Generative on English AI Terms Dictionary

Stable Diffusion

Sat, 18 Jul 2026 10:16:41 +0000

Definition

Stable Diffusion is a deep learning model that generates detailed images conditioned on text inputs using a latent diffusion process. Unlike pixel-space diffusion models, it operates in a compressed latent space, significantly reducing computational requirements while maintaining high fidelity. Developed by Stability AI and others, it has become a cornerstone of generative AI, enabling users to create diverse visual content from natural language prompts. Its open-source nature has fostered a vast ecosystem of extensions, fine-tunes, and community-driven tools.

Flow-based generative model

Sat, 18 Jul 2026 09:58:20 +0000

Definition

Flow-based generative models construct complex probability distributions by applying a series of invertible, differentiable transformations to a simple base distribution, such as a Gaussian. Because the transformations are invertible, these models can compute the exact likelihood of data points efficiently. This property distinguishes them from other generative models like GANs or VAEs, offering precise density estimation and exact sampling without approximation errors.

Summary

A class of generative models that use invertible transformations to map simple distributions to complex data distributions.

Generated

Sat, 18 Jul 2026 09:32:39 +0000

Definition

The term ‘generated’ describes output produced by generative AI models, such as text, images, audio, or code. Unlike retrieval-based systems that fetch existing data, generative models synthesize new content based on learned patterns from training data. This process involves predicting the next token or pixel sequence. Generated content is central to applications like chatbots, creative design tools, and automated coding assistants, distinguishing dynamic creation from static storage.

Summary

Content created by an AI model rather than retrieved directly from a static dataset.