MemCast
MemCast / episode / insight
#3d-ai13#diffusion-models1#text-to-image1
Diffusion models turned ‘impossible’ text‑to‑image generation into reality, powering today’s generative AI boom
  • Early attempts at generating images from text were dismissed as impossible, as illustrated by Andrej Karpathy’s skeptical response.
  • The breakthrough came with diffusion models, which iteratively denoise random noise conditioned on a textual prompt.
  • These models now create high‑fidelity images and videos from natural language, enabling tools like OpenAI’s Sora.
  • Li credits this paradigm shift for the explosion of generative content across art, design, and entertainment.
  • The story demonstrates how a new algorithmic class can overturn long‑standing assumptions about AI capability.
Fei‑Fei LiTED00:04:02

Supporting quotes

Quote
00:04:02
“安德烈说：‘哈哈，不可能。’” — Fei‑Fei Li
quoting Andrej Karpathy
Quote
00:04:11
“这要归功于一系列扩散模型，它们驱动了如今的生成式 AI 算法，将人为输入的句子转换为闻所未闻事物的照片和视频。” — Fei‑Fei Li
Quote
00:04:28
“很多人已经看到了 OpenAI 的 Sora 最近展示出的惊人成果。” — Fei‑Fei Li

From this concept

From Labels to Worlds: The Rise of Generative and Spatial AI

Li explains how diffusion models turned text-to-image generation from "impossible" to commonplace, and how generative video models like Walt push the frontier further. She then moves to spatial AI, where algorithms convert 2-D photos into 3-D scenes, opening the door to immersive, interactive worlds.

View full episode →

Similar insights

“Marble ingests multimodal inputs and produces editable 3‑D worlds”

Fei-Fei LiLatent Space

“Product focus balances immediate utility with long‑term world‑model ambition”

Fei-Fei LiLatent Space

“Real‑time demos showcase feasibility despite latency, proving concept”

Fei-Fei LiLatent Space