Methods and systems for generating clock face images and computing devices having generative clock face images

Abstract

Provided are systems and methods for generating clock face images. Provided is a framework for obtaining prompts, seeds, and conditions that are passed to a text-to-image synthesis model for generation of a clock face image. For instance, a wearable computing device can include one or more processors; a memory; one or more user input devices; and a display screen to display a clock face image. The clock face image can be generated by a computing system performing operations including obtaining an initial prompt that specifies desired content of the clock face image; obtaining an initial seed that specifies desired composition of the clock face image; obtaining at least one initial condition that specifies desired style of the clock face image; processing the initial prompt, the initial seed, and the at least one initial condition with a text-to-image model; and providing the clock face image, e.g., to the display screen.

Description

METHODS AND SYSTEMS FOR GENERATING CLOCK FACE IMAGES ANDCOMPUTING DEVICES HAVING GENERATIVE CLOCK FACE IMAGESFIELD[1] The present disclosure relates generally to generative clock face images. More particularly, the present disclosure relates to systems and methods for generating clock face images and computing devices having generative clock face images.BACKGROUND[2] Text-to-image synthesis has gained increasing attention and experienced rapid development with recent advances of generative adversarial networks (GANs). diffusion models, and other forms of generative models. With sophisticated designs and enormous amounts of training data, images with unprecedented quality and diversity can be generated through conditioning on free-form texts provided by users.[3] However, text-to-image synthesis has not been widely adopted by manufacturers or other providers for use in consumer products. In particular, computing devices (e.g., wearable computing devices such as a wristwatch, ring, band, etc. or non-wearable computing devices such as a smartphone or tablet) largely continue to utilize manually designed clock faces. Although such existing clock faces can be customizable, each option available for user selection usually requires at least some degree of manual design, which requires time and resources. Further, user customization of existing clock faces is generally limited, with users having few personalization options.SUMMARY[4] Aspects and advantages of embodiments of the present disclosure will be set forth in part in the following description, or can be learned from the description, or can be learned through practice of the embodiments.[5] One example aspect of the present disclosure is directed to a computer-implemented method to generate a clock face image for a computing device. The method includes obtaining, by a computing system comprising one or more computing devices, an initial prompt that specifies desired content of the clock face image. The method includes obtaining, by the computing system, an initial seed that specifies desired composition of the clock face image. The method includes obtaining, by the computing system, at least one initial condition that specifies the desired style of the clock face image. The method includes processing, bythe computing system, the initial prompt, the initial seed, and the at least one initial condition with a text-to-image model. The method includes providing, by the computing system, the clock face image.[6] Another example aspect of the present disclosure is directed to a computer system for generating a clock face image for a computing device. The computer system includes one or more processors and one or more non-transitory computer-readable media that collectively store instructions that, when executed by the one or more processors, cause the computer system to perform operations. The operations include obtaining an initial prompt that specifies desired content of the clock face image; obtaining an initial seed that specifies desired composition of the clock face image; obtaining at least one initial condition that specifies desired style of the clock face image; processing the initial prompt, the initial seed, and the at least one initial condition with a text-to-image model; and providing the clock face image.[7] Still another example aspect of the present disclosure is directed to a w earable computing device. The wearable computing device includes one or more processors, a memory, and one or more user input devices. The earable computing device also includes a display screen configured to display a clock face image generated as described with respect to the computer-implemented method to generate a clock face image for a computing device.[8] Other aspects of the present disclosure are directed to various systems, apparatuses, non-transitory computer-readable media, user interfaces, and electronic devices.[9] These and other features, aspects, and advantages of various embodiments of the present disclosure will become better understood with reference to the following description and appended claims. The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate example embodiments of the present disclosure and, together with the description, serve to explain the related principles.BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Detailed discussion of embodiments directed to one of ordinary skill in the art is set forth in the specification, which makes reference to the appended figures, in which:

[0011] FIG. 1 depicts a perspective view of a computing device according to example embodiments of the present disclosure.

[0012] FIG. 2 depicts a block diagram of an example computing device that generates a clock face image according to example embodiments of the present disclosure.

[0013] FIGS. 3 A and 3B depict block diagrams of a generation of an initial clock face image and a modified clock face image according to example embodiments of the present disclosure.

[0014] FIG. 4 depicts a block diagram of a computing system that generates a clock face image according to example embodiments of the present disclosure.

[0015] FIG. 5 A depicts a flow diagram of a method for generating a clock face image according to example embodiments of the present disclosure.

[0016] FIG. 5B depicts a flow diagram of a method for modifying the clock face image generated by the method of FIG. 5 A according to example embodiments of the present disclosure.

[0017] Reference numerals that are repeated across plural figures are intended to identify the same features in various implementations.DETAILED DESCRIPTIONOverview

[0018] Generally, the present disclosure is directed to systems and methods for generating clock face images specified by users or otherwise provided as an input. Unlike other clock faces, which generally overlay an image with clock features, example implementations described herein embed clock features within the clock face image. As one example, the arms of an analog clock may be part of the generated clock face image. As other examples, clock face images according to the present disclosure can be reactive to the passage of time, e.g., to moving clock arms, and / or can change after a given time period.

[0019] In general, a clock face image according to the present disclosure is generated using a prompt generator, a clock line art generator (Clag), a seed controller, and a text-to-image (T2I) model. The prompt generator prompts the T2I model, e.g., the prompt generator outputs to the T2I model a single static noun, a randomly sampled noun from a themed list (such as a list of fruits), an external condition (such as weather), or other prompt. The Clag conditions the T2I model and may be altered to change the overall style of the watch, such as a digital clock vs. an analog clock, a framed clock face, a clock arm width, etc. The seed controller sets the T2I seed, which controls the overall composition of the clock face image. Raising or lowering a control weight of the T2I model changes the creative freedom of the T2I model; a lower control weight allows the T2I model greater creative freedom.

[0020] By using the same seed and / or prompt in the present disclosure, the clock face image may be relatively consistent between minutes, e.g., the clock arms move to reflect the changein time and the clock face image adjusts for the new clock arm placement, with interpolation of one minute’s image to the next providing a smooth transition. A new seed and / or prompt may be used every given time period (e.g., a number of hours) to generate a different overall clock face image, which can provide further personalization for the user. For example, for the next time period, an entirely new prompt may be used or only a portion of the prompt may be changed (e.g., the time of day (morning, afternoon, evening) reflected in the image may be based on the user’s time of day; the scene may change based on the user’s location; any weather reflected in the image may be based on the weather experienced by the user; etc.).

[0021] Thus, in contrast to certain existing approaches that merely allow a user to select a clock face image and / or customize a display of data metrics on a clock face, aspects of the present disclosure are directed to fully generative clock face images. In particular, the present disclosure is directed to generating clock face images in which the clock is part of the image.

[0022] The present disclosure provides a number of technical effects and benefits. For example, certain prior approaches to clock face generation provide limited personalization, which is generally static without further input by the user, and usually, each available selection must be manually designed by a human. In contrast, the present disclosure utilizes image generation techniques described herein to automatically generate clock face images based on a user prompt, while also providing dynamic customization. By avoiding manual design of each potential clock face image, the present disclosure saves time and resources. Further, the generative techniques described herein possess simplicity, which can reduce implementation time and costs.

[0023] Example aspects of the present disclosure are directed to a computer-implemented method to generate a clock face image for a computing device. The method can include one or more steps performed by a computing system including one or more computing devices, which can include the computing device having the generated clock face image. For instance, the method can include obtaining, by the computing system, an initial prompt that specifies desired content of the clock face image; obtaining, by the computing system, an initial seed that specifies desired composition of the clock face image; and obtaining, by the computing system, at least one initial condition that specifies desired style of the clock face image. Further, the method can also include processing, by the computing system, the initial prompt, the initial seed, and the at least one initial condition with a text-to-image model; and providing, by the computing system, the clock face image.

[0024] As such, the text-to-image (T2I) model processes the initial prompt, the initial seed, and the at least one initial condition to output the clock face image. The method can further include obtaining, by the computing system, a control weight for the T2I model. The control weight, which can range from 0.0 to 1 .0 and any ranges therebetween, can be a weight of the condition controller (CC), specifies the creative freedom that may be exercised by the T2I model. Lowering the control weight can allow the T2I more creative freedom. For example, a control weight of 1.0 can specify that the T2I model may not exercise any creative freedom (i.e., zero creative freedom allowed by the T2I model), while a control weight of 0.85 can specify' that the T2I model may exercise some creative freedom, and a control weight of 0.50 can specify that the T2I model may exercise a greater amount of creative freedom. The amount of creative freedom afforded to the T2I model can, for example, determine how sharp the arms of an analog clock should be in the generated clock face image. For instance, a control weight of 1.0 specifies very defined clock arms, while a control weight of 0.8 allows the T2I freedom to blur the clock arms or otherwise further incorporate the clock arms into the generated clock face image.

[0025] The content and general composition of the clock face image can remain generally constant (e.g., changing only to reflect changes in time) until the user provides one or more inputs to change the clock face image. How ever, in at least some example aspects of the present disclosure, the content, composition, and / or at least one condition of the clock face image can change after a predetermined trigger. For instance, the method can include, after the predetermined trigger, obtaining, by the computing system, at least one of a modified prompt, a modified seed, or at least one modified condition; processing, by the computing system, the at least one of the modified prompt, the modified seed, and the at least one modified condition with the text-to-image model; and providing, by the computing system, a modified clock face image. The predetermined trigger can include one or more of the following, as w ell as other triggers not enumerated herein:• a period of time (e.g., the clock face image may be modified after an elapsed time period such as four hours, six hours, twelve hours, or other time period);• a change in the user’s location (e.g., the clock face image may be modified from an initial clock face image associated with the user’s home to a modified clock face image associated with the user’s workplace after the user travels from the user’s home to the user's workplace); or• a change in weather (e.g., the clock face image may be modified to reflect changes in the weather at the user's location, such as from a clock face image having sunny conditions to a clock face image having cloudy conditions).The change in the user’s location and the change in weather also can be referred to as a change in an external condition of the user.

[0026] The prompt, e.g.. the initial prompt or the modified prompt, controls the contents of the clock face image and can include at least one of a single static noun, a randomly sampled noun from a themed list, an external condition, a scene, a style or medium, or an adjective. As an example, the initial prompt may be a single static noun such as dog, lemon, forest, piano, car, or pool. As another example, the initial prompt may be randomly sampled from a themed list such as fruits, landscapes, or musical instruments. As still another example, the prompt may be a phrase incorporating two or more features of the foregoing list, such as an initial prompt that is “bird flying over ocean,” “umbrella on beach,” “painting of cat,” or “sleepy dog.”

[0027] The seed, e.g., the initial seed or the modified seed, controls the overall composition of the clock face image. The seed is an integer that randomly controls the overall composition of the clock face image. More particularly, each random generation of an image has a unique seed or integer, with the seed representing the exact way a specific image was generated. Maintaining the seed from one iteration to another, e.g.. keeping the same seed minute-to- minute by not changing the seed value, can maintain somewhat consistent images. Consistency in the clock face image on a small time scale, e.g., minute-to-minute, can provide a smooth transition from one time to the next. For instance, maintaining the same seed between minutes for an analog clock face image can result in only the clock arms moving and adjustments to the clock face image for the new placement of the clock arms.

[0028] While it may be desirable to maintain somewhat consistent images minute-to-minute by not changing the seed value, it may also be desirable to introduce interesting variance hour-to-hour or day-to-day by changing the seed. As an example, a prompt may be “strawberry,” a seed prompt may be “change every 12 hours,” and a Clag input (or a condition) may be “analog”; the T21 model will generate a clock face image that is a strawberry with clock arms, which has a first seed or integer. If the T2I model was run again with the same seed, prompt, and Clag input, the T2I model would output the exact same clock face image. However, if only the seed was changed to a second seed that is a different integer from the first seed, and the same prompt and Clag input were received by the T2I model, the T2I model would generate a different clock face image of a strawberry havingclock arms (thereby representing an analog clock), e.g., the clock arms could be strawberries (where the clock arms were not strawberries with the previous seed), the strawberry could be drawn in a different art style, or the strawberry could be shown at a different angle. Because the prompt is just “straw berry” in this example, the T2I model can randomly decide how- to represent “strawberry,” but it will be a different representation than the representation assigned the first seed.

[0029] The condition, e.g., the at least one initial condition or the at least one modified condition, can include time, type of clock (analog vs. digital), whether the clock face image includes a frame around the clock, and other sty listic elements of the clock face image.

[0030] In example aspects of the present disclosure, the method can include modifying a portion of the initial prompt to obtain the modified prompt, modifying a portion of the initial seed to obtain the modified seed, or modifying a portion of the at least one initial condition to obtain the at least one modified condition. For instance, where a modified prompt is obtained after the predetermined trigger, only a portion of the initial prompt can be modified or the modified prompt may be an entirely new prompt. As an example, if the initial prompt was randomly sampled from a list of fruits, e.g.. with “strawberry” sampled as the initial prompt, after the predetermined trigger (such as after an elapsed time period as described above), the prompt may be randomly resampled from the list to obtain the modified prompt, e.g., with “orange” sampled as the modified prompt. The following list includes examples of portions of the initial prompt that may be modified to obtain the modified prompt:• time of day (e g., the prompt can be modified from a forest in the morning to a forest in the afternoon), which can be based on the current time (e.g., the predetermined trigger can be the current time or an elapsed time period that reflects a transition from morning, to afternoon, to evening, to night, and so forth);• scene (e.g., the prompt can be modified from a dinosaur in a forest to a dinosaur in a city, and from the dinosaur in the city to a dinosaur at work), which can be based on user location (e.g., the predetermined trigger can be a change in the user’s location);• weather (e.g., the prompt can be modified from a beach on a sunny day to a beach on a rainy day), which can be based on user-experienced weather (e.g., the predetermined trigger can be a change in the weather at the user’s location);• randomly sampled styles (e.g., the prompt can be modified from a photo of a cat to an oil painting of a cat, and from the oil painting of the cat to a watercolor painting of a cat); or• randomly sampled adjectives (e.g.. the prompt can be modified from a super cat to a purple cat, and from the purple cat to a sleepy cat).It will be understood that the foregoing does not provide the only possibilities for prompts, either initial or modified, but instead provides only a few examples of prompts and modifications of prompts, for purposes of illustrating the present subject matter.

[0031] Further, it will be appreciated that, as used herein, the term "‘modified clock face image” refers to a clock face image that differs from a previous clock face image due to a change in one or more of the prompt, the seed, or at least one condition (other than time) input to the Clag that were used by the T2I model to generate the previous clock face image. Thus, the term “modified clock face image” encompasses a different overall clock face image and not a clock face image that is different from the previous clock face image only due to a change in time. That is, the “modified clock face image” encompasses changes to an initial or previous clock face image other than changes in time, although it will be understood that the time can also change between the generation of the initial clock face image and the modified clock face image.

[0032] In example aspects of the present disclosure, the text-to-image (T2I) model can be a T2I diffusion model that includes a condition controller (CC). For instance, the T2I diffusion model can be Stable Diffusion, which uses a latent diffusion model (LDM). The CC can be a neural network such as ControlNet. In other example aspects of the present disclosure, the T2I model is a text-to-image-sequence model, which can be used to generate videos or image sequences and can also include a condition controller. Thus, in some implementations, the clock face image generated as described herein can be a video, or image sequence, rather than an image. For example, the clock face image can be animated, such as with an image sequence that is looped (e.g., on a two to ten second loop, although other loop intervals could be used as well). The text-to-image-sequence model could also be described as a text-to- video model, but as used herein, it will be appreciated that, unless specified, “T2I model” can refer to a model for generating either or both images or image sequences.

[0033] Example aspects of the present disclosure also include computer systems for generating a clock face image for a computing device. For example, a computer system can include one or more processors and one or more non-transitoiy computer-readable media that collectively store instructions that, when executed by the one or more processors, cause the computer system to perform operations to provide the clock face image. The operations can include the method steps described above, such as obtaining an initial prompt that specifies desired content of the clock face image; obtaining an initial seed that specifies desiredcomposition of the clock face image; obtaining at least one initial condition that specifies desired style of the clock face image; processing the initial prompt, the initial seed, and the at least one initial condition with a text-to-image model; and providing the clock face image.

[0034] The present disclosure contemplates implementing example aspects in a computing device is a wearable computing device, such as a computing device that can be worn, for instance, on a user's wrist. However, it is to be understood that other wearable devices are also contemplated, such as, but not limited to. a band, a ring, etc. The wearable computing device can include at least one processor of the one or more processors of the computing system. The wearable computing device can include at least one non-transitory computer- readable medium of the one or more non-transitory computer-readable media of the computing system. For example, in some example aspects of the present disclosure, the wearable computing device includes one or more processors and a memory . The wearable computing device can include a display screen. Providing the clock face image can include displaying the clock face image on the display screen. In some aspects, the text-to-image model described herein can be implemented by the wearable computing device.

[0035] Further, the present disclosure also contemplates implementing example aspects in a computing device that is a non-wearable computing device, such as a personal computing device (e.g., laptop or desktop), a mobile computing device (e.g., smartphone or tablet), or a gaming console or controller. Such non-wearable computing devices can include at least one processor of the one or more processors of the computing system, at least one non-transitory computer-readable medium of the one or more non-transitory computer-readable media of the computing system, and / or a display screen, such that providing the clock face image can include displaying the clock face image on the display screen. In some example aspects of the present disclosure, the non-wearable computing device includes one or more processors, a memory, and a display for displaying the generated clock face image. In some aspects, the text-to-image model described herein can be implemented by the non-wearable computing device.

[0036] In some example aspects of the present disclosure, the wearable computing device or the non-wearable computing device can include one or more user input devices. The one or more user input devices can be manipulated by the user to interact with the wearable or non- wearable computing device. The one or more user input devices can include a touch-sensitive component (e.g., a touch-sensitive display screen or a touch pad) that is sensitive to the touch of a user input object (e.g.. a finger or a stylus). The touch-sensitive component can serve to implement a virtual keyboard. Other example user input devices include a microphone, atraditional keyboard, one or more mechanical buttons, a rotatable selector, or other means by which a user can provide user input. In some aspects, the user can input the initial prompt using at least one of the one or more user input devices. In further example aspects, the user can modify the initial prompt using at least one of the one or more user components, but the initial prompt, initial seed, and at least one initial condition may be modified in other ways as well.

[0037] Example aspects of the present disclosure also include storing and / or implementing the text-to-image model by a server computing system, which can be separate from the wearable computing device or non-wearable computing device and can communicate with the wearable computing device or non-wearable computing device. The server computing system can be part of the computing system having features for performing the operations outlined herein to produce a clock face image.

[0038] Further, as described above with respect to the example method, the operations performed by the computing system to provide the clock face image can include, after a predetermined trigger, obtaining at least one of a modified prompt, a modified seed, or at least one modified condition; processing the at least one of the modified prompt, the modified seed, and the at least one modified condition with the text-to-image model; and providing a modified clock face image. The predetermined trigger can be at least one of an elapsed time period, a change in external condition of a user, etc. as described above. Moreover, obtaining the modified prompt, modified seed, or at least one modified condition can include modifying all or only a portion of the initial prompt, initial seed, or at least one initial condition.

[0039] With reference now to the Figures, example embodiments of the present disclosure will be discussed in further detail.Example Embodiments

[0040] FIG. 1 depicts a perspective view of a wearable computing device according to example embodiments of the present disclosure. As illustrated in FIG. 1, the wearable computing device 100 can be worn, for instance, on an arm 102 (e.g.. wrist) of a user. For instance, the wearable computing device 100 can include a band 104 and a housing 106. In some implementations, the housing 106 can include a conductive material (e.g., metal), but in alternative implementations, the housing 106 can include a non-conductive material (e.g., a plastic material, a ceramic material). One or more processors and / or memory devices can be disposed in the housing 106. e.g., for performing operations to generate a clock face image as described elsewhere herein. Further, the housing 106 can be coupled to the band 104. In thismanner, the band 104 can be fastened to the arm 102 of the user to secure the housing 106 to the arm 102 of the user.

[0041] In some embodiments, the wearable computing device 100 can include a display screen 108. The display screen 108 can display content (e.g., time, date, biometrics, etc.) for viewing by the user, one or more of which can be conveyed through a clock face image as described herein. In some implementations, the wearable computing device 100 can include one or more user input devices 110 that can be manipulated (e.g.. touched, pressed, rotated, etc.) by the user to interact with the wearable computing device 100. It should be understood that the one or more input devices 110 can be configured to allow the user to interact with the wearable computing device 100 in any suitable manner. For instance, in some implementations, the one or more input devices 110 can be manipulated by the user to navigate through content (e.g., one or more menu screens) displayed on the display screen 108.

[0042] In some implementations, the one or more user input devices 110 can include a mechanical button that can be manipulated (e.g., pressed) to interact with the wearable computing device 100. In some implementations, the display screen 108 can include an interactive display screen (e.g., touchscreen or touch-free screen) such that the display screen 108 includes one or more user input devices 110. In such implementations, the user can interact with the wearable computing device 100 via the display screen 108 to control operation of the wearable computing device 100. For example, the user can interact with the wearable computing device 100 through the one or more user input devices 1 10 of the display screen 108 to input a prompt to generate a clock face image for display on the display screen 108.

[0043] FIG. 2 depicts a block diagram of an example computing device 200 that performs according to example embodiments of the present disclosure. The computing device 200 may be a standalone computing device or may be part of a computing system, e.g., the computing device may be a user computing device or a server computing device as described in greater detail with respect to FIG. 4. As described herein, the computing device 200 may be a wearable computing device, such as the wearable computing device 100 shown in FIG. 1, or may be anon-wearable computing device.

[0044] As illustrated in FIG. 2, the computing device 200 includes a seed controller 202, a prompt generator 204, a clock line art generator (Clag) 206. and a text-to-image model 208, which produces a clock face image 210. The clock face image 210 may be output to a display of the computing device 200, such as the display screen 108 of the wearable computingdevice 100. Further, in the depicted implementation, the text-to-image (T2I) model 208 includes a condition controller (CC) 212.

[0045] In an example embodiment of the present disclosure, the computing device 200 receives a seed input to the seed controller 202. Further, in this example, the computing device 200 receives a prompt input to the prompt generator 204 and receives at least one condition input to the Clag 206. Example seed inputs, prompt inputs, and condition inputs are discussed with respect to the example embodiment of FIGS. 3A and 3B.

[0046] The seed controller 202 outputs a seed, the prompt generator 204 outputs a prompt, and the Clag 206 outputs one or more conditions to the T2I model 208. The seed, prompt, and one or more conditions are processed by the T2I model 208. As previously stated, the prompt controls the contents and the seed controls the overall composition of the clock face image 210, while the conditions provided to the Clag 206 can change the overall style of the clock face image 210. Further, as described elsewhere herein, a control weight of the T2I model 208 can be selected to specify the creative freedom that can be exercised by the T2I model 208. Reducing the control weight can allow the T2I model 208 greater creative freedom. After processing by the T2I model 208, the computing device 200 provides the clock face image 210, e g., to a display such as the display screen 108 of the wearable computing device 100 of FIG. 1.

[0047] Referring now to FIGS. 3A and 3B, these figures depict block diagrams of an image generation scheme for generating an initial clock face image 10a and a modified clock face image 10b according to example embodiments of the present disclosure. The initial and modified clock face images of the illustrated implementation can be generated by a computing device such as the computing device 200 of FIG. 2. However, it will be appreciated that the image generation scheme is not limited to a particular computing device or computing system.

[0048] As illustrated in FIG. 3 A, a computing device 200 can obtain an initial seed input 12a. In the depicted embodiment, the initial seed input 12a specifies “change every76 hours,” which introduces variance to the clock face image every7six (6) hours. More particularly, for this example, the initial seed input 12a provides an input to the seed controller 202 that specifies how often (every 6 hours) to randomfy change the seed provided to the T2I model 208.

[0049] The computing device 200 can also obtain an initial prompt input 14a that specifies desired content of an output image. For example, in FIG. 3 A, the initial prompt input 14arequests “a bird flying over the ocean at sunset,"’ which specifies the content of the initial clock face image 10a generated by the computing device 200.

[0050] Further, the computing device 200 can also obtain at least one initial condition input 16a. In the embodiment of FIG. 3 A, the initial condition input 16a is ‘analog,” which specifies that the initial clock face image be an analog clock (i.e., having clock arms to indicate the time) rather than a digital clock (i.e., having numbers to indicate the time, with no clock arms). The initial condition input 16a is received by the Clag 206. which also receives the time 18, e.g., from an external source (i.e., a source external to the computing device 200) or from an internal source (e.g., a module, memory, or other portion of the computing device 200).

[0051] The seed controller 202 can receive the initial seed input 12a and output to the T2I model 208 an initial seed. The prompt generator 204 can receive the initial prompt input 14a and output to the T2I model 208 an initial prompt. The Clag 206 can receive the initial condition input 16a and the time 18 and can output to the T2I model 208 at least one initial condition. Thus, the computing device 200 can obtain an initial seed, an initial prompt, and at least one initial condition.

[0052] The T2I model 208 can process the initial seed, the initial prompt, and the at least one initial condition to provide or output the initial clock face image 10a. That is, the T2I model 208 can receive the initial seed from the seed controller 202, the initial prompt from the prompt generator 204, and the at least one initial condition from the Clag 206 and can process the initial seed, the initial prompt, and the at least one initial condition to generate the initial clock face image 10a. In the depicted embodiment, the T2I model 208 can include a condition controller (CC). The initial clock face image 10a could be a “still” image, with only the clock arms moving to reflect changes in time, or could be an image sequence or video (e.g., the ocean could be rippling or otherwise moving, one or more clouds could move across the clock face, etc.) looped over a time interval of two seconds, four seconds, eight seconds, ten seconds, etc., with the clock arms also moving to reflect changes in time. The initial clock face image 10a generated by the T2I model 208 can be output to a display of the computing device 200, which can be the same as or similar to the display screen 108 of the wearable computing device 100.

[0053] Referring now to FIG. 3B, a portion or all of the initial seed input 12a, the initial prompt input 14a, and / or at least one condition 16a can be modified to change the initial clock face image 10a to a modified clock face image 10b. In the embodiment shown in FIG. 3B, a portion of the initial prompt input 14a is changed and the initial seed input 12a andinitial condition input 16a remain the same. More particularly, in the illustrated implementation, the computing device 200 obtains a modified prompt input 14b that requests “a bird flying over the ocean at night.’’ In this example, the modified prompt input 14b is largely similar to the initial prompt input 14a but changes the “sunset” portion of the initial prompt input 14a to “night.” The prompt generator 204 receives the modified prompt input 14b and outputs to the T2I model 208 a modified prompt.

[0054] Keeping with FIG. 3B. the T2I model 208 processes the modified prompt, along with the initial seed, the at least one initial condition, and the time, to generate the modified clock face image 10b. As described herein, because the initial seed input 12a remains the same, the overall composition of the modified clock face image 10b is the same as the initial clock face image 10a. In the depicted example, the modified clock face image 10b differs from the initial clock face image 10a in terms of content (the modified image has a setting of nighttime rather than sunset) and the time, but the overall composition and the overall style of the modified clock face image 10b are the same as the initial clock face image 10a because the initial seed input 12a and the initial condition input 16a remain the same between the initial and modified clock face images 10a. 10b.

[0055] FIG. 4 depicts a block diagram of a computing system 400 for generating a clock face image according to example embodiments of the present disclosure. As shown in FIG. 4, the exemplary computing system 400 includes a user computing device 402 and a server computing system 420 that are communicatively coupled over a network 450.

[0056] The user computing device 402 can be any type of computing device, such as, for example, a personal computing device (e.g., laptop or desktop), a mobile computing device (e.g., smartphone or tablet), a gaming console or controller, a wearable computing device (e.g., such as described herein), an embedded computing device, or any other type of computing device.

[0057] The user computing device 402 includes one or more processors 404 and a memory 406. The one or more processors 404 can be any suitable processing device (e.g., a processor core, a microprocessor, an ASIC, an FPGA, a controller, a microcontroller, etc.) and can be one processor or a plurality of processors that are operatively connected. The memory 406 can include one or more non -transitory computer-readable storage media, such as RAM, ROM, EEPROM, EPROM, flash memory7devices, magnetic disks, etc., and combinations thereof. The memory 406 can store data 408 and instructions 410 which are executed by the processor 404 to cause the user computing device 402 to perform operations.

[0058] In some implementations, the user computing device 402 can store or include a text- to-image (T2I) model 412. For example, the T2I model 412 can be a diffusion T2I model or can be an image-sequence T2I model (e.g., a text-to-image-sequence model). In some implementations, the T2I model 412 can be received from the server computing system 420 over network 450, stored in the user computing device memory 406, and then used or otherwise implemented by the one or more processors 404.

[0059] Additionally or alternatively, a T2I model 430 can be included in or otherwise stored and implemented by the server computing system 420 that communicates with the user computing device 402 according to a client-server relationship. For example, the T2I model 430 can be implemented by the server computing system 420 as a portion of a web service (e.g., an image synthesis service). Thus. a T2I model 412 can be stored and implemented at the user computing device 402 and / or a T2I model 430 can be stored and implemented at the server computing system 420.

[0060] The user computing device 402 can also include one or more user input devices 414 that receives user input. For example, the user input device 414 can be a touch-sensitive component (e.g.. a touch-sensitive display screen or a touch pad) that is sensitive to the touch of a user input object (e.g., a finger or a stylus). The touch-sensitive component can serve to implement a virtual keyboard. Other example user input devices include a microphone, a traditional keyboard, or other means by which a user can provide user input.

[0061] The server computing system 420 includes one or more processors 422 and a memory 424. The one or more processors 422 can be any suitable processing device (e g., a processor core, a microprocessor, an ASIC, an FPGA, a controller, a microcontroller, etc.) and can be one processor or a plurality of processors that are operatively connected. The memory 424 can include one or more non-transitory computer-readable storage media, such as RAM, ROM, EEPROM, EPROM, flash memory devices, magnetic disks, etc., and combinations thereof. The memory 424 can store data 426 and instructions 428 which are executed by the processor 422 to cause the serv er computing system 420 to perform operations.

[0062] In some implementations, the server computing system 420 includes or is otherwise implemented by one or more server computing devices. In instances in which the server computing system 420 includes plural server computing devices, such server computing devices can operate according to sequential computing architectures, parallel computing architectures, or some combination thereof.

[0063] As described above, the server computing system 420 can store or otherwise include a T2I model 430. For example, the T2I model 430 can be or can otherwise include variousmachine-learned models. For example, the T2I model 412 can be a diffusion T2I model or can be an image-sequence T2I model (or text-to-image-sequence model).

[0064] The network 450 can be any type of communications network, such as a local area network (e.g., intranet), wide area network (e.g., Internet), or some combination thereof and can include any number of wired or wireless links. In general, communication over the network 450 can be carried via any type of wired and / or wireless connection, using a wide variety of communication protocols (e.g., TCP / IP. HTTP. SMTP. FTP), encodings or formats (e.g., HTML, XML), and / or protection schemes (e.g., VPN, secure HTTP, SSL).

[0065] FIG. 4 illustrates one example computing system that can be used to implement the present disclosure. Other computing systems can be used as well. For example, in some implementations, the user computing device 402 can include the T2I model 412 such that the T2I model 412 can be used locally at the user computing device 402. In other embodiments, the server computing system 420 can include the T2I model 430 such that the T2I model 430 can be supplied user inputs from the user input device(s) 414 of the user computing device 402 and generate the clock face image(s) remote from the user computing device 402. The remotely generated clock face image(s) can then be transmitted, e.g.. over the network 450, from the server computing system 420 to a display (not shown) of the user computing device 402.

[0066] FIG. 5 A depicts a flow diagram of a method for generating a clock face image, and FIG. 5B depicts a flow diagram of a method for modifying the clock face image generated by the method of FIG. 5 A, according to example embodiments of the present disclosure. The method 500 may be implemented using, for instance, the wearable computing device 100, the computing device 200, or the computing system 400 discussed above with reference to FIGS. 1, 2, and 4. respectively. Referring to FIG. 5A, at (502). the method 500 includes obtaining an initial prompt. At (504) and (506), the method 500 includes obtaining an initial seed and obtaining at least one initial condition. At (508), the method 500 optionally can include obtaining a control weight, which may be between 0.0 and 1.0.

[0067] Each of the initial prompt, initial seed, at least one initial condition, and control weight can be received by a T2I model as described herein. At (510). the method 500 includes processing the initial prompt, initial seed, and at least one initial condition with the T2I model. At (512), the method 500 includes providing an initial clock face image, such as by displaying the initial clock face image on a display of a computing device as described herein.

[0068] Optionally, the initial clock face image may be changed by modifying at least a portion of the initial prompt, the initial seed, and / or at least one initial condition. Referring to FIG. 5B, in such embodiments, the method 500 can include at (514) obtaining at least one of a modified prompt, a modified seed, or at least one modified condition. As show n at (516), the method 500 can also include obtaining a modified control weight. That is, the initial clock face image also may be changed by modifying the control weight of the T2I model to change the creative freedom allowed by the T2I model as described herein.

[0069] At (518), if obtained, the method 500 includes processing the at least one of the modified prompt, the modified seed, or at least one modified condition with the T2I model. As shown at (520). the T2I then provides a modified clock face image, e.g., on a display of a computing device as described above.

[0070] It will be appreciated that steps (508) and (514) to (520) are optional, as indicated by the dashed boxes around the text of each step. In some implementations, the method 500 may not modify the initial clock face image. For instance, no portion of the initial prompt, initial seed, at least one initial condition, or control weight may be changed to spur modification of the initial clock face image. In some implementations, the initial clock face image may be changed without performing steps (514) to (518). For example, as described with respect to FIG. 3A, the initial seed may be selected to change the clock face image after a period of time (such as 6 hours as shown in FIG. 3A). Thus, the method 500 in such embodiments can include providing a modified clock face image without obtaining a modified prompt, a modified seed, at least one modified condition, or a modified control weight, although such modifications can be obtained in some embodiments to further change the modified clock face image relati ve to the initial clock face image.

[0071] Although FIGS. 5A and 5B depict steps performed in a particular order for purposes of illustration and discussion, those of ordinary skill in the art, using the disclosures provided herein, will understand that various steps of the method 500 or any of the other methods disclosed herein may be adapted, modified, rearranged, performed simultaneously, or modified in various ways without deviating from the scope of the present disclosure.Additional Disclosure

[0072] The technology7discussed herein makes reference to servers, databases, software applications, and other computer-based systems, as well as actions taken and information sent to and from such systems. The inherent flexibility of computer-based systems allows for a great variety of possible configurations, combinations, and divisions of tasks andfunctionality between and among components. For instance, processes discussed herein can be implemented using a single device or component or multiple devices or components working in combination. Databases and applications can be implemented on a single system or distributed across multiple systems. Distributed components can operate sequentially or in parallel.

[0073] While the present subject matter has been described in detail with respect to various specific example embodiments thereof, each example is provided by way of explanation, not limitation of the disclosure. Those skilled in the art, upon attaining an understanding of the foregoing, can readily produce alterations to, variations of, and equivalents to such embodiments. Accordingly, the subject disclosure does not preclude inclusion of such modifications, variations and / or additions to the present subject matter as would be readily apparent to one of ordinary skill in the art. For instance, features illustrated or described as part of one embodiment can be used with another embodiment to yield a still further embodiment. Thus, it is intended that the present disclosure cover such alterations, variations, and equivalents.

Claims

WHAT IS CLAIMED IS:

1. A computer-implemented method to generate a clock face image for a computing device, the method comprising: obtaining, by a computing system comprising one or more computing devices, an initial prompt that specifies desired content of the clock face image; obtaining, by the computing system, an initial seed that specifies desired composition of the clock face image; obtaining, by the computing system, at least one initial condition that specifies desired style of the clock face image; processing, by the computing system, the initial prompt, the initial seed, and the at least one initial condition with a text-to-image model; and providing, by the computing system, the clock face image.

2. The computer-implemented method of claim 1, further comprising, after a predetermined trigger: obtaining, by the computing system, at least one of a modified prompt, a modified seed, or at least one modified condition; processing, by the computing system, the at least one of the modified prompt, the modified seed, and the at least one modified condition with the text-to-image model; and providing, by the computing system, a modified clock face image.

3. The computer-implemented method of claim 2, wherein the predetermined trigger is at least one of an elapsed time period or a change in external condition of a user of the computing system.

4. The computer-implemented method of claim 2, wherein a portion of the initial prompt is modified to obtain the modified prompt, a portion of the initial seed is modified to obtain the modified seed, or a portion of the at least one initial condition is modified to obtain the at least one modified condition.

5. The computer-implemented method of claim 1, further comprising obtaining, by the computing system, a control weight for the text-to-image model.

6. The computer-implemented method of claim 1, wherein the initial prompt comprises at least one of a static noun, an external condition, a scene, a medium, or an adjective.

7. The computer-implemented method of claim 1, wherein the at least one initial condition comprises time.

8. The computer-implemented method of claim 1, wherein the text-to-image model includes a condition controller.

9. The computer-implemented method of claim 1, wherein the text-to-image model is a text-to-image-sequence model.

10. A computer system for generating a clock face image for a computing device, the computer system comprising: one or more processors; and one or more non-transitory computer-readable media that collectively store instructions that, when executed by the one or more processors, cause the computer system to perform operations, the operations comprising: obtaining an initial prompt that specifies desired content of the clock face image; obtaining an initial seed that specifies desired composition of the clock face image; obtaining at least one initial condition that specifies desired style of the clock face image; processing the initial prompt, the initial seed, and the at least one initial condition with a text-to-image model; and providing the clock face image.

11. The computer system of claim 10, wherein the computing device is a wearable computing device, and wherein the wearable computing device includes at least one processor of the one or more processors and at least one non-transitory computer-readable medium of the one or more non-transitory computer-readable media.

12. The computer system of claim 11, wherein the wearable computing device comprises a display screen, and wherein providing the clock face image comprises displaying the clock face image on the display screen.

13. The computer system of claim 11, wherein the text-to-image model is implemented by the wearable computing device.

14. The computer system of claim 11, wherein the text-to-image model is stored and implemented by a server computing system that communicates with the wearable computing device.

15. The computer system of claim 10, wherein the operations further comprise, after a predetermined trigger: obtaining at least one of a modified prompt, a modified seed, or at least one modified condition; processing the at least one of the modified prompt, the modified seed, and the at least one modified condition with the text-to-image model; and providing a modified clock face image.

16. The computer system of claim 15, wherein the predetermined trigger is at least one of an elapsed time period or a change in external condition of a user of the computer system.

17. The computer system of claim 15, wherein a portion of the initial prompt is modified to obtain the modified prompt, a portion of the initial seed is modified to obtain the modified seed, or a portion of the at least one initial condition is modified to obtain the at least one modified condition.

18. A wearable computing device comprising: one or more processors; a memory: one or more user input devices; and a display screen configured to display the clock face image generated as described in claim 1.

19. The wearable computing device of claim 18. wherein a user inputs the initial prompt using at least one of the one or more user input devices.

20. The wearable computing device of claim 18, wherein the memory comprises one or more non-transitory computer-readable media that collectively store instructions that, when executed by the one or more processors, cause the wearable computing device to perform one or more operations to generate the clock face image.

Images