# How AI Generates Images Based on Style and Content Cues > This patent describes an artificial intelligence system that creates new images by understanding both what the image should show (like a cat) and how it should look (like a high-quality photo), using a special internal layer to blend these instructions. - **Patent:** US 12141700 - **Original title:** Generative adversarial network for generating images - **Owner:** Naver - **Granted:** 2024 - **Status:** Active - **Times cited:** 3 - **Field:** ai_ml, software, consumer_electronics, telecommunications ## What it does This patent details a generative adversarial network (GAN) that creates synthetic images. It uses two main parts: a generator neural network and a discriminator neural network. The generator takes a random 'noise vector' and a pair of 'conditioning variables' as input (Claim 1). One variable describes 'semantic information,' like what objects are in the image, and the other describes 'aesthetic information,' such as its quality or style (Claim 1). A key part of the generator is a 'mixed-conditional batch normalization layer' which normalizes the data flow within the network (Abstract, Claim 1). This layer uses the semantic and aesthetic conditioning variables to adjust its internal parameters, allowing it to precisely control how the generated image reflects both content and style (Abstract, Claim 1). For example, you could ask it to generate a 'dog' (semantic) that looks 'beautiful' (aesthetic). ## What it does NOT cover - Does not cover image generation systems that only use semantic information without also incorporating aesthetic information as a distinct conditioning variable. - Does not cover GANs that generate images without using a 'mixed-conditional batch normalization layer' that specifically adjusts its parameters based on both semantic and aesthetic inputs. - Does not cover image generation where the conditioning variables are not applied via an 'affine transformation' to compute the normalization layer's parameters. - Does not cover image generation where the aesthetic information is not provided as 'continuous information in the form of histogram score distributions' (Claim 1). ## The clever bit The clever part is how the patent uses a 'mixed-conditional batch normalization layer' within the generator. This layer dynamically adjusts its internal scaling and shifting parameters based on both semantic (what it is) and aesthetic (how it looks) instructions, allowing the AI to blend these two types of guidance seamlessly when creating an image. ## Real-world examples 1. AI art generators that allow users to specify style and content 2. Tools for generating synthetic datasets with controlled visual properties for training other AIs 3. Image editing software offering style transfer or content-aware generation features 4. Virtual try-on applications where clothing style and fit are controlled ## Why it matters This technology is important because it allows for more precise control over AI-generated images. Instead of just asking an AI to create 'a dog,' this system enables users to specify 'a beautiful dog' or 'a low-quality dog,' giving creators fine-grained control over both content and style. This level of control is crucial for applications where specific visual characteristics are desired, moving beyond simple object generation to nuanced artistic or functional outputs. ## Frequently asked questions ### What does How AI Generates Images Based on Style and Content Cues cover? This patent describes an artificial intelligence system that creates new images by understanding both what the image should show (like a cat) and how it should look (like a high-quality photo), using a special internal layer to blend these instructions. ### Who owns patent US 12141700? Naver owns this patent, granted in 2024. ### When does this patent expire? This patent is expected to expire on September 17, 2040, when the invention enters the public domain. ### What is patent US 12141700 cited by? This patent has been cited by 3 later patents that build on its ideas. ### What problem does this patent solve? This technology is important because it allows for more precise control over AI-generated images. Instead of just asking an AI to create 'a dog,' this system enables users to specify 'a beautiful dog' or 'a low-quality dog,' giving creators fine-grained control over both content and style. This level of control is crucial for applications where specific visual characteristics are desired, moving beyond simple object generation to nuanced artistic or functional outputs. ### What does this patent NOT cover? Does not cover image generation systems that only use semantic information without also incorporating aesthetic information as a distinct conditioning variable. **Full plain-English explainer:** https://patentbrief.org/patent/us/12141700/generative-adversarial-network-for-generating-images **Original patent:** https://patents.google.com/patent/US12141700 --- _Source: PatentBrief — https://patentbrief.org. Patent facts are from public records; the plain-English explanation is PatentBrief's._ ## Related patents Semantically similar inventions in the PatentBrief corpus: - [How AI Transfers Visual Styles Between Images While Keeping Structure](https://patentbrief.org/patent/us/12282696/method-and-system-for-semantic-appearance-transfer-using-splicing-vit-features) — This patent describes an AI method to generate a new image that combines the structure of one input image with the visual style of another, semantically related image, using a pre-trained Vision Transformer model. - [How to Train AI Models with Fake Data Using Generative Networks](https://patentbrief.org/patent/us/20230297446/data-model-generation-using-generative-adversarial-networks) — This patent describes a method for training artificial intelligence models using specially generated fake, or 'synthetic,' data created by a generative adversarial network, ensuring the synthetic data is high-quality and safe for training. - [Creating Realistic Character Animations with AI Networks](https://patentbrief.org/patent/us/10964084/generating-realistic-animations-for-digital-animation-characters-utilizing-a-gen) — This patent describes how to generate lifelike digital character animations using artificial intelligence networks, specifically by predicting joint movements and overall body motion from either random inputs or specific key poses. - [How Cloud Systems Automatically Create and Train AI Data Models](https://patentbrief.org/patent/us/11615208/dall-e-text-to-image-generation) — A cloud-based system that generates fake, privacy-safe data to train AI models, ensuring they remain accurate while protecting sensitive personal information. - [Sharing AI Knowledge Between Private Datasets Using Synthetic Data](https://patentbrief.org/patent/us/12039012/systems-and-methods-for-heterogeneous-federated-transfer-learning) — This patent describes a method for two separate AI systems to share learned information by generating artificial data based on common features, without directly exchanging their private training data.