You may not have heard about new AI image generation models as much lately, but that doesn’t mean that innovation in the field has stagnated: it’s quite the opposite. FLUX.1-dev immediately overshadowed the famous Stable Diffusion line of image generation models, while leading AI labs have released models such as Seedream, Ideogram, and Qwen-Image. Google also joined the action with Imagen 4. But all of those image models are vastly overshadowed by ChatGPT’s free image generation support in March 2025. After going organically viral on social media with the Make me into Studio Ghibli prompt, ChatGPT became the new benchmark for how most people perceive AI-generated images, for better or for worse. The model has its own image “style” for common use cases, which make it easy to identify that ChatGPT made it.
Two sample generations from ChatGPT. ChatGPT image generations often have a yellow hue in their images. Additionally, cartoons and text often have the same linework and typography.
Of note, gpt-image-1 , the technical name of the underlying image generation model, is an autoregressive model. While most image generation models are diffusion-based to reduce the amount of compute needed to train and generate from such models, gpt-image-1 works by generating tokens in the same way that ChatGPT generates the next token, then decoding them into an image. It’s extremely slow at about 30 seconds to generate each image at the highest quality (the default in ChatGPT), but it’s hard for most people to argue with free.
In August 2025, a new mysterious text-to-image model appeared on LMArena: a model code-named “nano-banana”. This model was eventually publically released by Google as Gemini 2.5 Flash Image, an image generation model that works natively with their Gemini 2.5 Flash model. Unlike Imagen 4, it is indeed autoregressive, generating 1,290 tokens per image. After Nano Banana’s popularity pushed the Gemini app to the top of the mobile App Stores, Google eventually made Nano Banana the colloquial name for the model as it’s definitely more catchy than “Gemini 2.5 Flash Image”.
The first screenshot on the iOS App Store for the Gemini app.
Personally, I care little about what leaderboards say which image generation AI looks the best. What I do care about is how well the AI adheres to the prompt I provide: if the model can’t follow the requirements I desire for the image—my requirements are often specific—then the model is a nonstarter for my use cases. At the least, if the model does have strong prompt adherence, any “looking bad” aspect can be fixed with prompt engineering and/or traditional image editing pipelines. After running Nano Banana though its paces with my comically complex prompts, I can confirm that thanks to Nano Banana’s robust text encoder, it has such extremely strong prompt adherence that Google has understated how well it works.
How to Generate Images from Nano Banana#
Like ChatGPT, Google offers methods to generate images for free from Nano Banana. The most popular method is through Gemini itself, either on the web or in an mobile app, by selecting the “Create Image 🍌” tool. Alternatively, Google also offers free generation in Google AI Studio when Nano Banana is selected on the right sidebar, which also allows for setting generation parameters such as image aspect ratio and is therefore my recommendation. In both cases, the generated images have a visible watermark on the bottom right corner of the image.
For developers who want to build apps that programmatically generate images from Nano Banana, Google offers the gemini-2.5-flash-image endpoint on the Gemini API. Each image generated costs roughly $0.04/image for a 1 megapixel image (e.g. 1024x1024 if a 1:1 square): on par with most modern popular diffusion models despite being autoregressive, and much cheaper than gpt-image-1 ’s $0.17/image.
Working with the Gemini API is a pain and requires annoying image encoding/decoding boilerplate, so I wrote and open-sourced a Python package: gemimg, a lightweight wrapper around Gemini API’s Nano Banana endpoint that lets you generate images with a simple prompt, in addition to handling cases such as image input along with text prompts.
... continue reading