Skip to content
All tags

#diffusion

2 posts
tech MIT 6.7960 導讀 (Fall 2024 OCW)

MIT 6.7960 L14: Generative Models Basics — Density/Energy Models, GANs, Autoregressive, Diffusion

Generative models learn the data distribution p(x). Density models model probability directly, energy models use an unnormalized potential + sampler, GANs let a discriminator force realistic samples, autoregressive predicts the next token step by step, and diffusion dodges tricky maximum-likelihood via 'add noise then learn to denoise'.

#mit-67960#deep-learning#generative-model#gan#diffusion#autoregressive#fall-2024
tech MIT 6.7960 導讀 (Fall 2024 OCW)

MIT 6.7960 L16: Conditional Generative Models — cGAN, cVAE, and Classifier-Free Guidance

The key to conditional generation is 'feed y into the model': cGAN concatenates y into G/D; cVAE passes y to both encoder and decoder; in diffusion, Classifier Guidance uses gradients from an external classifier to push samples toward a class, while Classifier-Free Guidance trains conditional + unconditional together and linearly combines them at inference — the latter is the standard weapon behind Stable Diffusion and Imagen.

#mit-67960#deep-learning#conditional-generative#cgan#cvae#classifier-free-guidance#diffusion#text-to-image#fall-2024