CTNF 18/958,842 CTNF 101698 Notice of Pre-AIA or AIA Status 07-03-aia AIA 15-10-aia The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA. Claim Rejections - 35 USC § 103 07-06 AIA 15-10-15 In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status. 07-20-aia AIA The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action: A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made. 07-23-aia AIA The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows: 1. Determining the scope and contents of the prior art. 2. Ascertaining the differences between the prior art and the claims at issue. 3. Resolving the level of ordinary skill in the pertinent art. 4. Considering objective evidence present in the application indicating obviousness or nonobviousness. 07-21-aia AIA Claim s 1-20 are rejected under 35 U.S.C. 103 as being unpatentable over Sarukkai et al (Collage Diffusion, hereinafter Sarukkai) in view of Lopez et al (US11449664B1, hereinafter Lopez) . Regarding claim 1, Sarukkai teaches a method comprising: receiving, by a user, a style kit including a first image generation input indicating a first image attribute, a second image generation input indicating a second image attribute, and a selectability parameter indicating that the second image generation input is selectable; (Figure 2 description “Figure 2. Collage Diffusion takes as input a sequence of layers of RGBA images paired with text (the image of sushi and the text “sushi”), along with a full-image text string (“A bento box with rice, edamame, ginger, and sushi”).”, where full-image text string corresponds to a first image generation input, and sequence of layers of RGBA images paired with text correspond to second image generation input) , receiving a third image generation input from the user based on the selectability parameter, wherein the third image generation input indicates a third image attribute different from the second image attribute of the second image generation input (Sect 5.2 “and (3) selecting an object in this image that they would like to re-generate” where regenerating results in a different image attribute, corresponding to a third image generation input, Figure 4 description “then improves the images using two refinement iterations, re-generating one of the original input layers in each refinement iteration.”, where each original input layer corresponds to a second image attribute) ; and generating, using an image generation model, a synthetic image based on the style kit , the first image generation input, and the third image generation input, wherein the synthetic image has the first image attribute and the third image attribute (Sect 5.2 “(1) generating 10 images using different random seeds, (2) allowing the user to select the image they like the most, and (3) selecting an object in this image that they would like to re-generate. This process continues until the user is satisfied with all aspects of the generated image.”, where user input causes an object corresponding to a second image attribute to be regenerated, corresponding to a third image attribute, and the final generated image includes attributes from regenerated objects and from the original text string, Page 4200, 5.1 Experimental Setup “1. SA : Image generation with Self-Attention control via Plug-and-Play Diffusion [30] applied to composite image xc, with negative prompt “A collage”. This is a baseline that does not leverage layer information, but maintains the image structure of xc via self-attention control”, where SA corresponds to an image generation model) Sarukkai fails to explicitly teach a style kit and a selectability parameter indicating that the second image generation input is selectable . In related field of endeavor, Lopez teaches a style kit (Col 3 Line 4-12 “a first device or application (e.g., a user using a design application 190) may create and export a template, which may be associated with an entity and which may describe a structure and visual representation for a content item. The technology may export the template including generating parameters and a preview for the template, storing a template file and an asset package of the template, and storing the template in the template database”, where template corresponds to style kit (Paragraph 0004 of the applicant’s specification states “The image generation template is also referred to as a style kit”)) and a selectability parameter indicating that the second image generation input is selectable (Col 3 Line 24-28 “the media publishing application 196 or another device used by the technology may lock (e.g., for editing, access, or use), unlock, or provide attribution for the template based on ownership, creator identification, association, or user action.”) It would have been obvious to one of ordinary skill in the art prior to the time of filing to have modified Sarukkai to include a style kit and a selectability parameter indicating that the second image generation input is selectable as taught by Lopez. Doing so would provide a means of sharing templates between users (Lopez Col 3 Line 14-15 “a second user may use the template to create a content item using a media publishing application”). Regarding claim 2, Sarukkai as modified by Lopez teach the method of claim 1. Sarukkai further teaches receiving, by another user , the first image generation input, the second image generation input (Figure 2 description “Figure 2. Collage Diffusion takes as input a sequence of layers of RGBA images paired with text (the image of sushi and the text “sushi”), along with a full-image text string (“A bento box with rice, edamame, ginger, and sushi”).”), but fails to explicitly teach receiving by another user, a selectability input indicating the selectability of the second image generation input; and generating, by the another user, the style kit based on the first image generation input, the second image generation input, and the selectability input. In related field of endeavor, Lopez teaches receiving by another user (Col 3 Line 14-16 “a second user may use the template to create a content item using a media publishing application 196”), a selectability input indicating the selectability of the second image generation input; and generating, by the another user, the style kit based on the first image generation input, the second image generation input, and the selectability input (Col 3 Line 4-12 “a first device or application (e.g., a user using a design application 190) may create and export a template, which may be associated with an entity and which may describe a structure and visual representation for a content item. The technology may export the template including generating parameters and a preview for the template, storing a template file and an asset package of the template, and storing the template in the template database”, Col 3 Line 24-28 “the media publishing application 196 or another device used by the technology may lock (e.g., for editing, access, or use), unlock, or provide attribution for the template based on ownership, creator identification, association, or user action.”). Regarding claim 3, Sarukkai as modified by Lopez teach the method of claim 2. Sarukkai fails to explicitly teach further comprising: providing a permission selection tool; and receiving the selectability input via the permission selection tool, wherein the selectability parameter is based on the selectability input. In related field of endeavor, Lopez teaches further comprising: providing a permission selection tool; and receiving the selectability input via the permission selection tool, wherein the selectability parameter is based on the selectability input (Col 3 Line 24-28 “the media publishing application 196 or another device used by the technology may lock (e.g., for editing, access, or use), unlock, or provide attribution for the template based on ownership, creator identification, association, or user action”, where user action corresponds to selectability input, Col 11 Line 15-21 “For instance, the user may join a mailing list, purchase access to a template list, watch an advertisement, or perform another action, which may cause the management server 194 to store an association or key providing access to the template(s) to the user, account, user device 920, or instance of the media publishing application 196.”) . It would have been obvious to one of ordinary skill in the art to have modified Sarukkai to include providing a permission selection tool; and receiving the selectability input via the permission selection tool, wherein the selectability parameter is based on the selectability input as taught by Lopez. Doing so would allow a user to select accessibility for a generated template (Col 3 Line 24-28 “the media publishing application 196 or another device used by the technology may lock (e.g., for editing, access, or use), unlock, or provide attribution for the template based on ownership, creator identification, association, or user action.”) Regarding claim 4, Sarukkai as modified by Lopez teach the method of claim 2. Sarukkai fails to explicitly teach further comprising: receiving an additional selectability input indicating a non-selectability of the first image generation input, wherein the style kit comprises an additional selectability parameter corresponding to the additional selectability input. In related field of endeavor, Lopez teaches further comprising: receiving an additional selectability input indicating a non-selectability of the first image generation input, wherein the style kit comprises an additional selectability parameter corresponding to the additional selectability input (Col 3 Line 24-28 “The media publishing application 196 or another device used by the technology may lock (e.g., for editing, access, or use), unlock, or provide attribution for the template based on ownership, creator identification, association, or user action”, Col 11 Line 15-21 “For instance, the user may join a mailing list, purchase access to a template list, watch an advertisement, or perform another action, which may cause the management server 194 to store an association or key providing access to the template(s) to the user, account, user device 920 , or instance of the media publishing application 196 .”). It would have been obvious to one of ordinary skill in the art to have further modified Sarukkai and Lopez to include receiving an additional selectability input indicating a non-selectability of the first image generation input, wherein the style kit comprises an additional selectability parameter corresponding to the additional selectability input as taught by Lopez. Doing so would allow templates to be locked (Col 3 Line 24-28 “the media publishing application 196 or another device used by the technology may lock (e.g., for editing, access, or use), unlock, or provide attribution for the template based on ownership, creator identification, association, or user action.”). Regarding claim 5, Sarukkai as modified by Lopez teach the method of claim 1. Sarukkai further teaches wherein: the first image generation input and the second image generation input correspond to different image generation input categories selected from a set of image generation input categories comprising a text prompt category, a foreground image category, a background image category, an image structure category, an image size category, an aspect ratio category, a content type category, a style category, or any combination thereof. (Page 4197, Figure 2. “Collage Diffusion takes as input a sequence of layers of RGBA images paired with text (the image of sushi and the text “sushi”), along with a full-image text string (“A bento box with rice, edamame, ginger, and sushi”).”, where the full-image text string corresponds to a text prompt, and a sequence of layers of RGBA images paired with text can correspond to a variety of categories, Fig 5 Toys shows sequence of layers of RGBA images corresponding to text prompt, foreground image, and background image) PNG media_image1.png 676 424 media_image1.png Greyscale Sarukkai Fig 5 Regarding claim 6, Sarukkai as modified by Lopez teach the method of claim 1. Lopez further teaches displaying a selection element for the second image generation input based on the selectability parameter . (Col 3 Line 35-40 “the second user may then interact with a user interface provided by the media publishing application 196 to modify the content item and/or components of the first template in which the content item is integrated and, in some instances, export the modified content item”, Col 4 Line 26-32 “as depicted in the user interfaces 300, 400, and 500 in FIGS. 3-5, the design application 190 may include a text field in a template page and receive input from the user defining a text format, include a sticker(s) in a template page, or otherwise customize a template page(s), etc., using various editing tools provided in the user interfaces to design the template”) It would have been obvious to one of ordinary skill in the art prior to the effective filing date to have further modified Sarukkai and Lopez to include displaying a selection element for the second image generation input based on the selectability parameter as taught by Lopez. Doing so would provide an interface for users to interact with inputs (Col 3 Line 35-38 “the second user may then interact with a user interface provided by the media publishing application 196 to modify the content item and/or components of the first template in which the content item is integrated”). Regarding claim 7, Sarukkai as modified by Lopez teach the method of claim 1. Sarukkai further teaches wherein: the third image generation input comprises a same image generation input category as the second image generation input. (Figure 4 description “then improves the images using two refinement iterations, re-generating one of the original input layers in each refinement iteration.”, where each original input layer corresponds to a second image generation input, and the regenerated layer corresponds to a third image generation input which is the same category as the original input layer.) Regarding claim 8, Sarukkai as modified by Lopez teach the method of claim 1. Sarukkai further teaches wherein generating the synthetic image comprises: obtaining a noise input; and performing a diffusion process on the noise input. (Figure 4, included below, shows obtaining a noise input, Page 4200, 5.1 Experimental Setup “1. SA: Image generation with Self-Attention control via Plug-and-Play Diffusion [30] applied to composite image xc, with negative prompt “A collage”. This is a baseline that does not leverage layer information, but maintains the image structure of xc via self-attention control”, where SA corresponds to an image generation model, Page 4201, 5.1 Experimental Setup step 5 “GH+CA+TI+LN( Collage Diffusion ): GH applied to composite image xc with both CA and TI, with per Layer Noise control”, Page 4201 Model and optimization “We use the Stable Diffusion [24] 2.1 base model as Dθ for GH, GH+CA, GH+CA+TI, and GH+CA+TI+LN, and generate images using the Euler ancestral solver with 50 steps”) PNG media_image2.png 557 421 media_image2.png Greyscale Regarding claim 9, Sarukkai teaches obtaining a style kit including a first image generation input indicating a first image attribute and a selectability parameter indicating that the first image generation input is selectable (Figure 2 description “Figure 2. Collage Diffusion takes as input a sequence of layers of RGBA images paired with text (the image of sushi and the text “sushi”), along with a full-image text string (“A bento box with rice, edamame, ginger, and sushi”, where a sequence of layers of RGBA images paired with text corresponds to a first image generation input, Sect 5.2 “We illustrate interactive editing with Collage Diffusion by repeatedly (1) generating 10 images using different random seeds, (2) allowing the user to select the image they like the most, and (3) selecting an object in this image that they would like to re-generate.”, where the selectable objects correspond to the first image generation input) ; receiving, via the user interface, a second image generation input indicating a second image attribute different from the first image attribute (Figure 2 description “Figure 2. Collage Diffusion takes as input a sequence of layers of RGBA images paired with text (the image of sushi and the text “sushi”), along with a full-image text string (“A bento box with rice, edamame, ginger, and sushi”, where a full-image text string corresponds to a second image generation input.) ; and generating, using an image generation model, a synthetic image based on the style kit and the second image generation input, wherein the synthetic image has the second image attribute (Sect 5.2 “(1) generating 10 images using different random seeds, (2) allowing the user to select the image they like the most, and (3) selecting an object in this image that they would like to re-generate. This process continues until the user is satisfied with all aspects of the generated image.”) . Sarukkai fails to explicitly teach a non-transitory computer readable medium storing code for image processing, the code comprising instructions that, when executed by at least one processor, cause the at least one processor to perform operations, and obtaining a style kit including a selectability parameter indicating that the first image generation input is selectable, and providing a user interface for replacing the first image generation input based on the selectability parameter. In related field of endeavor, Lopez teaches a non-transitory computer readable medium storing code for image processing, the code comprising instructions that, when executed by at least one processor, cause the at least one processor to perform operations (Col 13, Line 19-21 “The processor 1004 may execute software instructions by performing various input, logical, and/or mathematical operations.”, Col 13 Line 33-36 “the processor 1004 may be coupled to the memory 1006 via the bus 1010 to access data and instructions therefrom and store data therein.”) obtaining a style kit including a selectability parameter indicating that the first image generation input is selectable; (Col 3 Line 4-12 “a first device or application (e.g., a user using a design application 190) may create and export a template, which may be associated with an entity and which may describe a structure and visual representation for a content item. The technology may export the template including generating parameters and a preview for the template, storing a template file and an asset package of the template, and storing the template in the template database”, Col 3 Line 24-28 “the media publishing application 196 or another device used by the technology may lock (e.g., for editing, access, or use), unlock, or provide attribution for the template based on ownership, creator identification, association, or user action.”) and providing a user interface for replacing the first image generation input based on the selectability parameter (Col 3 Line 35-40 “the second user may then interact with a user interface provided by the media publishing application 196 to modify the content item and/or components of the first template in which the content item is integrated and, in some instances, export the modified content item”); It would have been obvious to one of ordinary skill in the art prior to the effective filing date to have modified Sarukkai to include a non-transitory computer readable medium storing code for image processing, the code comprising instructions that, when executed by at least one processor, cause the at least one processor to perform operations, and obtaining a style kit including a selectability parameter indicating that the first image generation input is selectable, and providing a user interface for replacing the first image generation input based on the selectability parameter as taught by Lopez. Doing so would provide a user interface for interacting with the generation model, and allow users to restrict access to templates (Lopez Col 3 Line 24-28 “the media publishing application 196 or another device used by the technology may lock (e.g., for editing, access, or use), unlock, or provide attribution for the template based on ownership, creator identification, association, or user action.”) Regarding claim 10, Sarukkai as modified by Lopez teaches the non-transitory computer readable medium of claim 9. Sarukkai further teaches wherein: the second image generation input has a same image generation input category as the first image generation input (Figure 2 description “Figure 2. Collage Diffusion takes as input a sequence of layers of RGBA images paired with text (the image of sushi and the text “sushi”), along with a full-image text string (“A bento box with rice, edamame, ginger, and sushi”, where both image generation inputs include text) . Regarding claim 11, Sarukkai as modified by Lopez teaches the non-transitory computer readable medium of claim 9. Sarukkai further teaches wherein: the first image generation input and the second image generation input correspond to different image generation input categories selected from a set of image generation input categories comprising a text prompt category, a foreground image category, a background image category, an image structure category, an image size category, an aspect ratio category, a content type category, a style category, or any combination thereof (Figure 2 description “Figure 2. Collage Diffusion takes as input a sequence of layers of RGBA images paired with text (the image of sushi and the text “sushi”), along with a full-image text string (“A bento box with rice, edamame, ginger, and sushi”, the full-image text string corresponds to the second image generation input and comprises a text prompt category, and the sequence of layers of RGBA images paired with text may correspond to a variety of categories, Figure 5 Toys shows input layers corresponding to foreground images and background images) . PNG media_image1.png 676 424 media_image1.png Greyscale Sarukkai Fig 5 Regarding claim 12, Sarukkai as modified by Lopez teaches the non-transitory computer readable medium of claim 9 . Sarukkai further teaches obtaining the first image generation input (Figure 2 description “Figure 2. Collage Diffusion takes as input a sequence of layers of RGBA images paired with text (the image of sushi and the text “sushi”), along with a full-image text string (“A bento box with rice, edamame, ginger, and sushi”)”, where a sequence of layers of RGBA images paired with text corresponds to a first image generation input) Sarukkai fails to explicitly teach obtaining a selectability input indicating the selectability of the first image generation input; and generating the style kit based on the first image generation input and the selectability input. In related field of endeavor, Lopez teaches obtaining a selectability input indicating the selectability of the first image generation input (Col 3 Line 24-28 “the media publishing application 196 or another device used by the technology may lock (e.g., for editing, access, or use), unlock, or provide attribution for the template based on ownership, creator identification, association, or user action.”); and generating the style kit based on the first image generation input and the selectability input (Col 3 Line 4-12 “a first device or application (e.g., a user using a design application 190) may create and export a template, which may be associated with an entity and which may describe a structure and visual representation for a content item. The technology may export the template including generating parameters and a preview for the template, storing a template file and an asset package of the template, and storing the template in the template database”). It would have been obvious to one of ordinary skill in the art to have further modified Sarukkai and Lopez to include obtaining a selectability input indicating the selectability of the first image generation input; and generating the style kit based on the first image generation input and the selectability input as taught by Lopez. Doing so would allow a user to restrict access to their template (Col 3 Line 24-28 “the media publishing application 196 or another device used by the technology may lock (e.g., for editing, access, or use), unlock, or provide attribution for the template based on ownership, creator identification, association, or user action.”) Regarding claim 13, Sarukkai and Lopez teach the non-transitory computer readable medium of claim 9. Sarukkai fails to explicitly teach wherein providing the user interface comprises: displaying a selection element corresponding to the first image generation input. In related field of endeavor, Lopez teaches wherein providing the user interface comprises: displaying a selection element corresponding to the first image generation input (Col 4 Line 26-32 “as depicted in the user interfaces 300, 400, and 500 in FIGS. 3-5, the design application 190 may include a text field in a template page and receive input from the user defining a text format, include a sticker(s) in a template page, or otherwise customize a template page(s), etc., using various editing tools provided in the user interfaces to design the template”) PNG media_image3.png 376 569 media_image3.png Greyscale Lopez Fig 3-5 It would have been obvious to one of ordinary skill in the art to have further modified Sarukkai and Lopez to include wherein providing the user interface comprises: displaying a selection element corresponding to the first image generation input as taught by Lopez. Doing so would allow a user to modify elements of the image generation (Col 4 Line 26-32 “as depicted in the user interfaces 300, 400, and 500 in FIGS. 3-5, the design application 190 may include a text field in a template page and receive input from the user defining a text format, include a sticker(s) in a template page, or otherwise customize a template page(s), etc., using various editing tools provided in the user interfaces to design the template”) Regarding claim 14, Sarukkai and Lopez teach the non-transitory compute readable medium of claim 9. Sarukkai fails to explicitly teach wherein: the user interface displays a plurality of image generation inputs, and wherein a subset of the plurality of image generation inputs is selectable. In related field of endeavor, Lopez teaches wherein: the user interface displays a plurality of image generation inputs, and wherein a subset of the plurality of image generation inputs is selectable (Col 4 Line 26-32 “as depicted in the user interfaces 300 , 400 , and 500 in FIGS. 3-5, the design application 190 may include a text field in a template page and receive input from the user defining a text format, include a sticker(s) in a template page, or otherwise customize a template page(s), etc., using various editing tools provided in the user interfaces to design the template”) . It would have been obvious to one of ordinary skill in the art prior to the time of filing to have further modified Sarukkai and Lopez to include wherein: the user interface displays a plurality of image generation inputs, and wherein a subset of the plurality of image generation inputs is selectable as taught by Lopez. Doing so would provide an interface to allow a user to modify image generation inputs (Col 4 Line 26-32 “as depicted in the user interfaces 300, 400, and 500 in FIGS. 3-5, the design application 190 may include a text field in a template page and receive input from the user defining a text format, include a sticker(s) in a template page, or otherwise customize a template page(s), etc., using various editing tools provided in the user interfaces to design the template”) PNG media_image3.png 376 569 media_image3.png Greyscale Lopez Fig 3-5 Regarding claim 15, Sarukkai and Lopez teach the non-transitory computer readable medium of claim 9 . Sarukkai fails to explicitly teach the code further comprising instructions executable by the at least one processor to perform operations comprising: providing a permission selection tool; and receiving a selectability input via the permission selection tool, wherein the selectability parameter is based on the selectability input. In related field of endeavor, Lopez teaches the code further comprising instructions executable by the at least one processor to perform operations comprising: providing a permission selection tool; and receiving a selectability input via the permission selection tool, wherein the selectability parameter is based on the selectability input (Col 3 Line 24-28 “the media publishing application 196 or another device used by the technology may lock (e.g., for editing, access, or use), unlock, or provide attribution for the template based on ownership, creator identification, association, or user action.”) It would have been obvious to one of ordinary skill in the art to have further modified Sarukkai and Lopez to include teaches the code further comprising instructions executable by the at least one processor to perform operations comprising: providing a permission selection tool; and receiving a selectability input via the permission selection tool, wherein the selectability parameter is based on the selectability input as taught by Lopez. Doing so would allow the user to adjust the access permissions of their template (Col 3 Line 24-28 “the media publishing application 196 or another device used by the technology may lock (e.g., for editing, access, or use), unlock, or provide attribution for the template based on ownership, creator identification, association, or user action.”) Regarding claim 16, Sarukkai teaches obtaining a style kit including a first image generation input indicating a first image attribute, a second image generation input indicating a second image attribute (Figure 2 description “Figure 2. Collage Diffusion takes as input a sequence of layers of RGBA images paired with text (the image of sushi and the text “sushi”), along with a full-image text string (“A bento box with rice, edamame, ginger, and sushi”).”, where full-image text string corresponds to a first image attribute, and sequence of layers of RGBA images paired with text correspond to second image attribute) , receiving a third image generation input from a user based on the selectability parameter, wherein the third image generation input indicates a third image attribute different from the second image attribute of the second image generation input (Sect 5.2 “and (3) selecting an object in this image that they would like to re-generate” where regenerating results in a different image attribute, corresponding to a third image generation input, Figure 4 description “then improves the images using two refinement iterations, re-generating one of the original input layers in each refinement iteration.”, where each original input layer corresponds to a second image attribute) ; and generating, using an image generation model, a synthetic image based on the style kit, the first image generation input, and the third image generation input, wherein the synthetic image has the first image attribute and the third image attribute (Sect 5.2 “(1) generating 10 images using different random seeds, (2) allowing the user to select the image they like the most, and (3) selecting an object in this image that they would like to re-generate. This process continues until the user is satisfied with all aspects of the generated image.”, where user input causes an object corresponding to a second image attribute to be regenerated, corresponding to a third image attribute, and the final generated image includes attributes from regenerated objects and from the original text string) . Sarukkai fails to explicitly teach A system comprising: a memory component; and a processing device coupled to the memory component, the processing device configured to perform operations and obtaining a style kit including a selectability parameter indicating that the second image generation input is selectable. In related field of endeavor, Lopez teaches A system comprising: a memory component; and a processing device coupled to the memory component, the processing device configured to perform operations (Col 13, Line 19-21 “The processor 1004 may execute software instructions by performing various input, logical, and/or mathematical operations.”, Col 13 Line 33-36 “the processor 1004 may be coupled to the memory 1006 via the bus 1010 to access data and instructions therefrom and store data therein.”) and obtaining a style kit including a selectability parameter indicating that the second image generation input is selectable (Col 3 Line 24-28 “the media publishing application 196 or another device used by the technology may lock (e.g., for editing, access, or use), unlock, or provide attribution for the template based on ownership, creator identification, association, or user action.”) It would have been obvious to one of ordinary skill in the art prior to the time of filing to have modified Sarukkai to include A system comprising: a memory component; and a processing device coupled to the memory component, the processing device configured to perform operations and obtaining a style kit including a selectability parameter indicating that the second image generation input is selectable as taught by Lopez. Doing so would provide a system for performing the operations, and allow users to control access to created templates (Col 3 Line 24-28 “the media publishing application 196 or another device used by the technology may lock (e.g., for editing, access, or use), unlock, or provide attribution for the template based on ownership, creator identification, association, or user action.”) Regarding claim 17, Sarukkai and Lopez teach the system of claim 16 . Sarukkai further teaches wherein: the image generation model comprises a diffusion model (Page 4200, 5.1 Experimental Setup “1. SA: Image generation with Self-Attention control via Plug-and-Play Diffusion [30] applied to composite image xc, with negative prompt “A collage”. This is a baseline that does not leverage layer information, but maintains the image structure of xc via self-attention control”, where SA corresponds to an image generation model) . Regarding claim 18, Sarukkai and Lopez teach the system of claim 16. Sarukkai further teaches wherein: the image generation model comprises a text encoder, a style encoder, a structure encoder, or any combination thereof (Page 4198 Image-to-Image Approaches Par 1 “self-attention [30]) to maintain image structure while making either local edits (adding/removing/modifying objects) or global edits (style, lighting).”, Page 4199 4.3. Appearance fidelity: inversion and ControlNet Par 1 “We offer per-layer control over two aspects of the input layer: the unique attributes of the real-world object, such as colors, textures, and shape, as well as the image structure, including edges and poses.”, Par 2 “layer text ci is specialized to image xi by learning a modifier token ai per layer, prepended to the layer text: (ai,ci). ai serves as an adjective describing the object in layer li, subject to the constraints of the existing layer description ci.”) . Regarding claim 19, Sarukkai and Lopez teach the system of claim 16 . Sarukkai fails to explicitly teach wherein: the system comprises a user interface configured to display the first image generation input and the second image generation input. In related field of endeavor, Lopez teaches wherein: the system comprises a user interface configured to display the first image generation input and the second image generation input (Col 4 Line 26-32 “as depicted in the user interfaces 300 , 400 , and 500 in FIGS. 3-5, the design application 190 may include a text field in a template page and receive input from the user defining a text format, include a sticker(s) in a template page, or otherwise customize a template page(s), etc., using various editing tools provided in the user interfaces to design the template.”) It would have been obvious to one of ordinary skill in the art prior to the time of filing to have further modified Sarukkai and Lopez to include wherein: the system comprises a user interface configured to display the first image generation input and the second image generation input as taught by Lopez. Doing so would provide a user interface to allow the user to adjust the inputs (Col 4 Line 27-29 “the design application 190 may include a text field in a template page and receive input from the user”) Regarding claim 20, Sarukkai and Lopez teach the system of claim 19 . Sarukkai fails to explicitly teach wherein: the user interface includes an element for saving the style kit and an additional element for sharing the style kit. In related field of endeavor, Lopez teaches wherein: the user interface includes an element for saving the style kit and an additional element for sharing the style kit (Col 8 Line 61-67 “the media publishing application 196 may receive a user input and accordingly export the result content item. In some instances, a user may select an option from a user interface provided by the media publishing application 196 to save the result content item to a data store, insert it into a document, upload it to a website, or post it to a social network page, etc.”) . It would have been obvious to one of ordinary skill in the art prior to the time of filing to have further modified Sarukkai and Lopez to include wherein: the user interface includes an element for saving the style kit and an additional element for sharing the style kit as taught by Lopez. Doing so would provide a way for the user to save and distribute content (Col 8 Line 63-67 “a user may select an option from a user interface provided by the media publishing application 196 to save the result content item to a data store, insert it into a document, upload it to a website, or post it to a social network page, etc.”) Conclusion 07-96 AIA The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. Collage Diffusion UI (Li et al, hereinafter Li) teaches a user interface (Shown below) for performing the method described by Sarukkai above . PNG media_image4.png 1328 1326 media_image4.png Greyscale Collage Diffusion UI (Li) Any inquiry concerning this communication or earlier communications from the examiner should be directed to JOHN PATRICK GOCO whose telephone number is (571)272-5872. The examiner can normally be reached M-Th, 7:00 am - 5:00 pm. Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice. If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Kee Tung can be reached at (571)272-7794. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300. Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000. /KEE M TUNG/Supervisory Patent Examiner, Art Unit 2611 /J.P.G./Examiner, Art Unit 2611 Application/Control Number: 18/958,842 Page 2 Art Unit: 2611 Application/Control Number: 18/958,842 Page 3 Art Unit: 2611 Application/Control Number: 18/958,842 Page 4 Art Unit: 2611 Application/Control Number: 18/958,842 Page 5 Art Unit: 2611 Application/Control Number: 18/958,842 Page 6 Art Unit: 2611 Application/Control Number: 18/958,842 Page 7 Art Unit: 2611 Application/Control Number: 18/958,842 Page 8 Art Unit: 2611 Application/Control Number: 18/958,842 Page 9 Art Unit: 2611 Application/Control Number: 18/958,842 Page 10 Art Unit: 2611 Application/Control Number: 18/958,842 Page 11 Art Unit: 2611 Application/Control Number: 18/958,842 Page 12 Art Unit: 2611 Application/Control Number: 18/958,842 Page 13 Art Unit: 2611 Application/Control Number: 18/958,842 Page 14 Art Unit: 2611 Application/Control Number: 18/958,842 Page 15 Art Unit: 2611 Application/Control Number: 18/958,842 Page 16 Art Unit: 2611 Application/Control Number: 18/958,842 Page 17 Art Unit: 2611 Application/Control Number: 18/958,842 Page 18 Art Unit: 2611 Application/Control Number: 18/958,842 Page 19 Art Unit: 2611 Application/Control Number: 18/958,842 Page 20 Art Unit: 2611 Application/Control Number: 18/958,842 Page 21 Art Unit: 2611 Application/Control Number: 18/958,842 Page 22 Art Unit: 2611 Application/Control Number: 18/958,842 Page 23 Art Unit: 2611 Application/Control Number: 18/958,842 Page 24 Art Unit: 2611 Application/Control Number: 18/958,842 Page 25 Art Unit: 2611
