Inside image generation’s Renaissance moment — the OpenAI Podcast Ep. 19

OpenAI · Advanced ·🎨 Image & Video AI ·5d ago
People are generating over 1.5 billion images a week in ChatGPT. In this episode, Product lead Adele Li and researcher Kenji Hata share some of the new use cases and trends since the launch of Images 2.0. Together with host Andrew Mayne, they trace the progress from the early DALL-E days and dive into the latest capabilities, including better text rendering, photorealism, multilingual support, world knowledge, aspect ratios, and character consistency. They also explore what comes next as image generation models evolve into more capable creative assistants. Chapters 00:36 How Adele and Kenji came to work on Images 02:27 Images 2.0 launch reception 05:25 Productivity use cases and and 360 images 09:34: Viral trends, authenticity, and imperfection 10:51 Training breakthroughs and photorealism 14:06 Evals, prompting, and creative control 22:16 Creative agents and what comes next 22:27 Images + Codex 28:08 Prompt tips
Watch on YouTube ↗ (saves to browser)
Sign in to unlock AI tutor explanation · ⚡30

Related AI Lessons

⚡
I Thought AI Image Tools Were Broken… Until I Realized My Prompts Had No Structure
Learn how to improve AI-generated images by structuring your prompts, a crucial step for reliable results
Medium · ChatGPT
 ⚡
I built a Stable Diffusion playground in 200 lines and zero API keys. Here's how.
Build a Stable Diffusion playground in under 200 lines of code without needing API keys, and explore AI image generation
Dev.to · Devanshu Biswas
 ⚡
What makes an AI image workflow useful for real commercial output?
Learn how to create a useful AI image workflow for commercial output, focusing on repeatability, versatility, and clarity
Dev.to AI
 ⚡
How to Write Better AI Image Prompts for Midjourney (With Examples That Actually Work)
Learn to write effective AI image prompts for Midjourney with actionable examples and techniques
Medium · ChatGPT

Chapters (8)

0:36 How Adele and Kenji came to work on Images
2:27 Images 2.0 launch reception
5:25 Productivity use cases and and 360 images
10:51 Training breakthroughs and photorealism
14:06 Evals, prompting, and creative control
22:16 Creative agents and what comes next
22:27 Images + Codex
28:08 Prompt tips
Up next
Google says it's making it easier to figure out what images are made with AI.
The Verge
Watch →