US 12,731,302 B2 · Rapid rendering and/or realistic visualization of apparel design draft files through application of one or more generative artificial neural networks

a coordination server comprising:

a processor of the coordination server;

a memory of the coordination server;

a draft receipt agent comprising computer readable instructions that when executed receive a draft file of a first image comprising a sketch of one or more apparel items;

a description module comprising computer readable instructions that when executed receive a text description comprising a description of the one or more apparel items,

wherein the text description comprises a positive description of one or more attributes to be present in the one or more apparel items and a negative description of one or more attributes to be excluded from the one or more apparel items;

a generative model selection routine comprising computer readable instructions that when executed select generative image model configured to generate an output image constrained by both the first image of the one or more apparel items and a first set of latent representations that includes at least one of one or more latent representations of a text-image relation model;

a model parameterization subroutine comprising computer readable instructions that when executed:

select the text-image relation model configured to relate the text description to the one or more latent representations of the text-image relation model, and

parameterize the generative image model with a set of model parameters comprising at least one of (i) a convolution step value, (ii) a constraint divergence value, (iii) a quality value of the output image;

(iv) a size value of the output image;

(v) a generative seed, (vi) a sampler model, (vii) a decoding algorithm, and (viii) a denoise algorithm;

a generative divergence engine comprising computer readable instructions that when executed:

generate second set of model parameters, wherein the second set of model parameters differs from the set of model parameters in at least one of:

the constraint divergence value, the generative seed, the text description, the positive description, the negative description, and the sampler model,

initiate a first request for generating a second set of latent representations of the one or more latent representations of the text-image relation model based on reduced constraint in the of the text-image relation model, and

initiate a second request for generating an alternative rendering file comprising a third image of the one or more apparel items;

a rendering delivery subroutine comprising computer readable instructions that when executed transmit a first rendering file and the alternative rendering file to a user,

wherein the generative divergence engine further comprising computer readable instructions that when executed receive a preference selection from the user for the alternative rendering file;

a generative tracking subroutine comprising computer readable instructions that when executed store the second set of model parameters and optionally lock the generative seed;

a generative structuring engine comprising computer readable instructions that when executed:

generate a graph data structure comprising:

a model selection node comprising attributes and associated values specifying a directed edge from the model selection node to an image generation model node, a directed edge from the model selection node to a text-image relation node, and a directed edge from the model selection node to a decoding algorithm node;

the text-image relation node comprising attributes and associated values specifying a directed edge from the text-image relation node to the image generation model node and storing a directed edge to the generative image model at least one of (i) the positive description of the one or more apparel items, and (ii) the negative description of the one or more apparel items;

a base parameterization node comprising attributes and associated values storing the size value of the output image and at least one of a directed edge from the base parameterization node to the image generation model node and from the image generation model node to the base parameterization node;

and

the image generation model node, comprising attributes and values storing the set of model parameters and a directed edge from the image generation model node to the decoding algorithm node;

an apparel segmentation engine comprising computer readable instructions that when executed:

input at least one of the draft file and the first rendering file into a computer vision model trained with a first set of training images comprising data distinguishing apparel items, and

generate a segmentation file comprising one or more boundary designations of the one or more apparel items;

an apparel rendering routine comprising computer readable instructions that when executed:

receive a selection of a boundary designation of the one or more boundary designations of the one or more apparel items to select an apparel item bounded by the boundary designation,

receive a new text description comprising a description of the apparel item bounded by the boundary designation,

request a second set of latent representations from at least one of the text-image relation model and a different text-image relation model based on the new text description, and

input into the generative image model at least a portion of the first rendering file within the boundary designation, the second set of latent representations of the text-image relation model, and a different set of model parameters,

a material identification routine comprising computer readable instructions that when executed input at least one of the draft file and the first rendering file into a computer vision model trained with a set of training images comprising data designating a material value associated with at least one of an apparel item and an apparel element;

the system further comprising a generative server comprising:

a processor of the generative server;

a memory of the generative server;

and

a latent image storage routine comprising computer readable instructions that when executed store the first set of latent representations from the text-image relation model;

and

a generative model execution engine comprising computer readable instructions that when executed:

input into the generative image model a set of inputs of the generative image model comprising (i) the draft file comprising the first image of the one or more apparel items, (ii) the first set of latent representations of the text-image relation model, and (iii) the set of model parameters, and

generate the first rendering file, wherein the first rendering file comprising a second image of the one or more apparel items modified by the text description to allow for at least one of rapid visualization, prototyping, and construction of the one or more apparel items;

generate a second rendering file re-rendering the apparel item bounded by the boundary designation;

and

the system further comprising a network communicatively coupling the coordination server and the generative server.

Rapid rendering and/or realistic visualization of apparel design draft files through application of one or more generative artificial neural networks

Life of this patent

Rapid rendering and/or realistic visualization of apparel design draft files through application of one or more generative artificial neural networks

Life of this patent

Abstract

Claims20