Shareable Style Kits With Selectable Image Generation Settings
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional image generation models fail to store generative settings and parameters as a template that can be shared with other users, lacking control over which settings of the image generation template others can remix or adjust to make their own synthetic images.
Innovation Solution
An image generation system that allows users to create a style kit, a package of image generation inputs and settings, which can be shared with others, enabling them to remix or adjust specific inputs while maintaining control over which settings are selectable or non-selectable.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If image generation models generate images based on input parameters, then image generation capability is improved, but the ability to store and share generative settings as templates is lost
Solution Approach 1:
The system stores generative settings and parameters as templates before they are needed for image generation. Users can create and save style kits with their preferred settings in advance, which are then available for future use and sharing, eliminating the loss of information about generative parameters.
Solution Approach 2:
The patent enables copying of generative settings by creating shareable templates that replicate the complete set of parameters and styles. Users can copy their configured settings and share them with others, allowing the information to be transmitted without loss while maintaining the original generation capability.
2Adaptability or versatility
If image generation templates are shared with users, then collaboration and reusability are improved, but control over which settings others can modify is lost
Solution Approach 1:
The system applies different qualities of control to different settings within the template. Certain parameters are marked as selectable (modifiable) while others are locked, allowing localized customization. This enables users to control exactly which settings others can modify based on the specific needs of each parameter.
Solution Approach 2:
The template system dynamically determines which settings are selectable based on the specific template and user permissions. The system can adapt the modifiability of settings on a per-template basis, allowing flexible control over what users can modify while maintaining overall template integrity.
3Adaptability or versatility
If all settings in a style kit are made selectable, then user customization is improved, but control over which settings can be modified is reduced
Solution Approach 1:
Instead of making all settings uniformly selectable or non-selectable, the system applies local quality control where individual settings within the style kit can be independently marked as selectable or locked. This allows fine-grained control over which specific parameters users can modify while maintaining customization capability where needed.
Data Source
AI summary
A method, apparatus, non-transitory computer readable medium, and system for image processing include obtaining a style kit including a first image generation input indicating a first image attribute, a second image generation input indicating a second image attribute, and a selectability parameter indicating that the second image generation input is selectable. A third image generation input is received from a user based on the selectability parameter, wherein the third image generation input indicates a third image attribute different from the second image attribute of the second image generation input. An image generation model generates a synthetic image based on the style kit, the first image generation input, and the third image generation input, wherein the synthetic image has the first image attribute and the third image attribute.