Abstract: The disclosed technology includes a computer-implemented technique for predicting or estimating physical attributes of products depicted in images is disclosed. The method includes receiving one or more images—either photographs of real-world products or synthetic images generated from user-provided descriptions—processing the images using one or more machine learning (ML) models trained to detect and measure physical characteristics, and predicting or estimating measures such as volume, weight, and dimensions. The system can identify product categories, select appropriate ML models, and generate natural language descriptions of predicted attributes for user display. Training datasets may include both real and synthetic images with known attributes, and user feedback can be incorporated to improve model accuracy.

Abstract: The disclosed technology includes a computer-implemented technique for generating images of physically producible products in response to user input describing a conceptual product. The system receives user input—such as natural language text, speech, or images—via a user interface, configures a prompt for a generative artificial intelligence (AI) system, and generates an image representing a version of the conceptual product with distinct physical attributes. Each version is associated with a unique identifier, enabling selection, modification, and purchase of the conceptual product. The system supports multiple product categories, including jewelry, home décor, and fashion, and extracts physical attributes to determine manufacturability and pricing. User feedback is incorporated to improve AI performance. The invention enables presentation of selectable product versions and initiates manufacturing processes based on user selections, supporting unstructured user input and multiple data modalities.

Abstract: The disclosed technology includes a computer-implemented technique for generating images of synthetic products that are manufacturable as physical products is disclosed. The system receives user input describing a conceptual product via a user interface, including text and/or image data. Based on the input, a manufacturer-specific or general generative model is selected and provided with a text-based prompt derived from the conceptual product description. The model generates one or more images of synthetic products, each conforming to manufacturing constraints. The images are presented to the user, each optionally associated with pricing and delivery information, and represent products that are manufacturable and acquirable via the interface. The system may incorporate manufacturability analysis, quality assurance, and model training using user feedback and product data.

Abstract: A computer-implemented technique for preprocessing user input to generate images of synthetic products representing conceptual products includes receiving user input, including text and/or images, indicative of a conceptual product, and selecting a machine learning (ML) model from a set of models based on characteristics such as product category or maker. Image inputs can be converted to text-based descriptions, combined with text inputs, and configured as a prompt instruction for the selected ML model, incorporating constraints (e.g., material, production, cost) and user feedback. The ML model can generate one or more images of a synthetic product, which can be refined iteratively based on further feedback. The system supports recognition of known and unknown objects in images and can adapt prompt instructions accordingly. The generated images include synthetic products that are producible as physical products, enabling efficient conceptual product visualization and refinement.