Comic Image Generation via Object Importance Levels
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional comic image generation methods ignore the generation differences between various objects, leading to increased resource consumption and reduced efficiency and rationality in image drawing.
Innovation Solution
A comic image generating method and apparatus that acquire target objects of multiple categories in a comic storyboard, determine target images based on object levels (determined by importance), and combine these images according to image layer levels to produce a comic image.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If a unified generation standard is adopted for image drawing, then the drawing process is simplified, but resource consumption increases and efficiency decreases
Solution Approach 1:
The patent applies local quality by differentiating image generation standards based on object importance levels. High-importance objects use detailed generation modes while low-importance objects use simplified generation modes, allowing each object to receive appropriate processing quality rather than uniform treatment, thus optimizing resource consumption and improving overall efficiency
2Device complexity
If a unified generation standard is adopted for image drawing, then the drawing process is simplified, but resource consumption increases
Solution Approach 1:
The patent implements local quality by assigning different generation standards to objects based on their importance levels. Critical objects receive high-quality detailed generation while less important objects receive simplified generation, enabling selective resource allocation that reduces overall resource consumption while maintaining necessary quality where needed
3Ease of manufacture
If all objects are drawn with the same detail level, then the generation process is uniform, but time consumption increases for lower-importance objects
Solution Approach 1:
The patent applies local quality by varying detail levels based on object importance. High-importance objects receive detailed generation while low-importance objects receive rapid simplified generation, creating non-uniform processing that reduces overall time consumption by avoiding unnecessary detailed processing on less critical objects
Data Source
AI summary
A comic image generating method, a computer device and a storage medium, wherein the method includes: acquiring target objects of a plurality of categories in a comic storyboard, wherein the plurality of categories at least include a character category, a scene category and a prop category; determining, for the target object of each category, a target image matching the target object according to an object level of the target object, wherein the object level is determined according to a degree of importance of the target object, and target images corresponding to the target objects with different object levels are determined through different image determination modes; and combining the target images matching the target objects according to image layer levels corresponding to the plurality of categories, to obtain a comic image corresponding to the comic storyboard.