Visual image generation method and device, electronic equipment and storage medium

Through the combination of large language model and image generation model, data themes and drawing styles are automatically processed, and image levels are generated and integrated, which solves the problems of the cumbersome process of generating visual images and the lack of automatic associative creation in the existing technology, and achieves rapid, beautiful and Information-rich image generation.

CN118941676APending Publication Date: 2024-11-12ZHEJIANG TONGHUASHUN INTELLIGENT TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410975519.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-18
Publication Date
2024-11-12

AI Technical Summary

Technical Problem

The prior art is cumbersome when generating visual images, requiring users to provide input content and instructions multiple times, and cannot automatically associate and create charts containing data content, and lack processing of event-related background images.

Method used

Use large language models to preprocess the data topics and detailed data, generate data intentions, drawing codes, drawing keywords and text content layers, combine the image generation model to generate background layers based on the drawing style and keywords, and fuse them into a complete visual image .

Benefits of technology

It realizes fast and automated visual image generation, reduces labor costs, and can create background layers that are coordinated with data content, and outputs beautiful and informative images.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118941676A_ABST
    Figure CN118941676A_ABST
Patent Text Reader

Abstract

The invention provides a visual image generation method and apparatus, an electronic device and a storage medium. The method comprises the steps of obtaining a data theme, detailed data and a drawing style; preprocessing the data theme and the detailed data by using a large language model to generate a data intention, a drawing code, a drawing keyword and a text content layer; drawing a basic chart layer according to the data intention and the drawing code; generating a background image layer according to the drawing style and the drawing keyword by using an image generation model; and fusing the text content layer, the basic chart layer and the background layer, and outputting a visual image.
Need to check novelty before this filing date? Find Prior Art