> For the complete documentation index, see [llms.txt](https://metaverse-imagen.gitbook.io/ai-tools-research/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://metaverse-imagen.gitbook.io/ai-tools-research/ai-technology/generative-ai-architectures-and-models.md). # Generative Ai Architectures & Models **Generative AI refers to a type of Artificial Intelligence that can create new content.** It does so by learning patterns from existing data and then using these patterns to generate similar but unique output. This content could be anything from written text to images, music, voice, and more. The fundamental idea is to use algorithms to mimic the creative process of humans, creating something novel based on what they have learned. **Generative AI Models** Generative AI models are the algorithms that power generative AI. They're trained on large amounts of data and learn to predict or generate new data that resembles the input they have been trained on. They can produce high-quality, novel creations by understanding and replicating patterns found in the input data. A popular type of generative AI model is the Generative Adversarial Network (GAN). In GANs, two neural networks are pitted against each other. The generator network creates new data instances, while the discriminator network evaluates them for authenticity; i.e., whether they appear similar to the training data or not. Through this competition, the generator improves its ability to create plausible data, and the discriminator enhances its ability to detect fakes, resulting in an increasingly sophisticated generation of new data. Another common type of generative model is the Variational Autoencoder (VAE), which generates new instances by learning a lower-dimensional representation of the input data, then sampling from this learned distribution to create new data. An example of a generative AI model is OpenAI's GPT (Generative Pretrained Transformer), used to generate human-like text. The model has been trained on vast amounts of text data and can generate creative, coherent, and contextually relevant sentences by predicting what text should come next given a specific input. Generative AI models are widely used in various fields like Copywriting and Text creation, Imaging, Art, Design, Audio. Music, Video, Healthcare, etc., for tasks ranging from creating digital art, generating music, generating video and animations, designing buildings, drug discovery, and more. These AI models fall into the following categories; a) Text Generation using NLP (Natural Language processing) b) Image Generation c) Audio Generation d) Video Generation f) Hybrid (Text, Images, Video and Audio) - latest advanced models --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://metaverse-imagen.gitbook.io/ai-tools-research/ai-technology/generative-ai-architectures-and-models.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.