domain generative seed

Generative Models

Models that learn to generate new data: images, text, audio, video. GANs, VAEs, diffusion models, and large language models.

#generative #generation #synthesis

Sub-topics

Generative Adversarial Networks (2014) concept

Goodfellow et al. (2014) introduced adversarial training: a generator creates samples while a discriminator judges authenticity. Produced breakthrough image synthesis results.

Variational Autoencoders (2013) concept

Kingma and Welling (2013) combined autoencoders with variational inference, creating a principled framework for learning latent representations and generating new samples.

Diffusion Models (2020) concept

Ho et al.'s DDPM (2020) generates data by learning to reverse a noise diffusion process. Achieved image quality surpassing GANs with more stable training.

Stable Diffusion (2022) concept

Stability AI's open-source latent diffusion model (2022). Performs diffusion in a compressed latent space, making high-quality image generation accessible on consumer GPUs.

DALL-E (2021) concept

OpenAI's text-to-image model (January 2021) using a transformer to generate images from text descriptions. DALL-E 2 (2022) and DALL-E 3 (2023) dramatically improved quality.

Large Language Models topic

Massive transformer-based models trained on internet-scale text corpora. Exhibit emergent abilities including reasoning, code generation, and instruction following.

Image Generation topic

The field of synthesizing images from noise, text, or other inputs. Evolved from GANs through VAEs to diffusion models, achieving photorealistic quality by 2022.

Text-to-Video Generation concept

Generating video from text descriptions. OpenAI's Sora (2024) and similar models extend diffusion to temporal consistency. One of the most challenging generative tasks.