Diffusion Model
A diffusion model is a class of generative machine learning model that creates new data — most commonly images — by learning to reverse a gradual noising process, starting from pure random noise and iteratively denoising it, step by step, into a coherent output guided by a learned model and, often, a text prompt.
35 resources across 1 library
Glossary Terms(35)
DALL-E
DALL-E is a series of text-to-image generation models developed by OpenAI that create original images from natural-language text descriptions, and is integrate…
Stable Diffusion
Stable Diffusion is an open-weight text-to-image diffusion model originally released by Stability AI in 2022, notable for being runnable on consumer hardware a…
Imagen
Imagen is Google's family of text-to-image generation models, producing photorealistic and stylized images from natural-language prompts, with successive versi…
Veo
Veo is Google DeepMind's text-to-video generation model that creates high-definition video clips from text, image, or video prompts. It generates cinematic foo…
Kling AI
Kling AI is a text-to-video and image-to-video generation model developed by Kuaishou, a major Chinese technology company, known for producing relatively long,…
Midjourney
Midjourney is an AI image-generation service known for producing highly stylized, artistic images from text prompts, originally accessed primarily through Disc…
Hugging Face Spaces
Hugging Face Spaces is a hosting platform for sharing and running interactive machine learning demo applications directly in the browser, using frameworks like…
Ideogram
Ideogram is an AI image-generation tool notable for its strong ability to accurately render legible text within generated images, alongside general text-to-ima…
Flux (Black Forest Labs)
Flux is a family of open-weight and commercial text-to-image diffusion models developed by Black Forest Labs, founded by former Stable Diffusion researchers, k…
Krea AI
Krea AI is a real-time AI image and video generation platform that lets users see generated visuals update instantly as they sketch, type, or adjust prompts, a…
Luma AI
Luma AI is a company known for AI-powered video generation (Dream Machine) and 3D capture technology, letting users generate short video clips from text or ima…
Runway Gen-3
Runway Gen-3 is a generation of AI video-generation models from Runway, producing short video clips from text or image prompts with improved motion realism, co…
Vidu
Vidu is an AI text-to-video and image-to-video generation model developed by the Chinese AI company Shengshu Technology, generating short video clips from natu…
Stable Diffusion XL
Stable Diffusion XL (SDXL) is a text-to-image diffusion model released by Stability AI in 2023, a larger and higher-fidelity successor to the original Stable D…
FLUX.1
FLUX.1 is a family of text-to-image diffusion transformer models released in 2024 by Black Forest Labs — a company founded by former Stability AI researchers w…
Parti
Parti (Pathways Autoregressive Text-to-Image model) is a text-to-image generation model from Google Research, introduced in 2022, that treats image generation…
CLIP
CLIP (Contrastive Language-Image Pretraining) is a neural network released by OpenAI in 2021 that learns to connect images and natural-language text by trainin…
GAN
A Generative Adversarial Network (GAN) is a machine learning framework, introduced by Ian Goodfellow and colleagues in 2014, in which two neural networks — a g…
Diffusion Model
A diffusion model is a class of generative machine learning model that creates new data — most commonly images — by learning to reverse a gradual noising proce…
Variational Autoencoder (VAE)
A Variational Autoencoder (VAE) is a generative neural network architecture, introduced by Diederik Kingma and Max Welling in 2013, that learns to compress dat…
Text-to-Speech Model
A text-to-speech (TTS) model converts written text into natural-sounding spoken audio, synthesizing voice output that can vary in tone, pace, accent, and emoti…
Diffusion Transformer (DiT)
A Diffusion Transformer (DiT) is a generative architecture that replaces the convolutional U-Net backbone traditionally used in diffusion models with a Transfo…
Synthetic Data
Synthetic data is artificially generated data — produced by algorithms, simulations, or generative models rather than collected from real-world events — that i…
Generative Adversarial Network
A Generative Adversarial Network (GAN) is a generative modeling framework in which two neural networks — a generator and a discriminator — are trained in compe…
Showing 24 of 35.