September 7 news, following ChatGPT set off the "Ghibli, pixel style" AI graphic craze, recently appeared overseas to use the Gemini 2.5 Flash Image (codename Nano Banana) AI model "photo model handmade" play.
1AI notes that currentlyGoogle Gemini has officially launched the corresponding model, users can see the "🍌 Generate Images with Imagen" button with a banana Emoji on the homepage, and click on the button to generate images by prompting the words, without having to specifically visit Google AI Studio to generate images.
Taking "Photo Nendoroid" as an example, users can enter the following prompts and upload photos for AI image generation:
- Please turn this photo into a figure. Behind it, there should be a paper box which has partially transparent plastic window, with the character from this photo printed on the box. In front of the box, on a round plastic base, place the figure version of the photo I gave you. I'd like the PVC material to be clearly represented. It would be even better if the background is indoors.
1AI learned that Gemini 2.5 Flash Image was released on August 26th of this year, and is currently Google's most advanced image generation and editing model, which is available to enterprise users through Vertex AI. Gemini 2.5 Flash Image is priced at $30.00 per 1 million output tokens. A single image is 1290 output tokens (i.e., about $0.039 per image, note: current exchange rate is about $0.28). All other input and output modal pricing follows Gemini 2.5 Flash pricing.