Business · TechCrunch AI
ChatGPT’s new Images 2.0 model is surprisingly good at generating text
Compiled by KHAO Editorial — aggregated from 1 outlet. See llms.txt for citation guidance.
◌ Single Source
It used to be easy enough to distinguish between human-made and AI-generated imagery — two years ago, you couldn’t use image models to create a menu for a Mexican restaurant without inventing new culinary delights like “enchuita,” “churiros,” “burrto,” and “margartas.”
Key facts
- The diffusion models […] are reconstructing a given input,” Asmelash Teka Hadgu, founder and CEO of Lesan AI, told TechCrunch in 2024
- For comparison, here’s the result the reporter got from DALL-E 3 two years ago (at the time, ChatGPT did not generate images)
- Unfortunately, OpenAI declined to answer a question in a press briefing this week about what kind of model is powering ChatGPT Images 2.0
- Images 2.0 brings an unprecedented level of specificity and fidelity to image creation
Summary
It used to be easy enough to distinguish between human-made and AI-generated imagery — two years ago, you couldn’t use image models to create a menu for a Mexican restaurant without inventing new culinary delights like “enchuita,” “churiros,” “burrto,” and “margartas.” Now, when the reporter ask the brand new ChatGPT Images 2.0 model for a menu of Mexican food, it creates something that could immediately be used in a restaurant without customers noticing that something’s off. (However, ceviche priced at $13.50 might make me question the quality of the fish.) For comparison, here’s the result the reporter got from DALL-E 3 two years ago (at the time, ChatGPT did not generate images):. AI image generators have historically struggled to spell because they generally used diffusion models, which work by reconstructing. “The diffusion models are reconstructing a given input,” Asmelash Teka Hadgu, founder and CEO of Lesan AI, told TechCrunch in 2024.