Want smart insight into your inbox? Enterprise AI, only what matters to data and security leaders, sign up for our weekly newspapers. Subscribe now
Google Mithun 2.5 released flash image, a new model known as many beta users Nanobanana, giving enterprises more options for creative projects. This enables them to change the form of images that they need quickly and with more control than the previous model.
The model will be integrated into the Gemini app.
The model built on top of the Gemini 2.5 flash, combines more abilities in native image editing on the Gemini app. Gemini 2.5 flash image maintains characteral similarity between different images and is more stable when editing pictures. If a user uploads a picture of his pet and then asks the model to change the background or add a hat to his dog, Gemini 2.5 will do so without changing the theme of the 2.5 flash image picture.
Google said in a blog post written by Gemini Apps Multimodal Generation Lead David Sharon and Google Deepmind Gemini Image Product Nicole Bitchtova, “We know that when we or you know well, when you know well, when you know well, a portrayal that is not ‘close, but not right.” “This is why our latest updates are designed to make pictures of your friends, family and even your pets.”
AI scaling hits its boundaries
Power caps, rising token costs, and entrance delays are re -shaping Enterprise AI. Join our exclusive salons to learn about top teams:
- Transform energy into a strategic profit
- Architecting efficient estimates for real thrruput benefits
- Unlocking competitive ROI with sustainable AI system
Secure your location to stay ahead,
A complaint enterprises and some individual users have that when indicating editing on AI-borne images, light twicex change the photo too much. For example, a person may instruct the model to move a person’s position in the picture, and when the model does what he is told, the person’s face changes slightly.
All images generated on Gemini will include Google’s syntid watermark. The model is available to all payments and free users of the Mithun app.
Speculation that Google plans to release a new image model, which runs extensively on social media platforms. Users of LM Arena saw a mysterious new model called Nanobanana, with “Complex, Multistap Instructions with impressive accuracy”, Andresson Horovitz Partner Justin Moore put it in a post.
People soon noticed that Nanobanana model was coming from Google, before many initial examiners confirmed this. However, at that time, Google did not confirm what he planned to do with the model on LM Arena.
By this week, when the model will come out, there is speculation on it, which is a kind of prediction.
Most enthusiasts come as a fight between model providers to offer more enabled and realistic images and editing, showing how powerful multimodal models have become.
However, Google still needs to fight rivals Cowen And recently released Qwen-image edited and OpeniIn which indigenous AI image editing was added to the spat and the model was also made available as API.
Absolutely, AdobeLong -term image has been considered one of the leaders in the editing location, adding its major model fireplace to Photoshop and its other photo editing platforms.
Domestic image editing
Mithun added native AI image editing on Gemini in March, which she introduced to free users of the chat platform.
Bringing image editing features directly into the chat platform will allow enterprises to fix images or graphs without transferring Windows.
Users can upload a photo to Gemini, then tell the model what changes they want. Once they are satisfied, new photos can be re -loaded and made in a video.
In addition to adding a dress or a location change, the Gemini 2.5 flash image can mix individual photos, provide multi-turn editing and one photo styles can be found in the other.
