Can Google’s Gemini AI generate free Ghibli-style images like Grok 3 and ChatGPT?

Google has astonished its AI world by releasing its new Gemini 2.5 Pro model available to all non-paying customers. Initially, it was planned as a premium feature only for Gemini Advanced subscribers, the decision of the company to make it open to all users is a reaction to the growing competition, especially from openAI's ChatGPT along with Anthropic's Claude.

But, Google's latest model of Gemini AI is not designed to support natively-created images, posing the question of whether it is able to satisfy the demand for Ghibli-style images.

Gemini 2.5 Pro Vs. its alternatives

In essence, Gemini 2.5 Pro is a reasoning model that is similar to OpenAI's GPT-4o mini and DeepSeek R1. Google claims to have significant improvement in math sciences, reasoning and coding. It also claims to have excellent performance in the most important AI benchmarks like Humanity's Final Exam and LMArena developed by UC Berkeley researchers.

But while OpenAI's GPT-4o has drawn attention for its seamless multimodal capabilities--including native image generation--Google has been vague about whether Gemini 2.5 Pro can create images on its own.

The official statement of the Grok 3 company is that the model is equipped with the ability of processing and interpreting images, text, sounds video, as well as codebases. There is no specific information regarding the in-built generation of images which leads the user to believe that it could depend in external AI tools to accomplish similar.

So, why is there no "Ghiblify" feature within Gemini 2.5 Pro?

Despite the growing awe-inspiring Studio Ghibli-inspired AI painting users were shocked to learn Gemini 2.5 Pro's lack of inline style conversions. Gemini 2.5 Pro lacks inline style conversions currently.

This indicates it is possible that the Imagen 3 model, which is the basis for Gemini's image generation does not have the same seamless flexibility in artistic expression that is available by OpenAI's ChatGPT. GPT-4o for instance is able to create art in the style of Ghibli without the need for third-party models, which makes it a popular option for creativity powered by AI.