothing pattern feature can also indicate the type of pattern of the clothing worn by the user, for example, when the user wears a diamond checkered coat, the clothing pattern feature can indicate that the type of the pattern of the clothing worn by the user is checkered.

[0149] The clothing material feature can include knitted, leather, cloth, etc. The clothing style feature can include modern dress, Tang suit, national style, etc.

[0150] The accessory feature can include one or more of the accessory material feature, the accessory shape feature, the accessory color feature, and the accessory style feature.

[0151] Among them, accessory material features can characterize the material of the accessory, for example, accessory material features can include metal, pearl, jade, plastic, etc. Accessory shape features can characterize the shape of the accessory, for example, the shape of the dial of a watch, the shape of the lens of glasses, etc. Accessory color features can characterize the color of the accessory. Accessory style features can characterize the style of the accessory, for example, they can include modern style, classical style, minimalist style, etc.

[0152] Optionally, the accessory features may further include the accessory type and the location where the accessory is worn. For example, the accessory type may include shoes, gloves, watches, jewelry, and glasses worn by the user, and the accessory features may further include the wearing location corresponding to the above-mentioned corresponding type of accessories.

[0153] In some embodiments, the electronic device may acquire a user image upon detecting that the content to be displayed includes a living creature. The living creature may be a virtual image or a real image. If the living creature is a virtual image, it may be a virtual person, animal, or other type of living creature. If the living creature is a real image, it may be a real person or animal.

[0154] Exemplarily, in response to a user's first operation, the electronic device may obtain first interface information to be displayed; if the first interface information includes a first image, the electronic device may capture an image of the user via a camera. The first operation is an operation for instructing the display of the first interface information. That is, when the electronic device detects a user's operation instructing the display of the first interface information, if the first interface information to be displayed includes the first image, the electronic device may activate the camera to capture an image of the user.

[0155] In a first possible scenario, the electronic device's desktop includes multiple pages, each displaying different content. One of these multiple pages may contain a biometric image. Therefore, when a user slides between any two pages on the desktop, for example, from a first page to a second page, the electronic device can retrieve interface information for the second page to be displayed based on the sliding operation. The interface information for the second page is the first interface information, which includes the content displayed on the second page. The electronic device then detects whether the first interface information contains a biometric image—that is, whether the content displayed on the second page to be displayed contains a biometric image. If a biometric image is contained, the electronic device can activate a camera to capture an image of the user, so as to update the biometric image to be displayed based on the user image. In this embodiment of the present application, the biometric image to be displayed on the second page may be referred to as the first image.

[0156] For example, referring to FIG. 5, the user can set the cute pet widget in the page 51 to display a virtual owl image 511. When the user switches from the page 50 to the page 51, the electronic device determines that the page 51 contains the cute pet widget by acquiring the interface information of the page 51, and determines that the virtual owl image 511 is about to be displayed in the page 51. In this case, the electronic device can start the camera to capture the user image.

[0157] In a second possible scenario, the desktop of the electronic device can be set with a wallpaper containing a biological image. The user can enter the desktop through an unlocking operation or an application exit operation, and in this case, the electronic device can acquire the first interface information about to be displayed after detecting the above operation, and the first interface information includes the wallpaper about to be displayed. If the wallpaper contains a biological image, the electronic device can start the camera to capture the user image. The biological image about to be displayed in the wallpaper is the first image.

[0158] In a third possible scenario, the electronic device has an application of a virtual assistant. When the user starts the virtual assistant, the electronic device can acquire the first interface information about to be displayed based on the operation of the user starting the virtual assistant. If the first interface information contains a biological image corresponding to the virtual assistant, the electronic device can start the camera to capture the user image. At this time, the biological image about to be displayed in the first interface information is the first image.

[0159] The above are several exemplary scenarios in which the electronic device acquires the user image according to the embodiments of the present application. Of course, for other scenarios, the electronic device can also refer to the above implementation manners, and in the case that the content about to be displayed contains a biological image, the electronic device can start the camera to capture the user image.

[0160] In some other embodiments, the electronic device can also acquire the user image at a preset time interval. For example, the electronic device can start the camera to capture the user image at a preset time interval. Alternatively, the electronic device can acquire the user image stored in the electronic device in advance by the user at a preset time interval.

[0161] It should be noted that in the embodiments of the present application, the operation of the electronic device acquiring the user image is performed with the authorization of the user. That is, the electronic device has informed the user that the biological image is to be updated by acquiring the user image through the prompt information, and has obtained the permission of the user before acquiring the user image.

[0162] At step 402, the electronic device obtains a second image based on the user image and the first image, the second image including a second avatar, the second avatar including a second costume, the second costume having one or more of the at least one costume feature.

[0163] The first avatar and the second avatar can be a human avatar or an animal avatar. Alternatively, the first avatar and the second avatar can be other biological avatars, such as a fairy. In addition, the first avatar and the second avatar can be virtual avatars or real avatars.

[0164] In addition, the first avatar can be a biological avatar in the content to be displayed. For example, the first avatar can be an avatar included in first interface information to be displayed corresponding to a first operation of the user detected by the electronic device. For example, the first avatar can be a virtual owl avatar obtained by the electronic device from interface information of a second page in a desktop when the user switches from a first page to the second page in the desktop. Alternatively, the first avatar can be an avatar included in wallpaper of the desktop obtained by the electronic device when the user enters the desktop. Alternatively, the first avatar can be an avatar included in interface information to be displayed obtained by the electronic device when the user starts a virtual assistant.

[0165] Alternatively, if the electronic device obtains the user image at a preset time interval, the first avatar can be an avatar included in any biological avatar-based application installed in the electronic device.

[0166] In addition, the first avatar can be an initial avatar that has not been updated based on the user image. In this case, the first avatar can include a costume or can not include a costume. Alternatively, the first avatar can be an avatar updated by the method provided in the embodiments of the present application, for example, an avatar updated based on a user image at the last time before the current time. In this case, the costume of the first avatar can be generated based on a costume in the last user image.

[0167] If the first avatar is an initial avatar that has not been updated based on the user image, the first avatar can be a real or virtual biological avatar uploaded by the user or sent by another device received by the electronic device. Alternatively, the first avatar can be an avatar generated based on a first image provided by the electronic device using an artificial intelligence generated content (AIGC) technology before the current time. The first image includes a human image and / or an animal image. For example, when the user sets a pet widget on the desktop of the electronic device, the electronic device can collect a pet image. Then, the electronic device can obtain a corresponding first avatar based on the pet image using the AIGC technology.

[0168] Specifically, in some embodiments, the electronic device can generate the first image corresponding to the first image through the cloud server. For example, referring to FIG. 6, the process can include the following steps:

[0169] S601: The electronic device sends the first image to the cloud server.

[0170] In some possible implementations, the electronic device can also generate an image description text corresponding to the first image based on the first image, and send the image description text and the first image to the cloud server.

[0171] For example, the electronic device can be deployed with an image description generation model. The electronic device can input the first image into the image description generation model, so as to output a corresponding image description text from the image description generation model, which is used to describe the character or animal in the first image. For example, the first image is an image of a white cat, and after identifying the first image through the image description generation model, the output image description text can be: a white cat.

[0172] S602: The cloud server generates the first image based on the first image.

[0173] In the first case, if the electronic device sends the first image but does not send the image description text corresponding to the first image, the cloud server can generate the corresponding image description text and the composition data based on the first image, and then generate the first image based on the image description text and the composition data corresponding to the first image.

[0174] For example, referring to FIG. 7, the cloud server can be deployed with a controlnet model, a BLIP model and an SD model. Based on this, after receiving the first image, the cloud server can input the first image into the controlnet model and the BLIP model respectively. The first image is processed through the controlnet model, so as to output the composition data of the first image, and the first image is processed through the BLIP model, so as to output the image description text of the first image. Then, the composition data and the image description text of the first image are input into the SD model, and the composition data and the image description text of the first image are processed by the SD model, so as to output the first image.

[0175] The controlnet model can identify the posture and contour of the person or animal in the first image, and output the composition data of the first image. The composition data of the first image can include the contour map and the posture data of the person or animal in the first image. For example, referring to FIG. 7, the first image is an image of a cat. After the controlnet model identifies the first image, the controlnet model can output the contour map of the cat and the posture data of the cat in the first image.

[0176] Optionally, the controlnet model can further predict the posture data of the person or animal in the first image based on the identified posture data, and obtain at least one posture data set. Correspondingly, the composition data of the first image can include the at least one posture data set. Each posture data set can include a plurality of posture data obtained by prediction, and in addition, can include the posture data identified from the first image. In addition, the plurality of posture data in each posture data set can be used to represent a group of continuous actions or postures.

[0177] It should be noted that the controlnet model can randomly predict the posture data of the first image based on the identified posture data. Alternatively, the cloud server can also receive the action prompt word sent by the electronic device together with the first image, and predict based on the action prompt word and the identified posture data of the first image. The action prompt word can be used to indicate the action of the desired image.

[0178] The BLIP model can identify the detailed information of the person or animal in the first image, and output the image description text corresponding to the first image. For example, referring to FIG. 7, the image description text corresponding to the first image output by the BLIP model after identifying the first image can be: a white, fat cat.

[0179] After receiving the composition data and the image description text of the first image, the SD model fuses the composition data and the image description text of the first image, and outputs the first image. For example, referring to FIG. 7, the SD model can generate a white cat image with a posture consistent with the posture of the cat in the first image according to the contour map of the cat, the posture data and the image description text.

[0180] It should be noted that if the image description text of the first image does not include clothing information, the first image generated by the SD model can not have clothing or have default clothing. The default clothing can be generated by the SD model based on preset clothing information. If the image description text of the first image includes clothing information, the first image can have the clothing described by the clothing information.

[0181] Optionally, if the composition data output by the controlnet model includes at least one pose data set, the SD model can further fuse the plurality of pose data in each pose data set, the image description text and the contour map to obtain a first image group corresponding to the plurality of pose data in each pose data set. The first image group includes a plurality of first images representing the poses represented by the plurality of pose data in the corresponding pose data set. In this way, the plurality of first images in the first image group can be displayed in a certain order to form an animation. On this basis, when there are a plurality of pose data sets, a plurality of first image groups can be obtained based on the plurality of pose data sets, and the plurality of first image groups will form a plurality of animations. Of course, the SD model can also select one pose data set from the composition data, and fuse the plurality of pose data sets in the selected pose data set with the image description text and the contour map to obtain the first image group corresponding to the pose data set.

[0182] Optionally, in some possible implementations, the cloud server can also be deployed with at least one LoRA model trained based on the SD model, and each LoRA model can provide a style parameter of an image style for the SD model. Based on this, the SD model can also fuse the composition data and the image description text of the first image based on the style parameter provided by the specified LoRA model to obtain the first image corresponding to the image style.

[0183] Specifically, the specified LoRA model can be a LoRA model set by default on the cloud server.

[0184] Alternatively, the specified LoRA model can also be a LoRA model specified by the user of the electronic device. For example, the electronic device can also send image style information expected by the user when sending the first image to the cloud server. On this basis, the cloud server can determine the LoRA model that can provide the style parameter of the image style based on the image style information. At this time, the LoRA model is the specified LoRA model.

[0185] In the second case, if the electronic device sends the first image and the corresponding image description text, the cloud server can generate the corresponding composition data based on the first image, and then generate the first image based on the image description text and the composition data corresponding to the first image.

[0186] In a possible implementation, the cloud server can input the first image into the controlnet model. The first image is processed by the controlnet model, and composition data of the first image is output. Then, the composition data of the first image and the image description text are input into the SD model, and the composition data of the first image and the image description text are processed by the SD model, and the first image is output.

[0187] It should be noted that in this implementation, unlike the first case, the cloud server can no longer use the BLIP model to process the first image, and the remaining implementations can refer to the related description in the first case.

[0188] In another possible implementation, the cloud server can input the first image into the controlnet model. The first image is processed by the controlnet model, and composition data of the first image is output. In addition, the cloud server can also adjust the image description text corresponding to the first image. Then, the composition data of the first image and the adjusted image description text are input into the SD model, and the composition data of the first image and the adjusted image description text are processed by the SD model, and the first image is output.

[0189] The cloud server can obtain the basic prompt text corresponding to the SD model, and fuse the basic prompt text and the image description text of the first image to obtain an adjusted image description text that is easier for the SD model to understand.

[0190] It should be noted that in this implementation, the related processing of the controlnet model and the SD model can refer to the introduction in the first case, and will not be repeated here.

[0191] In addition, after the cloud server generates the first image by any of the above-mentioned manners, the cloud server can also store the composition data of the first image and the image description text obtained when the SD model generates the first image corresponding to the first image.

[0192] S603: The cloud server sends the first image to the electronic device.

[0193] If the cloud server generates a first image of a posture, the first image is sent to the electronic device. If one or more first image groups are generated, the cloud server can send one or more first image groups to the electronic device, and each first image group contains a first image of multiple postures.

[0194] Optionally, in some possible implementation manners, the cloud server can also generate a corresponding reference animation based on each first image group, and send the generated one or more reference animations to the electronic device. The reference animation corresponding to any first image group includes the first images in multiple postures in the first image group, and in addition, can include a decoration element. The decoration element in any reference animation can be a decoration element in a certain specific scene, and accordingly, any reference animation can also correspond to a scene label to indicate that the corresponding reference animation is an animation in the scene indicated by the scene label. After receiving the one or more reference animations and the corresponding scene labels, the electronic device can store the one or more reference animations and the corresponding scene labels as reference composition data corresponding to the first image.

[0195] Of course, the steps of generating a reference animation and setting a scene label by the cloud server described above can also be performed by the electronic device, which is not limited herein.

[0196] Optionally, in some possible implementation manners, the cloud server can also send the composition data obtained in the process of generating the first image to the electronic device.

[0197] For example, when the composition data of the first image generated by the cloud server includes at least one posture data set, the cloud server can also send the at least one posture data set to the electronic device together with the first image, and accordingly, the electronic device can store the at least one posture data set as reference composition data after receiving the at least one posture data set, and store the first image corresponding to the reference composition data.

[0198] The above is the process of obtaining a first image by an electronic device provided by an embodiment of the present application in cooperation with a cloud server. In some possible cases, there can also be various models in the cloud server in the electronic device, and in this case, the electronic device can generate a first image based on a first image independently, and the related implementation process can be referred to the above description.

[0199] After obtaining the user image, the electronic device can obtain a second image based on the user image and the above-mentioned existing first image.

[0200] In some embodiments, the electronic device can obtain a second image through a cloud server. For example, referring to FIG. 8, the process can include the following steps:

[0201] S801: The electronic device sends user clothing information and a first image to a cloud server, the user clothing information including a user image or a first clothing description text, and the first clothing description text being obtained based on the user image.

[0202] The electronic device can determine user clothing information based on the user image, and then send the user clothing information and the first avatar to the cloud server.

[0203] The first avatar can or can not include clothing. In addition, when there is one or more first avatar groups in the electronic device, the electronic device can send the first avatar in at least one posture in any first avatar group to the cloud server.

[0204] In addition, the electronic device can determine the user image as the user clothing information.

[0205] Optionally, the electronic device can generate a first clothing description text based on the user image, and then determine the first clothing description text as the user clothing information.

[0206] Specifically, the electronic device can be deployed with a clothing model. The electronic device can input the user image into the clothing model, identify the first clothing in the user image through the clothing model, and output a first clothing description text describing at least one clothing feature of the first clothing.

[0207] For example, the user in the user image obtained by the electronic device wears a gray checkered knit jacket. The first clothing description text output by identifying the first clothing in the user image through the clothing model can be: gray checkered knit jacket.

[0208] It should be noted that in the embodiments of the present application, the first avatar sent by the electronic device to the cloud server can be an image containing the first avatar, for example, a wallpaper containing the first avatar. Of course, the first avatar can also be a separate avatar.

[0209] Optionally, in one possible case, when the electronic device sends the user clothing information and the first avatar to the cloud server, it can also send current scene data or a scene label to the cloud server, so that the cloud server can add corresponding decoration elements to the second avatar based on the scene data or the scene label in the process of generating the second avatar. The scene data or the scene label can be used to indicate the external scene and / or the internal scene currently in the electronic device.

[0210] In one example, the scene data can include external scene data and / or internal scene data. The external scene data is used to indicate the external scene, and the internal scene data is used to indicate the internal scene.

[0211] The external scene can refer to a scene of an external physical world. For example, the external scene can include weather conditions, temperature, time, and the like of the physical world. Based on this, the external scene data can include current weather data, temperature data, time data, and the like. In the embodiments of the present application, the electronic device can obtain the external scene data through its own application or sensor.

[0212] The internal scene can refer to a state of the electronic device or a state of a user of the electronic device indicated by application data in the electronic device. Based on this, the internal scene data can include the application data in the electronic device. For example, the internal scene data can include uncompleted order data in a take-out application in the electronic device, through which it can be indicated that the user is currently in a hungry state. For another example, the internal scene data can include running information of a music application in the electronic device, through which it can be determined that the user is currently listening to music.

[0213] Based on this, the electronic device can directly send the above-mentioned external scene data and / or internal scene data to the cloud server. Alternatively, the electronic device can also store a mapping relationship between the scene data and the corresponding scene label, where the mapping relationship can be a mapping table of one scene data and a scene label. Alternatively, the mapping relationship can be realized through a scene calculation model, where the scene calculation model can be a preset function or an AI model trained by using scene data samples and corresponding scene labels. Based on this, the electronic device can determine the scene label corresponding to the current scene data based on the mapping relationship, and then send the current scene label to the cloud server.

[0214] S802: The cloud server generates a second image based on the user clothing information and the first image.

[0215] As known from the foregoing, the first image can or can not include clothing. Based on this, after receiving the user clothing information and the first image, the cloud server can update the clothing of the first image or add clothing to the first image based on the user clothing information, thereby obtaining the second image, which includes second clothing, and the second clothing conforms to the user clothing information.

[0216] Specifically, as known from the foregoing in S801, the user clothing information sent by the electronic device can have different implementation manners, and correspondingly, the implementation manners of the cloud server for generating the second image based on the user clothing information and the first image are also different.

[0217] Manner 1: If the user costume information includes a user image and does not include the first image description text, the cloud server can obtain the second costume description text based on the user image; obtain the first image corresponding composition data and image description text based on the first image; and generate the second image based on the second costume description text, the first image corresponding composition data and image description text.

[0218] As an example, a clothing model can be deployed in the cloud server. The cloud server can input the user image into the clothing model, identify the first costume in the user image through the clothing model, and output the second costume description text for describing at least one costume feature possessed by the first costume.

[0219] As another example, as introduced in the foregoing S602, the cloud server can be deployed with a BLIP model. In this case, the BLIP model can also have the function of identifying costume information in an image. Based on this, the cloud server can use the BLIP model to identify the first costume in the user image, and output the second costume description text.

[0220] In addition, the cloud server can also obtain the first image corresponding composition data and image description text based on the first image.

[0221] In a possible implementation, if the first image is generated by the cloud server, the cloud server can store the composition data and image description text used by the SD model when generating the first image. Based on this, the cloud server can obtain the composition data and image description text stored by itself when generating the first image based on the first image. The composition data used when generating the first image can include posture data, for example, can include at least one posture data set.

[0222] For example, if the first image is an initial image generated by the cloud server based on the first image, the cloud server can store the composition data and image description text of the first image used when generating the first image. In this case, the cloud server can obtain the composition data and image description text of the first image, and use the composition data and image description text of the first image as the first image corresponding composition data and image description text.

[0223] For another example, if the first image is updated based on the last user image collected by the cloud server, the cloud server can also store the composition data and image description text of the last image used by the SD model when generating the first image, and in this case, the cloud server can use the composition data and image description text as the composition data and image description text of the first image.

[0224] In another possible implementation, the cloud server can also directly input the received first image into the controlnet model and the BLIP model respectively, identify the contour and the pose of the first image by using the controlnet model, so as to obtain the composition data corresponding to the first image, and identify the image details of the first image by using the BLIP model, so as to obtain the image description text of the first image.

[0225] Optionally, the controlnet model can not only identify the pose of the first image, so as to obtain the pose data of the first image, but also predict based on the identified pose of the first image, so as to obtain at least one pose data set. Based on this, the composition data corresponding to the first image can not only include the pose data of the identified first image, but also include at least one pose data set corresponding to the first image. Each pose data set includes a plurality of pose data, and each pose data is used to represent a pose. In this way, the plurality of pose data in one pose data set can be used to represent a group of consecutive actions or poses. In addition, the implementation of the controlnet model predicting based on the identified pose of the first image can refer to the related description in the foregoing step 602.

[0226] After obtaining the second clothing description text, the composition data corresponding to the first image and the image description text, the cloud server can generate a second image based on the second clothing description text, the composition data corresponding to the first image and the image description text.

[0227] In a possible implementation, the cloud server can input the second clothing description text, the composition data corresponding to the first image and the image description text into the SD model, and perform fusion processing on the above information by using the SD model, so as to generate a second image that conforms to the second clothing description text and has a contour, a pose and an image similar to the first image.

[0228] In this case, the second image includes the second clothing having one or more of the at least one clothing feature of the first clothing described in the second clothing description text.

[0229] Specifically, the second clothing has the clothing color feature of the first clothing. In this case, the clothing color of the second clothing can be determined according to the clothing color feature of the first clothing.

[0230] In the first example, the clothing color of the second clothing can be the same as or opposite to the clothing color of the first clothing.

[0231] Specifically, the garment color of the second garment can be the same as the garment color of the first garment can mean that the second garment and the first garment contain the same or similar hue. Hue refers to the appearance of a color, which is an attribute of a color and is different colors that can be perceived by the human eye under the irradiation of light of different wavelengths. For example, hue includes red, orange, yellow, blue, green, and the like. Different hues can form a hue ring, and the smaller the angle between two hues in the hue ring, the smaller the difference between the two hues. Based on this, any two hues that are the same or similar can mean that the angle between the two hues on the hue ring is within a first angle range, for example, the first angle range can be -30 degrees to 30 degrees, at which time the visual difference between the two hues is small. For example, the first garment contains red and yellow, and the second garment can also contain red or yellow; or the second garment can contain a hue similar to red and a hue similar to yellow, for example, the second garment can contain orange-red and yellow-green.

[0232] Alternatively, the garment color of the second garment can be the same as the garment color of the first garment can also mean that the garment main color of the second garment and the first garment is the same or similar. Among them, the garment main color refers to the color with the largest area ratio in the garment. For example, the garment main color of the first garment is yellow, and the garment main color of the second garment can be yellow-green.

[0233] The garment color of the second garment can be opposite to the garment color of the first garment can mean that the second garment and the first garment contain opposite hues. Among them, any two opposite hues can mean that the angle between the two hues on the hue ring is within a second angle range, for example, the second angle range is -120 degrees to 120 degrees, at which time the visual difference between the two hues is large. For example, the first garment contains red and yellow, and the second garment contains cyan which is opposite to red and blue which is opposite to yellow.

[0234] Alternatively, the garment color of the second garment can be opposite to the garment color of the first garment can also mean that the hue of the garment main color of the second garment and the first garment is opposite. For example, the hue of the garment main color of the first garment is red, and the hue of the garment main color of the second garment is cyan which is opposite to red.

[0235] In the second example, the garment color at the first body part in the second garment can be the same as the garment color at the first body part in the first garment. That is, the garment color at the same body part in the second garment and the first garment can be the same.

[0236] Specifically, the hue of the garment main color at the same body part in the second garment and the first garment can be the same or similar. For example, the garment main color of the abdomen in the first garment is yellow, and the garment main color of the back is white, and the garment main color of the abdomen in the second garment is also yellow, and the garment main color of the back is also white.

[0237] Alternatively, the garment at the same body part in the second garment and the first garment contains the same or similar hue. For example, the garment of the abdomen of the first garment has two colors, which are red and yellow, and the garment of the abdomen of the second garment also contains red and yellow.

[0238] In a third example, the garment hue of the second garment can be the same or opposite to the garment hue of the first garment. Wherein, the garment hue refers to the overall summary of the garment color, that is, the basic tendency of the garment color. Specifically, according to the two attributes of hue and lightness included in the color, the hue can include cool tone, intermediate tone and warm tone. For example, when the red, yellow or orange color in the garment accounts for a large proportion, the garment hue is warm, and in this case, the higher the lightness, the warmer the hue. When the blue color in the garment accounts for a large proportion, the garment hue is cold, and the lower the lightness, the colder the hue. When the green or white color in the garment accounts for a large proportion, the garment hue is intermediate. Based on this, when the garment hue of the first garment is warm, the garment hue of the second garment can be warm or the opposite cold. When the garment hue of the first garment is cold, the garment hue of the second garment can be the same cold or the opposite warm. When the garment hue of the first garment is intermediate, the garment hue of the second garment is intermediate.

[0239] Optionally, the second garment can have the garment pattern feature of the first garment, and in this case, the garment pattern in the second garment can be determined according to the garment pattern feature of the first garment.

[0240] Specifically, the second garment can include part or all of the garment pattern in the first garment. For example, if the garment pattern of the first garment can be completely identified, the garment pattern of the second garment can include the largest pattern in the garment pattern of the first garment. If the garment pattern of the first garment is partially identified and partially blocked and cannot be identified, the garment pattern of the second garment can include the identified part of the garment pattern of the first garment. In addition, it can also include the part that is intelligently supplemented based on the identified part, that is, the garment pattern of the second garment is a complete pattern obtained by intelligently supplementing the garment pattern of the first garment based on the identified part.

[0241] Alternatively, the clothing pattern in the second outfit is similar to the clothing image in the first outfit. For example, the clothing pattern in the second outfit can be redrawn, sketched or regenerated according to the clothing pattern features of the first outfit, so that the clothing pattern of the second outfit has visual similarity with the clothing pattern of the first outfit. For example, the clothing pattern of the first outfit is plaid, and the clothing pattern in the second outfit can also be plaid, but the plaid of the two can be plaid of different shapes.

[0242] Optionally, the second outfit can have the accessory features of the first outfit, wherein the accessory features can include at least one of an accessory material feature, an accessory shape feature, an accessory color feature and an accessory style feature, that is, the accessories in the second outfit can be determined based on the accessory features in the first outfit.

[0243] Specifically, the second outfit can include at least one accessory having the accessory features of the first outfit. For example, the accessories in the second outfit are of the same material, the same shape or similar shape, the same style or similar style, and the same color or opposite color as the accessories in the first outfit.

[0244] Optionally, the accessory features can also include the wearing position of the accessories. Based on this, the wearing position of any accessory in the second outfit corresponds to the wearing position of the corresponding accessory in the first outfit. For example, the first outfit includes a first accessory, and the second outfit includes a second accessory having the accessory features of the first accessory, in which case the wearing position of the first accessory on the user and the wearing position of the second accessory on the second image can be the same.

[0245] Optionally, in some possible cases, the accessory features can also include the accessory type, in which case any accessory included in the second outfit is an accessory matching the image type of the second image. For example, the accessory type in the first outfit includes glasses, and the second image is a virtual pet image, at this time, the accessory of glasses does not match the virtual pet image, so the second outfit can not include the accessory of glasses. For another example, the accessories in the first outfit also include a hat, and the hat matches the virtual pet image, therefore, the second outfit can include the accessory of the hat, and in the first outfit, the hat is worn on the head of the user, so the head of the second image can also wear the hat. It should be noted that the hat in the second outfit can be the same as or different from the hat in the first outfit.

[0246] Optionally, the second garment can have the garment style feature and / or the garment material feature and / or the garment style feature of the first garment, that is, the garment style, the garment material and / or the garment style of the second garment can be determined based on the corresponding features of the first garment. For example, the garment style and / or the garment material and / or the garment style in the second garment can be the same as the garment style and / or the garment material and / or the garment style in the first garment. For example, the garment style of the first garment is Tang suit, and the garment style of the second garment is also Tang suit; the garment material of the first garment is knitted, and the garment material of the second garment is also knitted, and the garment style of the first garment is a dress, and the garment style of the second garment is also a dress.

[0247] In addition, as introduced in the foregoing, the composition data corresponding to the first image can include at least one posture data set. Based on this, at least one second image group can be generated based on the at least one posture data set, wherein each second image group includes a second image having multiple postures.

[0248] In another possible implementation, the cloud server can reorganize the second garment description text and the image description text corresponding to the first image to obtain a comprehensive description text. At this time, the comprehensive description text includes not only the image description information of the first image, but also the description information of at least one garment feature possessed by the first garment. On this basis, the cloud server can input the composition data corresponding to the first image and the comprehensive description text into the SD model, and perform fusion processing on the composition data and the comprehensive description text by the SD model, so as to output a second image conforming to the second garment description text, and having a contour, a posture and an image close to the first image.

[0249] For example, referring to FIG. 9, the user in the user image 90 wears a knitted coat with checks, the first image 91 is a white cat, and correspondingly, the second garment description text is: knitted coat with checks, the image description text of the first image is: a white cat, and the comprehensive description text obtained after reorganization can be: a white cat wearing a knitted coat with checks. The SD model can generate the second image 92 as shown in FIG. 9 based on the comprehensive description text.

[0250] Optionally, if the electronic device not only sends the user garment information and the first image, but also sends the current scene data or the scene label, the cloud server can also obtain the corresponding decoration element based on the scene data or the scene label. Then, the cloud server can generate a second image based on the obtained second garment description text, the composition data and the image description text corresponding to the first image, and the obtained decoration element, and in this case, the second image not only includes the second garment, but also includes the decoration element corresponding to the current scene data or the scene label.

[0251] In a possible implementation, the cloud server can store different decoration elements corresponding to different scene labels. If the electronic device sends current scene data, the cloud server can determine a corresponding scene label based on the scene data, and then obtain the decoration element corresponding to the current scene label. If the electronic device sends a current scene label, the cloud server can directly obtain the corresponding decoration element based on the scene label.

[0252] The cloud server can also store a mapping relationship between scene data and corresponding scene labels in the cloud server. The mapping relationship can be a mapping table of scene data and scene labels. Alternatively, the mapping relationship can be implemented by a scene calculation model. The scene calculation model can be a preset function or an AI model trained using scene data samples and corresponding scene labels. Based on this, the cloud server can determine the scene label corresponding to the current scene data by using the mapping relationship.

[0253] It should be noted that, in a possible implementation, the decoration element corresponding to a scene label can include images of things that can appear in the corresponding scene. For example, when the scene data is weather data, and the scene label corresponding to the weather data is a rainy day, the decoration element corresponding to the scene label can include an umbrella and raindrops. For another example, when the scene data is uncompleted order data in a takeout application in the electronic device, and the uncompleted order data corresponds to a scene label of waiting for lunch, the decoration element corresponding to the scene label can include tableware and the like. For another example, when the scene data is running information of a music application in the electronic device, and the running information corresponds to a scene label of listening to music, the decoration element corresponding to the scene label can include earphones, microphones, and the like.

[0254] After the cloud server obtains the decoration element corresponding to the current scene, the cloud server can input the second clothing description text, the composition data and the image description text corresponding to the first image, and the decoration element into the SD model, and perform fusion processing on the above information by the SD model, so as to generate a second image that conforms to the second clothing description text, and has a contour, a posture, and an image similar to the first image, and has a decoration element suitable for the current scene. Alternatively, the cloud server can also reorganize the second clothing description text and the image description text corresponding to the first image, so as to obtain a comprehensive description text. Then, the cloud server inputs the composition data corresponding to the first image, the comprehensive description text, and the decoration element corresponding to the current scene into the SD model, and performs fusion processing on the composition data, the comprehensive description text, and the decoration element by the SD model, so as to output a second image that conforms to the second clothing description text, and has a contour, a posture, and an image similar to the first image, and has a decoration element suitable for the current scene.

[0255] In another possible implementation, the cloud server can store different decoration element description texts corresponding to different scenario labels, where the decoration element description texts are used to describe things that can appear in the corresponding scenarios. In this case, after obtaining the current scenario label, the cloud server can obtain the decoration element description text corresponding to the scenario label. Then, the cloud server can input the decoration element description text corresponding to the current scenario label, the second clothing description text, the composition data corresponding to the first image, and the image description text of the first image into the SD model, and the SD model fuses the above information to generate the second image that conforms to the second clothing description text, has similar contour, posture, and image as the first image, and has decoration elements that are suitable for the current scenario. Alternatively, the cloud server can reorganize the decoration element description text corresponding to the current scenario label, the second clothing description text, and the image description text of the first image to obtain a comprehensive description text. Then, the cloud server inputs the composition data corresponding to the first image and the comprehensive description text into the SD model, and the SD model fuses the composition data and the comprehensive description text to output the second image that conforms to the second clothing description text, has similar contour, posture, and image as the first image, and has decoration elements that are suitable for the current scenario.

[0256] For example, when the current scenario is a rainy day, as shown in FIG. 10, the second image output by the SD model can be a cat standing in the rain and holding an umbrella. When the current scenario is waiting for eating, as shown in FIG. 11, the second image output by the SD model is a cat squatting beside a cat food bowl and waiting for eating. When the current scenario is listening to music, as shown in FIG. 12, the second image output by the SD model is a cat singing in front of a microphone with earphones.

[0257] Method 2: If the user clothing information sent by the electronic device includes the first clothing description text, the cloud server can obtain the composition data and the image description text corresponding to the first image based on the first image, and generate the second image based on the first clothing description text, the composition data, and the image description text corresponding to the first image. The first clothing description text is used to describe at least one clothing feature of the first clothing in the user image.

[0258] That is, in the case where the user clothing information sent by the electronic device includes the first clothing description text, the cloud server can no longer identify the first clothing in the user image, but directly use the first clothing description text sent by the electronic device to generate the second image in combination with the composition data and the image description text of the first image.

[0259] The implementation of the cloud server obtaining the composition data of the first image and the image description text can refer to the related description in mode 1, and the implementation of the cloud server generating the second image based on the first clothing description text, the composition data and the image description text of the first image can refer to the description of generating the second image based on the second clothing description text, the composition data and the image description text of the first image in mode 1, and details are not repeated here.

[0260] S803: The cloud server sends the second image to the electronic device.

[0261] If the cloud server generates a second image with one pose, the second image is directly sent to the electronic device. Alternatively, if the cloud server generates at least one second image group, the at least one second image group can be sent to the electronic device, wherein each second image group includes second images with multiple poses, which can be presented as a group of continuous actions or poses, and correspondingly, the second images with multiple poses can be presented as an animation.

[0262] Alternatively, in some possible implementations, the cloud server can also generate a corresponding reference animation based on each second image group, and send the generated one or more reference animations to the electronic device. The reference animation corresponding to any second image group includes the second images with multiple poses in the second image group. In addition, the reference animation can also include decoration elements. The decoration elements in any reference animation can be decoration elements in a certain specific scene, wherein the specific scene can be the current scene if the electronic device provides current scene data or a scene label, or the specific scene can be any of the multiple scenes indicated by the multiple scene labels stored in the cloud server if the current scene data or the scene label is not provided. Correspondingly, any reference animation can also correspond to a scene label to indicate that the corresponding reference animation is an animation in the scene indicated by the scene label. After receiving the one or more reference animations and the corresponding scene labels, the electronic device can store the one or more reference animations and the corresponding scene labels as the reference composition data corresponding to the second image for subsequent use when updating the second image.

[0263] Of course, the steps of the cloud server generating the reference animation corresponding to the second image group and setting the scene label can also be performed by the electronic device, which is not limited here.

[0264] Optionally, in some possible implementation manners, if the cloud server obtains the composition data by recognizing the pose of the first image and making a prediction when generating the second image, the cloud server can further send the composition data obtained in the process of generating the second image to the electronic device. The composition data includes at least one pose data set, and accordingly, the electronic device can store the composition data as the reference composition data corresponding to the second image after receiving the composition data.

[0265] The above S801 to S803 mainly introduce the process in which the electronic device obtains the second image through the cloud server. In some other embodiments, the electronic device can also have the models in the cloud server, and in this case, the electronic device can generate the second image based on the first image of the user independently. The related implementation process can refer to the introduction in S801 to S803.

[0266] Step 403: The electronic device displays the second image.

[0267] After receiving the second image sent by the cloud server, the electronic device can replace the first image with the second image, and display the second image in the corresponding interface.

[0268] In the first possible scenario, the first image is an image in a certain page included in the desktop of the electronic device in the foregoing step 401. In this case, the electronic device can directly replace the first image in the interface information of the page with the second image, and refresh the page based on the updated interface information when the interface is refreshed, so as to display the second image.

[0269] In the second possible scenario, the first image is an image in the first wallpaper set on the desktop of the electronic device. In this case, the electronic device can display a second wallpaper based on the second image and the first wallpaper, where the second wallpaper includes the second image.

[0270] In some embodiments, if the first wallpaper is a static wallpaper, the electronic device can directly replace the first image in the first wallpaper with the second image to obtain a second wallpaper. Then, the second wallpaper is displayed.

[0271] Specifically, the first wallpaper can include an image layer, a decoration layer and a background layer, where the background layer contains a background image, the image layer contains an image, and the decoration layer contains other images except the background image and the image. Based on this, in the embodiments of the present application, the electronic device can replace the first image contained in the image layer in the first wallpaper with the second image, so as to obtain a second wallpaper.

[0272] Optionally, after replacing the first image included in the image layer in the first wallpaper with the second image, the electronic device can further adjust the layer relationship between the image layer and the decoration layer, so that the second image in the second wallpaper can be more stereoscopic.

[0273] After obtaining the second wallpaper, if the electronic device is currently displaying the first wallpaper, the electronic device can refresh the displayed first wallpaper to the second wallpaper. Optionally, if the electronic device is not currently displaying the desktop, the electronic device can directly display the second wallpaper on the desktop after detecting the operation of the user entering the desktop.

[0274] It is worth noting that in the embodiments of the present application, after the electronic device displays the second wallpaper on the desktop, if the electronic device subsequently performs a lock screen operation or enters an application interface of an application in response to a user operation, the electronic device can continue to collect a user image and update the second image in the second wallpaper based on the user image to obtain a third image by the method described above after detecting the operation of the user entering the desktop again, and then display a wallpaper containing the third image. Of course, in some possible implementations, considering that the frequency of changing the user's clothes of the current user can be much lower than the frequency of the user performing the operation of entering the desktop, in the embodiments of the present application, when the electronic device collects the user image again, the electronic device can also analyze whether the clothes in the user image detected again are the same as the first clothes in the user image used to generate the second image, and if so, the electronic device can end the operation, that is, not perform the operation of updating the second clothes based on the user image.

[0275] In another possible case, after the electronic device displays the second wallpaper on the desktop, the user can switch between multiple pages contained in the desktop, in which case, since the electronic device is always displaying the interface of the desktop in the process of the user switching, the electronic device can not update the second image in the second wallpaper in this case.

[0276] In another embodiment, if the first wallpaper is a dynamic wallpaper and the cloud server sends one or more second image groups to the electronic device, the electronic device can directly select a target image group from the one or more second image groups, replace the first image group in the first wallpaper with the second image group, thereby obtaining a second wallpaper, set the second wallpaper as the current wallpaper, and display the second wallpaper.

[0277] Optionally, in the case where the first wallpaper is a dynamic wallpaper, if the cloud server sends a single second image to the electronic device, the electronic device can update the first wallpaper to the second wallpaper containing the second image by S1301 to S1303 shown in FIG. 13.

[0278] S1301: Obtain first composition data corresponding to the first wallpaper, the first composition data being used to represent a plurality of first poses.

[0279] The dynamic wallpaper can include a plurality of pictures, which when displayed in sequence will present an animation. Based on this, in the case that the first wallpaper is a dynamic wallpaper, the first wallpaper will include a plurality of pictures, and each picture will include a first image with a pose. In this way, when the plurality of pictures are displayed in sequence, the first images with different poses in the plurality of pictures will present a coherent action.

[0280] Based on this, in a possible implementation, the electronic device can be deployed with a controlnet model. The electronic device can use the controlnet model to identify the pose of the first image in each picture in the first wallpaper, thereby obtaining first composition data. The first composition data can include a set of pose data of the identified first image, and the set of pose data includes a plurality of pose data, each pose data being used to represent a pose of the first image.

[0281] Alternatively, if the second image provided by the cloud server does not have a decoration element corresponding to the current scene, the electronic device can also obtain scene data corresponding to the current scene when using the controlnet model to identify the pose of the first image. The scene data can be used to indicate the external scene and / or the internal scene of the electronic device. Then, based on the scene data, the corresponding decoration element is obtained. On this basis, the first composition data can not only include the set of pose data of the identified first image, but also include the decoration element corresponding to the current scene data. In this way, the second image in the second wallpaper obtained based on the first composition data will have a decoration element corresponding to the current scene data.

[0282] Specifically, the scene data can include external scene data and / or internal scene data. The external scene data is used to indicate the external scene, and the internal scene data is used to indicate the internal scene.

[0283] The external scene can refer to the scene of the external physical world, for example, the external scene can include the weather condition, temperature, time, etc. of the physical world. Based on this, the external scene data can include current weather data, temperature data, time data, etc. In the embodiments of the present application, the electronic device can obtain the external scene data through its own application or sensor.

[0284] The internal scenario can refer to a state of the electronic device or a state of a user of the electronic device indicated by application data in the electronic device. Based on this, the internal scenario data can include the application data in the electronic device. For example, the internal scenario data can include uncompleted order data in a takeout application in the electronic device, through which it can be indicated that the user is currently in a hungry state. For another example, the internal scenario data can include running information of a music application in the electronic device, through which it can be determined that the user is currently listening to music.

[0285] The electronic device can store different decoration elements corresponding to different scenario labels. Based on this, the electronic device can obtain a scenario label corresponding to the current scenario data, and then obtain the corresponding decoration element based on the scenario label.

[0286] The electronic device can store a mapping relationship between the scenario data and the corresponding scenario label, and determine the scenario label corresponding to the current scenario data based on the mapping relationship. The mapping relationship can be a mapping table of one scenario data and a scenario label. Alternatively, the mapping relationship can be implemented through a scenario calculation model, where the scenario calculation model can be a preset function or an AI model trained using scenario data samples and corresponding scenario labels.

[0287] In addition, it should be noted that the decoration element corresponding to a certain scenario label can include images of things that can appear in the corresponding scenario. For example, when the scenario data is weather data, and the scenario label corresponding to the weather data is a rainy day, the decoration element corresponding to the scenario label can include an umbrella and raindrops. For another example, when the scenario data is uncompleted order data in a takeout application in the electronic device, and the scenario label corresponding to the uncompleted order data is waiting for lunch, the decoration element corresponding to the scenario label can include tableware, etc. For another example, when the scenario data is running information of a music application in the electronic device, and the scenario label corresponding to the running information is listening to music, the decoration element corresponding to the scenario label can include earphones, microphones, etc.

[0288] In another possible implementation, the electronic device can store reference composition data corresponding to the first wallpaper, and based on this, the electronic device can obtain the first composition data based on the reference composition data corresponding to the first wallpaper.

[0289] In the first example, the reference composition data corresponding to the first wallpaper includes reference composition data corresponding to the first image. The reference composition data corresponding to the first image can be generated when the first image is generated in the first wallpaper based on the method introduced in S601 to S603, or can be obtained in the process of updating the clothing of the previous image of the first image to obtain the first image. The reference composition data corresponding to the first image can include at least one posture data set, and each posture data set includes a plurality of posture data for representing a plurality of reference postures. In this case, the electronic device can obtain a target posture data set from the reference composition data, and use the target posture data set as the first composition data.

[0290] Optionally, in the case that the second image provided by the cloud server does not have a decoration element corresponding to the current scene, the electronic device can further obtain the scene data of the current scene, and then obtain the decoration element corresponding to the scene data, and use the obtained target posture data and decoration element as the first composition data. The implementation of the electronic device obtaining the scene data of the current scene can refer to the foregoing description, and will not be repeated here.

[0291] In the second example, the reference composition data corresponding to the first image can include one or more reference animations. The reference animation can be generated and distributed by the cloud server based on one or more first image groups, or can be generated by the electronic device based on one or more first image groups. Each reference animation includes a first image of a plurality of postures in the corresponding first image group. In this case, the electronic device can randomly obtain a reference animation from the one or more reference animations as the first composition data.

[0292] Optionally, as introduced in the foregoing step 603, the reference animation can further correspond to a scene label. In this case, the electronic device can further obtain the scene data of the current scene, determine the scene label corresponding to the scene data, and then obtain the reference animation corresponding to the scene label from the plurality of reference animations as the first composition data. The electronic device can obtain the scene label corresponding to the scene data based on the foregoing description, and will not be repeated here.

[0293] It should be noted that the reference animation corresponding to any one scene can include the first image in multiple postures in the scene and the corresponding decorative element. For example, when the scene data is weather data, and the scene label corresponding to the weather data is a rainy day, the animation corresponding to the scene label can include a first image in multiple umbrella postures and a corresponding umbrella. At this time, the umbrella is the decorative element in the scene of a rainy day. For another example, when the scene data is the unfinished order data in the take-out application in the electronic device, and the scene label corresponding to the unfinished order data is waiting to eat, the animation corresponding to the scene label can include an image in a posture of waiting to eat and tableware. At this time, the tableware is the decorative element in the current scene.

[0294] In a third example, the reference composition data corresponding to the first wallpaper can include at least one motion data for describing the motion law of the biological image. For example, the motion data can be a function, and each motion data can determine a plurality of reference postures conforming to the motion law. Based on this, the electronic device can randomly obtain one motion data from the at least one motion data as the first composition data.

[0295] Optionally, the electronic device can also obtain the current scene data, and then obtain the decorative element corresponding to the scene data, and obtain the motion data and the decorative element as the first composition data. The implementation of the electronic device obtaining the current scene data can refer to the foregoing description, and will not be described here.

[0296] S1302: generating a second wallpaper based on the first composition data and the second image, the second wallpaper including a plurality of first postures of the second image.

[0297] In the first implementation, the electronic device can adjust the posture of the second image based on the first composition data, so as to obtain a second image group including a plurality of first postures of the second image, and then generate a second wallpaper based on the first wallpaper and the second image group. The plurality of first postures are the postures represented by the first composition data.

[0298] In an example, if the first composition data includes a posture data set for representing a plurality of first postures, the electronic device can adjust the posture of the second image based on the posture data set, so as to obtain a second image group including a plurality of first postures of the second image.

[0299] The electronic device can deploy an SD model, input the posture data set for representing a plurality of first postures and the second image into the SD model, adjust the posture of the second image by using each posture data in the posture data set by the SD model, and output the second image with the first posture represented by each posture data.

[0300] In another example, if the first composition data includes motion data describing a motion rule of the figure, the electronic device can generate a second figure group containing a plurality of second figures of the second figure based on the motion data and the second figure. Each second figure of a different pose in the second figure group will present a coherent action when displayed in sequence, and the motion rule of the second figure will conform to the motion rule described in the motion data in the first composition data.

[0301] The electronic device can input the motion data describing the motion rule of the figure and the second figure into the SD model, and the SD model adjusts the pose of the second figure based on the motion data, thereby outputting a second figure group conforming to the corresponding motion rule.

[0302] Optionally, in the above two examples, if the first composition data further includes a decoration element corresponding to the current scene data, the electronic device can also input the decoration element into the SD model, thereby obtaining a second figure group containing the decoration element in the current scene and a plurality of second figures of the first pose.

[0303] After obtaining the second figure group containing a plurality of second figures of the first pose, the electronic device can replace the plurality of different poses of the first figure in the first figure group in the first wallpaper with the second figures in the corresponding order in the second figure group in sequence, thereby obtaining a second wallpaper. For example, the first figure contained in the figure layer in the first picture in the first wallpaper is replaced with the first second figure in the second figure group, the first figure contained in the figure layer in the second picture in the first wallpaper is replaced with the second second figure in the figure group, and so on.

[0304] Optionally, after replacing the first figure group with the second figure group, the electronic device can also adjust the layer relationship between the figure layer and the decoration layer in the picture to make the second figure in the second wallpaper more stereoscopic.

[0305] In a second possible implementation, if the first composition data includes a reference animation containing a plurality of first figures of the first pose, the electronic device can generate a second wallpaper based on the reference animation and the second figure.

[0306] The electronic device can input the reference animation and the second figure into the SD model, and the SD model can update the first figure in each picture in the animation to the second figure with the corresponding first pose, thereby outputting the second wallpaper.

[0307] For example, the second image is a cat wearing a coat, the first composition data is an animation corresponding to the current scene data, when the current scene data indicates that the current scene is a rainy day, as shown in FIG. 10, the second wallpaper output by the SD model contains a picture of a cat standing in the rain holding an umbrella. When the current scene data indicates that the current scene is waiting for a meal, as shown in FIG. 11, the second wallpaper output by the SD model contains a picture of a cat sitting and waiting for a meal and a cat food bowl. When the current scene data indicates that the current scene is listening to music, as shown in FIG. 12, the second wallpaper output by the SD model contains a picture of a cat singing in front of a microphone with earphones.

[0308] S1303: Display the second wallpaper.

[0309] After generating the second wallpaper, the electronic device can set the second wallpaper as the current wallpaper. And if the electronic device is currently displaying the first wallpaper, the electronic device can refresh the displayed first wallpaper to the second wallpaper. Alternatively, if the electronic device is currently not displaying the desktop, the electronic device can directly display the second wallpaper on the desktop after detecting the operation of the user entering the desktop.

[0310] The above is the implementation process of displaying the second image in two possible scenarios given by the embodiments of the present application. In other scenarios, the electronic device can also refer to the methods introduced above to replace the first image to be displayed or being displayed with the second image, so as to realize the display of the second image. For example, in the display scenario of the virtual image corresponding to the virtual assistant, the current first image corresponding to the virtual assistant can be replaced with the second image, and the second image can be displayed in the process of the user using the virtual assistant.

[0311] In the embodiments of the present application, the user can also interact with the image in the dynamic wallpaper when the electronic device displays the dynamic wallpaper. For example, after displaying the second wallpaper by the method introduced in the above embodiments, subsequently, the electronic device can further update the second wallpaper based on the user's interaction signal by S1304 to S1306 shown in FIG. 13 after detecting the user's interaction signal. Exemplarily, the implementation process of S1304 to S1306 is as follows:

[0312] S1304: In response to the user's interaction signal, based on the reference composition data corresponding to the first wallpaper, obtain second composition data corresponding to the interaction signal, the second composition data being used to represent a plurality of second poses.

[0313] In the embodiments of the present application, the user can interact with the second image in the second wallpaper displayed by the electronic device. The electronic device can detect the interaction signal of the user, and obtain the second composition data from the reference composition data corresponding to the first wallpaper based on the detected interaction signal.

[0314] For example, the user can touch a certain body part of the second image, and the electronic device can detect the touch signal of the user on the display screen through the touch sensor. For another example, the user can interact with the second image through his own movement, and accordingly, the electronic device can detect the movement signal of the user through the gyroscope sensor and / or the acceleration sensor. For another example, the user can also interact with the second image by simulating a certain environment or a certain contact action, and accordingly, the electronic device can detect the ambient light signal through the ambient light sensor, or detect the human contact signal through the proximity light sensor and / or the infrared sensor, etc.

[0315] As introduced above, the reference composition data corresponding to the first wallpaper can include at least one posture data set, or at least one reference animation, or at least one movement data. In the embodiments of the present application, the electronic device can also store the mapping relationship between the posture data set or the reference animation or the movement data and the interaction signal. Based on this, after detecting the interaction signal of the user, the electronic device can determine the posture data set or the reference animation or the movement data corresponding to the interaction signal of the user as the second composition data based on the mapping relationship.

[0316] For example, the electronic device stores different action tags corresponding to different interaction signals, wherein the action tag is used to indicate the action expected to be made by the biological image under the corresponding interaction signal. In addition, each posture data set or reference animation or movement data can also correspond to an action tag, which can be determined by the cloud server or the electronic device based on the corresponding posture data set or reference animation or movement data, and is used to indicate that the corresponding data contains data for realizing the action indicated by the corresponding action tag. Based on this, the electronic device can obtain the target action tag corresponding to the interaction signal of the user, and obtain the posture data set or the reference animation or the movement data corresponding to the target action tag from the reference composition data as the second composition data.

[0317] For example, the interaction signal of the user is a touch signal on the display position of the second image in the display screen, and the action tag corresponding to the touch signal can be a clapping tag, which is used to instruct the second image to make a clapping action at the position touched by the user. For another example, the interaction signal of the user is a motion signal detected by a gyroscope sensor, and the action tag corresponding to the motion signal can be a somersault tag, which is used to instruct the second image to make a somersault action following the motion signal. For another example, the interaction signal of the user is a signal of covering the screen detected by the ambient light sensor and the proximity light sensor in cooperation, and the action tag corresponding to the signal can be an action tag of covering the eyes.

[0318] In addition, the second composition data can include data for implementing the target action indicated by the target action tag. For example, the second composition data can include a pose data set representing a plurality of second poses, which can constitute the target action. Alternatively, the second composition data can include a motion data describing a motion rule of the biological image, and the target action conforms to the motion rule. Alternatively, the second composition data can include an animation of the biological image containing a plurality of second poses.

[0319] S1305: generating a third wallpaper based on the second composition data and the second image, the third wallpaper including a plurality of second images corresponding to the plurality of second poses respectively.

[0320] After obtaining the second composition data, the electronic device can generate a third wallpaper based on the second composition data and the second image.

[0321] If the second composition data includes a pose data set representing a plurality of second poses or a motion data describing a motion rule of the image, the electronic device can refer to the method introduced in S1302 above to obtain a third image group containing a plurality of second images based on the second composition data and any one of the second images in the second wallpaper. Then, the third image group is used to replace the second image group in the second wallpaper to obtain the third wallpaper.

[0322] If the second composition data includes an animation of an image containing a plurality of second poses, the electronic device can refer to the method introduced in S1302 above to generate the third wallpaper based on the animation and any one of the second images in the second wallpaper.

[0323] S1306: displaying the third wallpaper.

[0324] After generating the third wallpaper, the electronic device can set the third wallpaper as the current wallpaper, and refresh the second wallpaper currently displayed as the third wallpaper.

[0325] It should be noted that the above mainly introduces the implementation process of the user interacting with the image in the dynamic wallpaper displayed by the electronic device, and in some possible scenarios, the user can also refer to the above-mentioned manner to realize the interaction with the image displayed in other scenarios, for example, for the image in the pet widget displayed in the desktop page of the electronic device, the user can also refer to the above-mentioned manner to realize the interaction with the image, so as to improve the interest.

[0326] In the embodiment of the present application, the electronic device can obtain a user image, and then obtain a second image based on the user image and the existing first image, and display the second image. Wherein, the user image includes a first costume, the first costume has at least one costume feature, the second image includes a second costume, and the second costume has one or more features of the at least one costume feature of the first costume. As can be seen, the costume of the second image displayed in the embodiment of the present application based on the existing first image can be in harmony with the user costume in the user image. On this basis, as the user costume in the user image obtained by the electronic device changes, the costume of the displayed biological image will also change accordingly. In this way, the diversity of the costume of the displayed biological image and the relevance to the user costume are enhanced, so as to better improve the user's attention to the biological image, and then improve the user's willingness to use the biological image related products.

[0327] In addition, in the embodiment of the present application, after obtaining the second image, the electronic device can display the desktop wallpaper based on the second image. In this way, for the interface of the desktop which is frequently stayed by the user, the costume of the biological image in the desktop wallpaper can change with the change of the user costume, so as to better attract the user's attention and increase the user's willingness to use.

[0328] Finally, in the embodiment of the present application, the electronic device can realize composition in combination with the current scene data in the process of generating the dynamic wallpaper based on the second image. In this way, the posture of the second image in the dynamic wallpaper and the decoration element are consistent with the current scene, so that the dynamic wallpaper is more personalized and more interesting. In addition, the user can also interact with the image in the dynamic wallpaper displayed by the electronic device, and the electronic device can update the posture of the image in the dynamic wallpaper based on the user's interaction signal, so that the image in the dynamic wallpaper can make the action responding to the user's interaction signal, improve the interest of the dynamic wallpaper, enrich the user experience, and thus enhance the user's willingness to use.

[0329] Next, the biological image display device provided in the embodiment of the present application is introduced.

[0330] FIG. 14 is a structural schematic diagram of a biological image display device provided in an embodiment of the present application. The biological image display device can be deployed in an electronic device. As shown in FIG. 14, the biological image display device 1400 includes a user image acquisition module 1401, an image acquisition module 1402, and a display module 1403, wherein the user image acquisition module 1401 is configured to perform step 401 in the above embodiment, the image acquisition module 1402 is configured to perform step 402 in the above embodiment, and the display module 1403 is configured to perform step 403 in the above embodiment.

[0331] Optionally, the at least one clothing feature includes one or more of a clothing color feature, a clothing style feature, a clothing pattern feature, a clothing material feature, a clothing style feature, and an accessory feature, and the accessory feature includes one or more of an accessory material feature, an accessory shape feature, an accessory color feature, and an accessory style feature.

[0332] Optionally, when the second clothing has a clothing color feature in the at least one clothing feature, the clothing color of the second clothing is the same as or opposite to the clothing color of the first clothing, or the clothing shade of the second clothing is the same as or opposite to the clothing shade of the first clothing.

[0333] Optionally, when the second clothing has a clothing color feature in the at least one clothing feature, the clothing color of the second clothing and the first clothing at the same body part is the same.

[0334] Optionally, when the second clothing has a clothing pattern feature in the at least one clothing feature, the second clothing includes part or all of the clothing pattern of the first clothing, or the second clothing is similar to the clothing pattern of the first clothing.

[0335] Optionally, when the second clothing has a clothing style feature in the at least one clothing feature, the clothing style of the second clothing is the same as the clothing style of the first clothing.

[0336] Optionally, when the second clothing has a clothing material feature in the at least one clothing feature, the clothing material of the second clothing is the same as the clothing material of the first clothing.

[0337] Optionally, when the second clothing has a clothing style feature in the at least one clothing feature, the clothing style of the second clothing is the same as the clothing style of the first clothing.

[0338] Optionally, when the second clothing has at least one of an accessory material feature, an accessory shape feature, an accessory color feature, and an accessory style feature in the at least one clothing feature, the second clothing includes at least one accessory having the at least one feature.

[0339] Optionally, the image obtaining module 1402 is specifically configured to: send the user clothing information and the first image to a cloud server, so that the cloud server generates a second image based on the user clothing information and the first image, the user clothing information comprises a user image or a first clothing description text, the first clothing description text is obtained based on the user image and is used to describe at least one clothing feature of the first clothing; and receive the second image sent by the cloud server.

[0340] Optionally, the user image obtaining module 1401 is specifically configured to: in response to a first operation of the user, obtain first interface information to be displayed; and if the first interface information comprises a first image, capture a user image through a camera.

[0341] Optionally, the first image is an image in a first wallpaper, and the display module 1403 is specifically configured to: based on the second image and the first wallpaper, display a second wallpaper, the second wallpaper comprising the second image.

[0342] Optionally, the first wallpaper is a static wallpaper, and the display module 1403 is specifically configured to: replace the first image in the first wallpaper with the second image to obtain the second wallpaper; and display the second wallpaper.

[0343] Optionally, the first wallpaper is a dynamic wallpaper, and the display module 1403 is specifically configured to: obtain first composition data corresponding to the first wallpaper, the first composition data being used to represent a plurality of first poses; generate a second wallpaper based on the first composition data and the second image, the second wallpaper comprising a plurality of second images corresponding to the plurality of first poses respectively; and display the second wallpaper.

[0344] Optionally, the display module 1403 is specifically configured to: obtain current scene data, the scene data being used to indicate an external scene and / or an internal scene of the electronic device; and obtain first composition data corresponding to the scene data based on reference composition data corresponding to the first wallpaper.

[0345] Optionally, the display module 1403 is further configured to: in response to an interaction signal of the user, obtain second composition data corresponding to the interaction signal based on the reference composition data corresponding to the first wallpaper, the second composition data being used to represent a plurality of second poses; generate a third wallpaper based on the second composition data and the second image, the third wallpaper comprising a plurality of second images corresponding to the plurality of second poses; and display the third wallpaper.

[0346] Optionally, the first image and the second image are virtual images.

[0347] In the embodiments of the present application, the electronic device can obtain a user image, and then obtain a second image based on the user image and the existing first image, and display the second image. The second image includes a second dress, and the second dress has one or more characteristics of at least one dress characteristic of the first dress in the user image. It can be seen that the dress of the second image displayed in the embodiments of the present application on the basis of the existing first image can correspond to the user dress in the user image. On this basis, as the user dress in the user image obtained by the electronic device changes, the dress of the displayed image will also change accordingly. In this way, the diversity and relevance of the dress of the displayed image are enhanced, so that the user's attention to the biological image can be better improved, and then the user's use intention for the biological image related product can be improved.

[0348] FIG. 15 is a structural schematic diagram of another biological image display device provided by the embodiments of the present application. The biological image display device can be deployed in a cloud server. As shown in FIG. 15, the biological image display device 1500 includes a receiving module 1501, an image generation module 1502, and a sending module 1503.

[0349] The receiving module 1501 is configured to receive the user dress information and the first image sent by the electronic device after the electronic device executes S801 in the above-mentioned embodiments. The image generation module 1502 is configured to execute S802 in the above-mentioned embodiments. The sending module 1503 is configured to execute S803 in the above-mentioned embodiments.

[0350] Optionally, the at least one dress characteristic includes one or more of a dress color characteristic, a dress style characteristic, a dress pattern characteristic, a dress material characteristic, a dress style characteristic, and an accessory characteristic. The accessory characteristic includes one or more of an accessory material characteristic, an accessory shape characteristic, an accessory color characteristic, and an accessory style characteristic.

[0351] Optionally, when the second dress has a dress color characteristic in the at least one dress characteristic, the dress color of the second dress at the same body part as the first dress is the same.

[0352] Optionally, when the second dress has a dress color characteristic in the at least one dress characteristic, the dress color of the second dress at the same body part as the first dress is the same.

[0353] Optionally, when the second dress has a dress pattern characteristic in the at least one dress characteristic, the second dress includes part or all of the dress pattern of the first dress, or the second dress is similar to the dress pattern of the first dress.

[0354] Optionally, when the second clothing has the clothing style feature in the at least one clothing feature, the clothing style of the second clothing is the same as the clothing style of the first clothing.

[0355] Optionally, when the second clothing has the clothing material feature in the at least one clothing feature, the clothing material of the second clothing is the same as the clothing material of the first clothing.

[0356] Optionally, when the second clothing has the clothing style feature in the at least one clothing feature, the clothing style of the second clothing is the same as the clothing style of the first clothing.

[0357] Optionally, when the second clothing has at least one of the accessory material feature, the accessory shape feature, the accessory color feature, and the accessory style feature in the at least one clothing feature, the second clothing includes at least one accessory having the at least one feature.

[0358] Optionally, the user clothing information includes a user image, and the image generation module 1502 is specifically configured to: based on the user image, obtain a second clothing description text; based on the first image, obtain composition data and an image description text corresponding to the first image; and based on the second clothing description text, the composition data corresponding to the first image, and the image description text, generate a second image by using a stable diffusion SD model.

[0359] Optionally, the image generation module 1502 is specifically configured to: based on the second clothing description text and the image description text corresponding to the first image, generate a comprehensive description text; and input the comprehensive description text and the composition data corresponding to the first image into the SD model to output the second image by using the SD model.

[0360] Optionally, the image generation module 1502 is specifically configured to: identify the first clothing in the user image by using a clothing model to obtain the second clothing description text.

[0361] Optionally, the image description text corresponding to the first image is obtained by identifying the first image by using a bootstrap language image pre-training BLIP model, and the image generation module 1502 is specifically configured to: identify the first clothing in the user image by using the BLIP model to obtain the second clothing description text.

[0362] Optionally, the first image and the second image are virtual images.

[0363] In the embodiments of the present application, the cloud server can receive the user clothing information and the first image sent by the electronic device, and generate a new second image according to the user clothing information and the first image, so as to make the electronic device display the second image. The user clothing information is obtained based on the user image, and the second clothing included in the second image has one or more of the at least one clothing feature of the first clothing in the user image. As can be seen, the clothing of the second image generated on the basis of the existing first image in the present application can correspond to the user clothing in the user image. On this basis, with the change of the user clothing in the user image sent by the electronic device, the clothing of the generated biological image will also change accordingly. In this way, the diversity and relevance of the clothing of the biological image displayed by the electronic device are enhanced, so as to better improve the user's attention to the biological image, and further improve the user's willingness to use the biological image related product.

[0364] It should be noted that the division of the modules in the biological image display device provided by the above embodiments is illustrative, and is only a logical function division. In actual implementation, there can be another division manner. In addition, each function module in each embodiment of the present application can be integrated in one processor, or can be physically separated, or two or more modules can be integrated into one module. The integrated module can be realized in the form of hardware or in the form of a software function module.

[0365] When the integrated module is realized in the form of a software function module and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the embodiments of the present application can be embodied in the form of a software product in essence or the part that contributes to the prior art or the whole or part of the technical solutions. The computer software product is stored in a storage medium, and includes a plurality of instructions for causing a computer device (which can be an electronic device or a server, etc.) or a processor to execute all or part of the steps of the method of the embodiments of the present application. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various storage program codes.

[0366] In addition, the biological image display device and the biological image display method provided by the above embodiments belong to the same concept, and the specific implementation process is detailed in the method embodiments, which will not be described here.

[0367] In the above embodiments, all or part of the embodiments can be implemented by software, hardware, firmware or any combination thereof. When implemented by software, all or part of the embodiments can be implemented in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of the present application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center through wired (for example: coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (for example: infrared, wireless, microwave, etc.) mode. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that includes one or more available media sets. The available media can be magnetic media (for example: floppy disk, hard disk, magnetic tape), optical media (for example: digital versatile disc (DVD)), or semiconductor media (for example: solid state disk (SSD)) and the like.

[0368] In various embodiments of the present application, the terms and / or descriptions of different embodiments are consistent and can be referred to each other if there is no special description and logical conflict, and the technical features in different embodiments can be combined to form new embodiments according to their inherent logical relationship. In the embodiments of the present application, "at least one" means one or more, and "multiple" means two or more. The "and / or" describes the association relationship of the associated objects, which means that there can be three kinds of relationships, for example, A and / or B, which can represent the following three cases: A exists alone, A and B exist together, and B exists alone, where A and B can be singular or plural. In the textual description of the embodiments of the present application, the character " / ", generally indicates that the front and rear associated objects are in an "or" relationship. In the present application, "first", "second" and various number designations are only for the convenience of distinguishing description, and are not used to limit the scope of the embodiments of the present application. For example, to distinguish different messages, rather than to describe a specific order or sequence.

[0369] It can be understood that various digital numbers involved in the embodiments of the present application are only distinguished for convenience of description, and are not used to limit the scope of the embodiments of the present application. The size of the serial number of each process does not mean the order of execution, and the execution order of each process should be determined according to its function and inherent logic.

[0370] Finally, it should be noted that the above description is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any change or replacement within the technical scope disclosed in the present application should be covered in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A biological image display method, characterized in that: Applied to electronic equipment, the method includes: Acquire a user image, the user image including a first garment, the first garment having at least one garment feature; Acquire a second image based on the user image and the first image, wherein the second image includes a second garment, and the second garment has one or more features of the at least one garment feature; The second image shown is displayed.

2. The method according to claim 1, characterized in that The first image is a virtual image, and the second image is a virtual image.

3. The method according to claim 1 or 2, characterized in that The at least one clothing feature includes one or more of clothing color features, clothing style features, clothing pattern features, clothing material features, clothing style features, accessory material features, accessory shape features, accessory color features, and accessory style features.

4. The method according to claim 3, characterized in that When the second apparel has the apparel color feature of the at least one apparel feature, the apparel color matching of the second apparel is the same as or opposite to the apparel color matching of the first apparel, or the apparel hue of the second apparel is the same as or opposite to the apparel hue of the first apparel.

5. The method according to claim 3, characterized in that When the second clothing has the clothing color feature of the at least one clothing feature, the clothing colors of the second clothing and the first clothing located at the same body part are the same.

6. The method according to any one of claims 3 to 5, characterized in that: When the second apparel has the clothing pattern feature of the at least one apparel feature, the second apparel includes part or all of the clothing pattern of the first apparel, or the clothing pattern in the second apparel is similar to the clothing pattern in the first apparel.

7. The method according to any one of claims 3 to 6, characterized in that: When the second clothing has at least one feature among the accessory material feature, the accessory shape feature, the accessory color feature, and the accessory style feature of the at least one clothing feature, the second clothing includes at least one accessory having the at least one feature.

8. The method according to any one of claims 3 to 7, characterized in that: When the second apparel has the clothing style feature of the at least one clothing feature, the clothing style of the second apparel is the same as the clothing style of the first apparel; When the second clothing has the clothing material feature of the at least one clothing feature, the clothing material of the second clothing is the same as the clothing material of the first clothing; When the second apparel has a clothing style feature among the at least one apparel feature, the clothing style of the second apparel is the same as the clothing style of the first apparel.

9. The method according to any one of claims 1 to 8, characterized in that: The acquiring of the second image based on the user image and the first image includes: Sending user clothing information and the first image to a cloud server, so that the cloud server generates the second image based on the user clothing information and the first image, wherein the user clothing information includes the user image or first clothing description text, and the first clothing description text is obtained based on the user image and is used to describe the at least one clothing feature; Receive the second image sent by the cloud server.

10. The method according to any one of claims 1 to 9, characterized in that: The obtaining of the user image includes: In response to a first operation by a user, obtaining first interface information to be displayed; If the first interface information includes the first image, the user image is captured through a camera.

11. The method according to any one of claims 1 to 10, characterized in that: The first image is an image in the first wallpaper, and displaying the second image includes: Based on the second image and the first wallpaper, a second wallpaper is displayed, wherein the second wallpaper includes the second image.

12. The method according to claim 11, characterized in that The first wallpaper is a static wallpaper, and the displaying of the second wallpaper based on the second image and the first wallpaper includes: replacing the first image in the first wallpaper with the second image to obtain the second wallpaper; The second wallpaper is displayed.

13. The method according to claim 11, characterized in that The first wallpaper is a dynamic wallpaper, and the displaying of the second wallpaper based on the second image and the first wallpaper includes: Acquire first composition data corresponding to the first wallpaper, where the first composition data is used to represent a plurality of first postures; generating a second wallpaper based on the first composition data and the second image, wherein the second wallpaper includes second images corresponding to the plurality of first postures respectively; The second wallpaper is displayed.

14. The method according to claim 13, characterized in that The acquiring first composition data corresponding to the first wallpaper includes: Acquiring current scenario data, where the scenario data is used to indicate an external scenario and / or an internal scenario of the electronic device; The first composition data corresponding to the scene data is acquired based on the reference composition data corresponding to the first wallpaper.

15. The method according to claim 13 or 14, characterized in that After displaying the second wallpaper, the method further includes: In response to a user interaction signal, obtaining second composition data corresponding to the interaction signal based on reference composition data corresponding to the first wallpaper, wherein the second composition data is used to represent a plurality of second gestures; generating a third wallpaper based on the second composition data and the second image, the third wallpaper including a plurality of second images corresponding to the second postures; The third wallpaper is displayed.

16. The method according to any one of claims 1 to 15, characterized in that The second image further includes decorative elements corresponding to current scene data, where the scene data is used to indicate an external scene and / or an internal scene of the electronic device.

17. A biological image display method, characterized in that: Applied to a cloud server, the method includes: Receiving user clothing information and a first image sent by an electronic device, the user clothing information including a user image or a first clothing description text, the user image including a first clothing item, the first clothing item having at least one clothing feature, the first clothing description text being obtained based on the user image and used to describe the at least one clothing feature; generating a second image based on the user clothing information and the first image, wherein the second image includes second clothing, and the second clothing has one or more features of the at least one clothing feature; The second image is sent to the electronic device, so that the electronic device displays the second image.

18. The method according to claim 17, characterized in that The first image is a virtual image, and the second image is a virtual image.

19. The method according to claim 17 or 18, characterized in that The at least one clothing feature includes one or more of clothing color features, clothing style features, clothing pattern features, clothing material features, clothing style features, accessory material features, accessory shape features, accessory color features, and accessory style features.

20. The method according to any one of claims 17 to 19, characterized in that The user clothing information includes the user image, and generating the second image based on the user clothing information and the first image includes: acquiring, based on the user image, a second clothing description text, where the second clothing description text is used to describe the at least one clothing feature; Based on the first image, obtaining composition data and image description text corresponding to the first image; The second image is generated using a stable diffusion (SD) model based on the second clothing description text, the composition data corresponding to the first image, and the image description text.

21. The method according to claim 20, characterized in that The step of generating the second image using a stable diffusion (SD) model based on the second clothing description text, the composition data corresponding to the first image, and the image description text includes: generating a comprehensive description text based on the second clothing description text and the image description text corresponding to the first image; The comprehensive description text and the composition data corresponding to the first image are input into the SD model, and the second image is output through the SD model.

22. The method according to claim 20 or 21, characterized in that The acquiring of a second clothing description text based on the user image includes: The first clothing in the user image is identified using a clothing model to obtain a description text of the second clothing.

23. The method according to claim 20 or 21, characterized in that The image description text corresponding to the first image is obtained by recognizing the first image using a bootstrapped language image pre-trained BLIP model. The obtaining of the second clothing description text based on the user image includes: The first clothing item in the user image is recognized using a BLIP model to obtain a description text of the second clothing item.

24. An electronic device, characterized in that: The electronic device includes a processor, and the processor is used to execute at least one program instruction or code stored in the memory to implement the biological image display method according to any one of claims 1 to 16.

25. The electronic device according to claim 24, characterized in that The electronic device further includes a display screen, and the processor is configured to control the display screen to display a second image.

26. A cloud server, characterized in that: The cloud server includes a processor configured to execute at least one program instruction or code stored in a memory to implement the biological image display method according to any one of claims 17 to 23.

27. A computer-readable storage medium, characterized in that The computer-readable storage medium stores instructions, and when the instructions are executed on a computer device, the computer device executes the biological image display method according to any one of claims 1 to 23.

28. A computer program product comprising instructions, characterized in that When the instructions are executed by a computer device, the computer device is caused to execute the biological image display method according to any one of claims 1 to 23.

Images