ChatGPT 4o Applies Any Style to Photos

ChatGPT 4o image recreation ca take a photo and apply all kinds of styles.

Styles:
Studio Ghibli
Wallace and Gromit
Rick and Morty
Attack on Titan

Improved capabilities

OpenAI trained the 4o native image models on the joint distribution of online images and text, learning not just how images relate to language, but how they relate to each other. Combined with aggressive post-training, the resulting model has surprising visual fluency, capable of generating images that are useful, consistent, and context-aware.

Text rendering

A picture is worth a thousand words, but sometimes generating a few words in the right place can elevate the meaning of an image. 4o’s ability to blend precise symbols with imagery turns image generation into a tool for visual communication.

Instruction following

GPT‑4o’s image generation follows detailed prompts with attention to detail. While other systems struggle with ~5-8 objects, GPT‑4o can handle up to 10-20 different objects. The tighter binding of objects to their traits and relations allows for better control.

2 thoughts on “ChatGPT 4o Applies Any Style to Photos”

  1. OpenAI basically ate Midjourney’s and all other image generators lunch overnight. Images in Midjourney are fine looking, but it is sadly context unaware and misses many nuances on the prompts.

    The only market remaining are corner cases, like adult themed image generation.

    MJ would have to really up their ante to take the crown from OAI now. Something which probably would only come from other competitors, like Grok.

Comments are closed.