OpenAI released ChatGPT Images 2.0 today, their latest image generation model. On the livestream Sam Altman said that the leap from gpt-image-1 to gpt-image-2 was equivalent to jumping from GPT-3 …
21st April 2026
OpenAI released ChatGPT Images 2.0 today, their latest image generation model. On the livestream Sam Altman said that the leap from gpt-image-1 to gpt-image-2 was equivalent to jumping from GPT-3 to GPT-5. Here’s how I put it to the test.
My prompt:
Do a where's Waldo style image but it's where is the raccoon holding a ham radio
gpt-image-1
Widow’s Bay Is a Menacing and Hilarious Mash-up
Build a robot artist for your Discord server with Stable Diffusion, Replicate, and Fly.io – Replicate blog
Replicate Intelligence #4 – Replicate blog
AI radio hosts demonstrate why AI can’t be trusted alone
OpenAI is adding reasoning and web search to its ChatGPT Images 2.0 image generator. The model can now create up to eight…
ChatGPT’s new Images 2.0 model is surprisingly good at generating text , Alibaba Drops Qwen 3.6 Max Preview , SpaceX is working…
At a time when much TV recycles familiar formulas, the Apple TV series feels like something new.
I put ChatGPT Images 2.0 and Gemini Nano Banana through nine image-generation tests. The winner was clear.
My ChatGPT Images 2.0 results were impressive, but occassionally wrong. Here's how it handles branding, text, and infographics.
GPT-5.5, GPT Image 2.0, Workspace Agents, DeepSeek V4, Kimi K2.6, Qwen 3.6 Max, Copilot Agent Mode, Deep Research Max, Claude…
