Asset creation using generative artificial intelligence
A method including collecting one or more inputs, each of which describes a target object. The method including generating a plurality of images of the target object using an image generation artificial intelligence system configured for implementing latent diffusion based on the one or more inputs. The method including decomposing the target object into a first plurality of attributes based on the plurality of images of the target object, wherein each of the plurality of attributes includes one or more variations. The method including receiving selection of one or more of a plurality of variations of the plurality of attributes. The method including blending the one or more of the plurality of variations of the plurality of attributes that have been selected into one or more options of the target object.
1 . A method, comprising:
collecting one or more inputs, each of which describes a target object;
generating a plurality of images of the target object using an image generation artificial intelligence (AI) system configured for implementing latent diffusion based on the one or more inputs;
decomposing the target object into a plurality of attributes based on the plurality of images of the target object, wherein each of the plurality of attributes includes one or more variations;
receiving selection of one or more of a plurality of variations of the plurality of attributes; and
blending the one or more of the plurality of variations of the plurality of attributes that have been selected into one or more options of the target object.
2 . The method of claim 1 , further comprising:
providing a prompt to the image generation AI system to generate the plurality of images of the target object.
3 . The method of claim 2 , wherein the decomposing the target object includes:
providing the plurality of images of the target object to an AI model configured to extract the plurality of attributes from the plurality of images.
4 . The method of claim 1 , further comprising:
editing one or more of the plurality of variations of the plurality of attributes; and
using the image generation AI system to generate a second plurality of attributes for the target object based on the one or more of the plurality of variations of the plurality of attributes that have been edited and the one or more inputs that have been collected.
5 . The method of claim 4 , wherein the editing of the one or more of the plurality of variations of the plurality of attributes includes:
receiving selection of a variation of an attribute;
receiving an editing input; and
tuning the variation of the attribute based on the editing input for inclusion in the plurality of variations of the plurality of attributes.
6 . The method of claim 4 , wherein the editing of the one or more of the plurality of variations of the plurality of attributes includes:
filtering a variation of an attribute based on at least one filtering parameter.
7 . The method of claim 4 , wherein the editing of the one or more of the plurality of variations of the plurality of attributes includes:
receiving selection of a variation of an attribute;
receiving an editing input; and
favorably or unfavorably selecting the variation of the attribute based on the editing input.
8 . The method of claim 4 , wherein the editing of the one or more of the plurality of variations of the plurality of attributes includes:
receiving selection of a variation of an attribute;
receiving an editing input; and
locking the variation of the attribute based on the editing input.
9 . The method of claim 1 ,
determining that no variation of an attribute has been selected; and
automatically selecting a variation of the attribute for performing the blending of the plurality of variations of the plurality of attributes that have been selected.
10 . The method of claim 1 , further comprising:
saving at least one of the plurality of variations of the plurality of attributes that has been selected for use in building a second target object.
11 . A computer system comprising:
a processor;
memory coupled to the processor and having stored therein instructions that, if executed by the computer system, cause the computer system to execute a method, comprising:
collecting one or more inputs, each of which describes a target object;
generating a plurality of images of the target object using an image generation artificial intelligence (AI) system configured for implementing latent diffusion based on the one or more inputs;
decomposing the target object into a plurality of attributes based on the plurality of images of the target object, wherein each of the plurality of attributes includes one or more variations;
receiving selection of one or more of a plurality of variations of the plurality of attributes; and
blending the one or more of the plurality of variations of the plurality of attributes that have been selected into one or more options of the target object.
12 . The computer system of claim 11 , the method further comprising:
editing one or more of the plurality of variations of the plurality of attributes; and
using the image generation AI system to generate a second plurality of attributes for the target object based on the one or more of the plurality of variations of the plurality of attributes that have been edited and the one or more inputs that have been collected.
13 . The computer system of claim 12 , wherein in the method the editing of the one or more of the plurality of variations of the plurality of attributes includes:
receiving selection of a variation of an attribute;
receiving an editing input; and
tuning the variation of the attribute based on the editing input for inclusion in the plurality of variations of the plurality of attributes.
14 . The computer system of claim 12 , wherein in the method the editing of the one or more of the plurality of variations of the plurality of attributes includes:
receiving selection of a variation of an attribute;
receiving an editing input; and
favorably or unfavorably selecting the variation of the attribute based on the editing input.
15 . The computer system of claim 12 , wherein in the method the editing of the one or more of the plurality of variations of the plurality of attributes includes:
receiving selection of a variation of an attribute;
receiving an editing input; and
locking the variation of the attribute based on the editing input.
16 . A non-transitory computer-readable storage medium storing a computer program executable by a processor-based system, comprising:
program instructions for collecting one or more inputs, each of which describes a target object;
program instructions for generating a plurality of images of the target object using an image generation artificial intelligence (AI) system configured for implementing latent diffusion based on the one or more inputs;
program instructions for decomposing the target object into a plurality of attributes based on the plurality of images of the target object, wherein each of the plurality of attributes includes one or more variations;
program instructions for receiving selection of one or more of a plurality of variations of the plurality of attributes; and
program instructions for blending the one or more of the plurality of variations of the plurality of attributes that have been selected into one or more options of the target object.
17 . The non-transitory computer-readable storage medium of claim 16 , further comprising:
program instructions for editing one or more of the plurality of variations of the plurality of attributes; and
program instructions for using the image generation AI system to generate a second plurality of attributes for the target object based on the one or more of the plurality of variations of the plurality of attributes that have been edited and the one or more inputs that have been collected.
18 . The non-transitory computer-readable storage medium of claim 17 , wherein the editing of the one or more of the plurality of variations of the plurality of attributes includes:
program instructions for receiving selection of a variation of an attribute;
program instructions for receiving an editing input; and
program instructions for tuning the variation of the attribute based on the editing input for inclusion in the plurality of variations of the plurality of attributes.
19 . The non-transitory computer-readable storage medium of claim 17 , wherein the editing of the one or more of the plurality of variations of the plurality of attributes includes:
program instructions for receiving selection of a variation of an attribute;
program instructions for receiving an editing input; and
program instructions for favorably or unfavorably selecting the variation of the attribute based on the editing input.
20 . The non-transitory computer-readable storage medium of claim 17 , wherein the editing of the one or more of the plurality of variations of the plurality of attributes includes:
program instructions for receiving selection of a variation of an attribute;
program instructions for receiving an editing input; and
program instructions for locking the variation of the attribute based on the editing input.