Key Points of This Article
- Google announces “Nano Banana Pro (Gemini 3 Pro Image),” its state-of-the-art image generation AI model based on “Gemini 3 Pro,” as an evolution of “Nano Banana,” and is rolling it out in the Google AI “Gemini” app and other services.
- The model features improvements in three areas: enhanced text rendering, advanced image editing, and superior image composition capabilities.
- It is also integrated into Google Workspace services like “Google Slides” and “NotebookLM,” enhancing the image generation and editing capabilities within each of these services.
On Thursday, November 20, 2025, Google announced “Nano Banana Pro (Gemini 3 Pro Image),” a state-of-the-art image generation AI model based on Gemini 3 Pro, as an evolution of its previous “Nano Banana” model. It has begun rolling out in the Google AI “Gemini” app and other services.
“Nano Banana Pro” is a state-of-the-art image generation AI model that improves upon “Nano Banana” in three key areas: enhanced text rendering, advanced image editing, and superior image composition. The enhanced text rendering capabilities improve the generation of images containing text, such as posters and diagrams, enabling it to accurately and clearly reproduce text in multiple languages.
The image editing features have been enhanced to more faithfully execute prompt-based instructions for adjustments like camera angles, bokeh effects, lighting, and color grading. The image composition capabilities have been upgraded to allow for the merging of up to 14 images.
The state-of-the-art image generation AI model, “Nano Banana Pro,” is being integrated not only into the “Gemini” app but also into Google Workspace services such as “Google Slides” and “NotebookLM,” enhancing the image generation and editing features within each of these services.
Source: Google
コメントを残す