This is exactly what happened—X canceled the mixed text and image editing feature in post editing, forcing me to write articles with illustrations using the "articles" format instead. Every article needs an illustration, which is both impressive and creates great atmosphere vibes.
So I fed the same prompt to 4 AI image models to generate pictures for me: 1 Grok, 2 ChatGPT, 3 Doubao, 4 Ideogram;
Here are the results (images 1-4). It's very obvious that in terms of understanding, color matching, rendering, and visual communication, "Ideogram" stands out from the crowd and is uniquely exceptional
查看原文