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

Google has surprised the AI world by making its latest Gemini 2.5 Pro model available to non-paying users. Initially planned as an exclusive feature for Gemini Advanced subscribers, the company’s decision to open access suggests a response to mounting competition, particularly from OpenAI’s ChatGPT and Anthropic’s Claude. The Gemini AI launch comes when Ghibli-style images are trending on social media, largely because of ChatGPT’s built-in image creation feature.

However, Google’s new model of Gemini is not designed for natively created images, raising a question of whether it can meet the demand for Ghibli-styles.

Advertisement

Gemini 2.5 Pro vs. its alternatives

At its core, Gemini 2.5 Pro is a reasoning model, similar to OpenAI’s GPT-4o Mini and DeepSeek R1. Google claims significant improvements in areas like math, science, reasoning, and coding, with high performance in key AI benchmarks such as Humanity’s Last Exam and LMArena by UC Berkeley researchers.

Now that #Eid is here, social media is full of a heartening trend—content creators are creating #StudioGhibli -inspired artworks to celebrate the festival.https://t.co/xymi21sNbl#ghiblistyle #Ghibli #AI #TheStatesman

— The Statesman (@TheStatesmanLtd) March 31, 2025

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 formal company statement is that the model has the capability of processing and understanding text, sound, pictures, video, and codebases. There is no direct word given on in-built image generation, leading the user to suspect that it might rely on external AI tools for the same.

So, no ‘Ghiblify’ feature in Gemini 2.5 Pro?

Despite rising giddiness over Studio Ghibli-flavored AI painting, users were surprised to see that Gemini 2.5 Pro lacks inline style conversions at present.

People who tried using something as basic as a “Ghiblify this” command saw an error returned:
“I’m sorry, I cannot do that. The function required to apply the ‘Ghibli’ style to your image is not available right now.”

This suggests that Google’s Imagen 3 model, which powers Gemini’s image generation, lacks the seamless artistic flexibility seen in OpenAI’s ChatGPT. GPT-4o, for instance, can produce Ghibli-style art without relying on third-party models, making it a preferred choice for AI-powered creativity.

Google’s decision to open Gemini 2.5 Pro to free users likely stems from the need to retain its AI user base. OpenAI’s ChatGPT continues to dominate public perception, especially with its free-tier multimodal capabilities.

By making Gemini 2.5 Pro available to non-subscribers, Google may be hoping to increase adoption and showcase its reasoning advancements—even if it still trails behind in creative AI features.

Also Read: Eid in Ghibli style? You need to see this stunning art trend!