Zazzle Inc.

A computer-implemented method and apparatus for generating a quadrilateral grid from an image with an alpha channel. The method includes receiving an image with an alpha channel depicting a shape mapped onto a 3D surface, vectorizing the shape to create a vector path, determining corners by calculating a centroid and identifying the points, correcting a winding order to ensure a clockwise orientation, constructing a quadrilateral grid by setting sub-paths based on detected corners, resampling the sub-paths to match specified rows and columns, performing weighted interpolation across the grid using inverse square distance weighting, and outputting the generated quadrilateral grid for display on a computer device. The apparatus comprises a processor configured to execute these steps, including vectorizing the shape, determining corners, correcting the winding order, constructing and resampling the grid, performing weighted interpolation, and subdividing the 3D mesh for flexible manipulation and extrapolation.

A computer-implemented method and apparatus for generating and validating digital markups on customizable products. The method includes receiving a textual prompt describing a product and a desired markup, generating a synthetic image of the product with the markup using a generative AI model, and validating the synthetic image by comparing the synthetic image with known product metrics. The method further involves isolating and recognizing specific markup regions, refining the synthetic image based on validation results, generating manufacturing instructions, and providing the instructions to a manufacturing system. The apparatus comprises an AI-assisted markup generator, a validation and correction system, an image segmentation and recognition module, a generative image evaluation and correction module, a manufacturing instruction generator, and a descriptive phrase processor. The apparatus utilizes various generative AI models, machine learning algorithms, and advanced segmentation techniques to ensure the accurate and efficient production of customizable products.

A computer-implemented method for generating and refining synthetic video content comprises: receiving a text prompt describing a product and a markup; generating a synthetic image of the product having the markup using a generative artificial intelligence (GAI) system; validating the synthetic image against physical product specifications; mapping the synthetic image onto a 3D surface; applying inpainting techniques to remove the markup; generating an enhanced synthetic image by incorporating lighting and specular effects; generating an interactive asset by mapping the enhanced synthetic image onto the 3D surface of the product; generating using the GAI system a video frame sequence; for each frame, generating a vector data file for the interactive asset; generating a video data file based on each vector data file for each frame, and customization instructions; and transmitting the video data file and the customization instructions to a manufacturing entity for rendering of the interactive asset.

A computer-implemented method and apparatus for generating and refining synthetic images of customizable products. The method includes receiving a text prompt describing a product and a desired markup, generating a synthetic image using a generative AI system, validating the image against physical product specifications, mapping the image onto a 3D surface using quadrilateral grid interpolation, applying inpainting techniques to remove the markup while preserving fabric details, incorporating lighting and specular effects to enhance realism, and integrating the enhanced image into an interactive asset for user interaction and customization prior to manufacturing. The apparatus comprises a generative AI system, a validation and correction module, a 3D mapping and image synthesis module, an inpainting module, an interactive asset creation system, depth estimation and mapping tools, and a lighting and specular effects module. The system supports real-time customization and multiple design variations, ensuring conformity with physical specifications.

In some embodiments, a data processing method for generating a synthetic view rendering of a custom product, the method comprises: initializing, for a digital asset, a coverage mapping array; wherein each member of the coverage mapping array represents a possible coverage of sub-pixel regions of a pixel, and can be held in a scalar instruction register of a computer microprocessor; calculating a distance of each edge of the triangle from a center of a sub-pixel using a single scalar set instruction, operating on a pair of two scalar instruction set registers; using the distance and an angle of the edge to select a member of the array; combining pairs of found members of the coverage mapping array using the single scalar set instruction, operating on the pair, to assemble a sub-pixel coverage map array; rendering the pixel using the sub-pixel coverage mapping array and the sub-pixel regions of the pixel.

In some embodiments, a method for generating digital image extensions contextually based on a custom image comprises: determining a plurality of image elements in a custom image based on one or more characteristics associated with image elements of the plurality of image elements; determining a plurality of product components of a custom product; for each product component: selecting one or more first image elements based on element characteristics associated with the one or more first image elements; based on the product component and the one or more first image elements, generating a first request for customizing the product component of the custom product; transmitting the first request to an AI-based image generator to cause the AI-based image generator to generate a first customized synthetic images for the product component; including the first customized synthetic images in a region corresponding to the product component of the custom product.

In some embodiments, a computer-implemented AI-driven method for generating and refining embroidery designs comprises: receiving, by a design generator of a system, a reference design and a text prompt; generating an embroidery-friendly design image; determining, by a global decisions module of the system, high-level embroidery plans for the embroidery-friendly design image; refining, by a local decisions module of the system, the high-level embroidery plans to generate detailed stitch instructions; rendering, by a visualizer of the system, a visualization of based on the embroidery-friendly design image and the detailed stitch instructions; scoring and reordering, by a reranker of the system, variations of the high-level embroidery plans; receiving feedback and corrections from various sources; updating, by a trainer of the system, parameters of the design generator, the global decisions module, and the local decisions module based on the feedback and the corrections to improve future embroidery designs.

In an embodiment, an apparatus for generating embroidery designs comprises: a design generator configured to receive input data including at least one of a text prompt, a reference image, or a combination thereof, and to generate an embroidery-friendly design image; a global decisions module configured to receive the embroidery-friendly design image and metadata, and to generate one or more high-level embroidery plans; a local decisions module configured to receive the one or more high-level embroidery plans and to generate detailed stitch instructions for each Manufacturable Component and layer, including stitch directions, stitch density, and modifications to entry and exit points; a visualizer configured to render multiple variations of the detailed stitch instructions and embroidery designs for review; a reranker configured to score and filter the variations of the detailed stitch instructions; a trainer configured to collect inputs, outputs, and feedbacks to improve the modules.

A computer-implemented method, for generating and using functional data containers (ZIGs) for designing, visualizing, and manufacturing a customizable product is disclosed. In some embodiments, the method comprises: initiating an application for generating functional data containers (ZIGs) and causing reading a list of resources that includes ZIGs and images; generating, using product definition information from each of the sets of product+manufacturing instructions, a proxy representation, of proxies, of each set that defines a transformation translation mechanism; combining the proxies and images into a file and saving the file; in response to determining that the file is used by another software application, opening the file in the another software application to allow editing the proxies, and saving the file with the set of product+manufacturing instructions once editing the proxies is complete.

A method and apparatus for real-time animation and customization of products on a client-side device are disclosed. The technique involves receiving external inputs as identifier+value pairs, updating key-value pairs of a product description within a functional data container, and triggering resources to generate image frames representing customization stages. These frames are displayed as an animation to visualize product customization. The functional data container and product options are stored as identifier+value pairs in the device's memory, allowing local editing and updating without a web service connection. The final instructions are pushed to initiate manufacturing, with system optimization to mitigate connectivity issues and enhance performance. The apparatus includes a processor, memory, display, and communication interface to support these functions, ensuring data security and user experience stability. The system supports various data formats and employs data compression, with optional synchronization with cloud services and machine learning algorithms to optimize customization.