DETAILED ACTION
Notice of Pre-AIA or AIA Status
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
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.
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.
Claim(s) 1, 16, and 21 is/are rejected under 35 U.S.C. 103 as being unpatentable over Zhu et al. (US 2025/0284723 A1) in view of Mallya et al. (US 2021/0374552 A1).
Regarding claim 1, Zhu discloses a method comprising: obtaining an input image and a text prompt comprising an image modification request; (Paragraph 0029, image extracted from a video and a user entered prompt to apply a visual editing component to the image) generating, using a language generation model, a text response based on the input image and the text prompt, wherein the text response describes a modification to the input image corresponding to the image modification request; (Paragraph 0029, a vision language model generates a text description based on the user prompt to apply the video editing component to the image) Zhu further discloses an output embedding of the language generation model (Paragraph 0031, generation of label embeddings using text labels based on the text descriptions of the visual language model, figure 3) and wherein the synthetic image depicts the modification to the input image (Claim 1, applying the visual editing component to video). Zhu does not clearly disclose generating, using an image generation model, a synthetic image based on the input image and an output embedding of the language generation model. Mallya discloses generating output images or video frames using input from a label embedding network and input images or video frames (Paragraph 0054). Mallya’s technique of generating output images or video frames using input from a label embedding network and input images or video frames would have been recognized by one of ordinary skill in the art to be applicable to the images for applying visual editing components to and label embeddings of Zhu and the results would have been predictable in the generation of output images with applied visual editing components based on input images and label embeddings. Therefore, the claimed subject matter would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention.
Regarding claim 16, Zhu discloses an apparatus comprising: at least one processor; (Paragraph 0056, CPU) at least one memory storing instructions executable by the at least one processor; (Paragraph 0061, mass storage device storing application programs) a language generation model trained to generate a text response based on an input image and a text prompt (Paragraph 0029, a vision language model generates a text description based on a user prompt to apply a video editing component to an image extracted from a video). Zhu further discloses an output embedding of the language generation model (Paragraph 0031, generation of label embeddings using text labels based on the text descriptions of the visual language model, figure 3). Zhu does not clearly disclose a language generation model comprising parameters stored in the at least one memory and an image generation model comprising parameters stored in the at least one memory and trained to generate a synthetic image based on the input image and an output embedding of the language generation model. Mallya discloses generating output images or video frames using input from a label embedding network and input images or video frames (Paragraph 0054) with models using stored parameters (Paragraphs 0068 and 0083). Mallya’s technique of generating output images or video frames using input from a label embedding network and input images or video frames with models using stored parameters would have been recognized by one of ordinary skill in the art to be applicable to the images for applying visual editing components to and label embeddings of Zhu and the results would have been predictable in the generation of output images with applied visual editing components based on input images and label embeddings using with models using stored parameters. Therefore, the claimed subject matter would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention.
Regarding claim 21, similar reasoning as discussed in claim 1 is applied.
Claim(s) 2, 3, 18, 22, and 23 is/are rejected under 35 U.S.C. 103 as being unpatentable over Zhu et al. (US 2025/0284723 A1) in view of Mallya et al. (US 2021/0374552 A1) and further in view of Liu et al. (US 2024/0282016 A1).
Regarding claim 2, Zhu in view of Mallya discloses all limitations as discussed in claim 1. Zhu in view of Mallya does not clearly disclose wherein generating the synthetic image comprises: encoding, using an image encoder, the input image to obtain an image embedding, wherein the synthetic image is generated based on the image embedding. Liu discloses an image encoder that generates embeddings based on a received image that are used for synthesizing a new image (Paragraph 0074). Liu’s technique of using an image encoder to generate embeddings based on a received images for synthesizing a new image would have been recognized by one of ordinary skill in the art to be applicable to extracted images for applying visual editing components to of Zhu in view of Mallya and the results would have been predictable in using an image encoder to generate embeddings for extracted images for synthesizing a new image with applied visual editing components. Therefore, the claimed subject matter would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention.
Regarding claim 3, Zhu in view of Mallya and further in view of Liu discloses transforming, using an image projection layer of the language generation model, the image embedding to obtain a projected image embedding, wherein the text response and the output embedding are based on the projected image embedding (Zhu, paragraphs 0034-0035, different embeddings can be projected into a common space including the embeddings generated for images, Liu, paragraph 0074).
Regarding claim 18, Zhu in view of Mallya discloses all limitations as discussed in claim 1. Zhu in view of Mallya does not clearly disclose an image embedding of the input image. Liu discloses an image encoder that generates embeddings based on a received image that are used for synthesizing a new image (Paragraph 0074). Liu’s technique of using an image encoder to generate embeddings based on a received images for synthesizing a new image would have been recognized by one of ordinary skill in the art to be applicable to extracted images for applying visual editing components to of Zhu in view of Mallya and the results would have been predictable in using an image encoder to generate embeddings for extracted images for synthesizing a new image with applied visual editing components. Therefore, the claimed subject matter would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention. Zhu in view of Mallya and further in view of Liu further discloses an image projection layer comprising parameters stored in the at least one memory and configured to transform an image embedding of the input image to obtain a projected image embedding (Zhu, paragraphs 0034-0035, different embeddings can be projected into a common space including the embeddings generated for images, Liu, paragraph 0074, where the model for projecting uses stored parameters, Mallya, 0068 and 0083).
Regarding claim 22, similar reasoning as discussed in claim 2 is applied.
Regarding claim 23, similar reasoning as discussed in claim 3 is applied.
Claim(s) 4, 7, 19, 20, 24, and 27 is/are rejected under 35 U.S.C. 103 as being unpatentable over Zhu et al. (US 2025/0284723 A1) in view of Mallya et al. (US 2021/0374552 A1) and further in view of Francis (US 2024/0185498 A1).
Regarding claim 4, Zhu in view of Mallya discloses all limitations as discussed in claim 1. Zhu in view of Mallya does not clearly disclose wherein generating the synthetic image comprises: transforming, using a guidance projection layer of the language generation model, the output embedding of the language generation model to obtain a guidance embedding, wherein the synthetic image is generated based on the guidance embedding. Francis discloses using a language model to generate text embeddings as guidance for generating an image relevant to text descriptions (Paragraph 0032). Francis’ technique of using a language model to generate text embeddings as guidance for generating an image relevant to text descriptions would have been recognized by one of ordinary skill in the art to be applicable to the effect description for applying visual editing components to an image of Zhu in view of Mallya and the results would have been predictable in using a language model to generate text embeddings for generating an image with applied visual effects relevant to an effect description. Therefore, the claimed subject matter would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention.
Regarding claim 7, Zhu in view of Mallya discloses all limitations as discussed in claim 1. Zhu in view of Mallya does not clearly disclose the language generation model is trained to generate a guidance embedding for the image generation model; and the image generation model is trained to generate the synthetic image based on the guidance embedding. Francis discloses using a language model to generate text embeddings as guidance for generating an image relevant to text descriptions (Paragraph 0032). Francis’ technique of using a language model to generate text embeddings as guidance for generating an image relevant to text descriptions would have been recognized by one of ordinary skill in the art to be applicable to the effect description for applying visual editing components to an image of Zhu in view of Mallya and the results would have been predictable in using a language model to generate text embeddings for generating an image with applied visual effects relevant to an effect description. Therefore, the claimed subject matter would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention.
Regarding claim 19, Zhu in view of Mallya discloses all limitations as discussed in claim 1. Zhu in view of Mallya does not clearly disclose a guidance projection layer comprising parameters stored in the at least one memory and configured to transform the output embedding of the language generation model to obtain a guidance embedding. Francis discloses using a language model with parameters to generate text embeddings as guidance for generating an image relevant to text descriptions (Paragraphs 0032 and 0035). Francis’ technique of using a language model with models to generate text embeddings as guidance for generating an image relevant to text descriptions would have been recognized by one of ordinary skill in the art to be applicable to the effect description for applying visual editing components to an image with stored parameters of Zhu in view of Mallya and the results would have been predictable in using a language model with stored parameters to generate text embeddings for generating an image with applied visual effects relevant to an effect description. Therefore, the claimed subject matter would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention.
Regarding claim 20, Zhu in view of Mallya discloses all limitations as discussed in claim 16. Zhu in view of Mallya does not clearly disclose the image generation model comprises a diffusion model. Francis discloses using a diffusion model to generate images (Abstract). Francis’ technique of using a diffusion model to generate images would have been recognized by one of ordinary skill in the art to be applicable to the generation of an image with applied visual editing components of Zhu in view of Mallya and the results would have been predictable in the generation of an image with applied visual editing components using a diffusion model. Therefore, the claimed subject matter would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention.
Regarding claim 24, similar reasoning as discussed in claim 4 is applied.
Regarding claim 27, similar reasoning as discussed in claim 7 is applied.
Claim(s) 5, 6, 25, and 26 is/are rejected under 35 U.S.C. 103 as being unpatentable over Zhu et al. (US 2025/0284723 A1) in view of Mallya et al. (US 2021/0374552 A1) and further in view of Hsiao (US 2022/0092728 A1).
Regarding claim 5, Zhu in view of Mallya discloses all limitation as discussed in claim 1. Zhu in view of Mallya does not clearly disclose wherein generating the synthetic image comprises: obtaining a reference image, wherein the synthetic image is generated based on the reference image. Hsiao discloses transferring style from a reference image to video frames to generate stylized video frames (Paragraph 0051). Hsiao’s technique of transferring style from a reference image to video frames to generate stylized video frames would have been recognized by one of ordinary skill in the art to be applicable to the images extracted from a video for applying visual editing components of Zhu in view of Mallya and the results would have been predictable in transferring style from a reference image to images with applied visual editing effects to generate stylized images with applied visual editing effects. Therefore, the claimed subject matter would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention.
Regarding claim 6, Hsiao discloses generating a plurality of images by iteratively adjusting a parameter that balances the input image and the reference image (Paragraph 0051, sets of weights for the style transfer where different values would affect the generation of the generated stylized images with applied visual effects).
Regarding claim 25, similar reasoning as discussed in claim 5 is applied.
Regarding claim 26, similar reasoning as discussed in claim 6 is applied.
Claim(s) 17 is/are rejected under 35 U.S.C. 103 as being unpatentable over Zhu et al. (US 2025/0284723 A1) in view of Mallya et al. (US 2021/0374552 A1) in view of Liu et al. (US 2024/0282016 A1) and further in view of Willmott et al. (US 2025/0191337 A1).
Regarding claim 17, Zhu in view of Mallya discloses all limitations as discussed in claim 16. Zhu in view of Mallya does not clearly disclose an image encoder configured to encode the input image to obtain an image embedding. Liu discloses an image encoder that generates embeddings based on a received image that are used for synthesizing a new image (Paragraph 0074). Liu’s technique of using an image encoder to generate embeddings based on a received images for synthesizing a new image would have been recognized by one of ordinary skill in the art to be applicable to extracted images for applying visual editing components to of Zhu in view of Mallya and the results would have been predictable in using an image encoder to generate embeddings for extracted images for synthesizing a new image with applied visual editing components. Therefore, the claimed subject matter would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention. Zhu in view of Mallya and further in view of Liu does not clearly disclose an image encoder comprising parameters stored in the at least one memory. Willmott discloses an image encoder with updatable parameters (Abstract). Willmott’s technique of providing an image encoder with updatable parameters would have been recognized by one of ordinary skill in the art to be applicable to the image encoder that synthesizes a new image with models having stored parameters of Zhu in view of Mallya and further in view of Liu and the results would have been predictable in an image encoder with stored updatable parameters for synthesizing a new image. Therefore, the claimed subject matter would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Showalter et al. (US 2025/0245883 A1) discloses modifying an image using a diffusion model and natural language prompts.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to PHI HOANG whose telephone number is (571)270-3417. The examiner can normally be reached Mon-Fri 8:00-5:00.
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, JASON CHAN can be reached at (571)272-3022. 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.
/PHI HOANG/Primary Examiner, Art Unit 2619
Prosecution Insights