Conditional procedural model generation

A system comprising:

• a memory component;
• and
• a processing device coupled to the memory component, the processing device to perform operations including:
• training a machine learning model to generate procedural models based on input digital images;
• receiving an input including an input digital image having a particular visual appearance;
• and
• generating a procedural model including a sequence of parametrized nodes connected by one or more edges usable to recreate the particular visual appearance of the input digital image using the trained machine learning model.

A non-transitory computer-readable storage medium storing executable instructions, which when executed by a processing device, cause the processing device to perform operations comprising:

• training a node transformer, an edge transformer, and a parameter transformer of a machine learning model configured to generate procedural models;
• receiving, in a user interface of the processing device, an input to initiate generation of a procedural model;
• generating, responsive to the input, a node sequence using the node transformer and an edge sequence using the edge transformer of the machine learning model;
• generating a parameter sequence using the parameter transformer based on the node sequence and the edge sequence;
• and
• generating the procedural model based on the node sequence, the edge sequence, and the parameter sequence.