The Gemini app has introduced a new image editing model from Google DeepMind, focusing on maintaining a consistent likeness when editing photos of people and pets. This update allows users to freely change outfits, blend photos, and apply styles from one image to another.
Key Features:
- Maintain Consistent Appearance: Gemini ensures that the look of individuals or pets remains consistent across different images, avoiding situations where the depiction is 'close but not quite the same.' Whether trying a 60's hairstyle or dressing your dog in a tutu, Gemini can handle it.
- Photo Blending: Users can upload multiple photos and blend them to create entirely new scenes. For instance, you can combine your photo with your pet's to create a perfect portrait together.
- Multi-Turn Editing: Users can keep editing the images generated by Gemini. Start with an empty room, paint the walls, and then add a bookshelf or furniture, with Gemini preserving other aspects of the image.
- Design Mixing: You can apply the style of one image to an object in another. For example, take the color and texture of flower petals and apply it to rain boots, or design a dress using a butterfly's wing pattern.
All images created or edited in the Gemini app include a visible watermark and an invisible SynthID digital watermark to clearly indicate they are AI-generated.
Conclusion
The upgraded image editing feature in Gemini not only enhances user creativity but also provides more control while maintaining realism.
Blogger's Review: This upgrade marks another leap in AI image editing technology, especially in maintaining character consistency, significantly enhancing user experience. With the continuous advancement of generative AI technology, future image processing will become even more personalized and intelligent. Looking forward to more innovations!