Multi-Reference Media Generation for Better Content Control

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing methods for generating media content, such as images or text descriptions, lack control and fail to meet user requirements for quality and customization.

Innovation Solution

A configuration interface is presented with input components for reference images and prompt items, allowing users to generate media content with multiple frames based on these inputs.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Manufacturing precision

If existing methods for generating media content are used, then the generation process is simple, but the quality and customization of the generated content cannot meet user requirements

Engineering Contradiction:
Improvequality of generated media contentVSAvoidcomplexity of generation system
Core Design Contradiction:
Manufacturing precisionVSDevice complexity

Solution Approach 1:

The generation system is segmented into multiple independent input components: text prompt input, reference image input, style reference input, and parameter control components. Each component handles a specific aspect of content generation, allowing users to control different dimensions independently while maintaining system modularity and manageability.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system transitions from traditional single-dimension text-to-image generation to multi-dimensional generation by incorporating reference images, style references, and adjustable parameters as additional control dimensions. This enables precise control over content, style, and composition simultaneously, significantly improving generation quality and customization without overwhelming complexity.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

2Ease of operation

If multiple input components are added to improve control, then user control over generated content improves, but the interface complexity increases

Engineering Contradiction:
Improveuser control over media contentVSAvoidinterface complexity
Core Design Contradiction:
Ease of operationVSDevice complexity

Solution Approach 1:

The configuration interface is designed as a universal multi-functional platform that integrates text processing, image upload, style selection, and parameter adjustment in a unified structure. This allows the same interface framework to handle various generation tasks (images, videos, styles) without requiring separate controls for each function, improving ease of operation while controlling complexity.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Data Source

PatentEP4654190A1Method, apparatus, device, and storage medium for generating media content
Publication Date: 2025.11.26 BEIJING YOUZHUJU NETWORK TECH CO LTD
  • EP4654190A1 patent drawingFigure 1~2A
  • EP4654190A1 patent drawingFigure 2B
  • EP4654190A1 patent drawingFigure 2C

AI summary

A method, an apparatus, a device, and a storage medium for generating media content are provided. The method proposed herein includes: in response to receiving a content generation request, presenting a configuration interface including at least a first input component and a second input component; obtaining a plurality of reference images via the first input component and a prompt item via the second input component; and generating a target media content based on the plurality of reference images and the prompt item, where the target media content includes a plurality of frames corresponding to the plurality of reference images. In this way, the user is supported to further control the generated target media content by inputting multiple reference images and prompt words, thereby improving quality of the generated target media content and enhancing user experience.