When Van Gogh painted the stars with a trembling hand, the artist who wouldn't have foreseen the future simply said to the AI, "Let the cypress burn in the quantum vortex."
The latest release from Google ResearchGemini 2.0 Multi-Modal Model, is reshaping the workflow of image editing, talking the talk and one-click Pics!
At this moment, Asaaki would like to say: this is not the year when I learned Photoshop imagine that human beings can have "superpowers" well ~ I did not expect to really realize this day!
First, let's feel the effect
Case 1: Portrait Editing
For example, I want the model whose eyes are closed to open them:
I wanted to refine the model a bit and put on a beret:
Case 2: Landscape Editor
I would like to P out the car from the picture:
Draw Tesla again:
PS. Of course, we will find that the current out of the picture effect with MJ these still can not be compared, but with the evolution of the model, Asaki believes that these are not a problem ~ ~
Second, the use of tutorials
Web site: https://aistudio.google.com/ (note that magic is required~)
Select the model on the right to Gemini 2.0 Flash Experimental . It's currently free (10 requests per minute, 1500 free requests per day), which is still very generous!
Output format, be sure to check the version that is supported by both image and text
Then you can start playing with it.
For more fun cases, you can dig it up yourself~
final words
Gemini 2.0 reveals not only the evolutionary map of image editing, but also the fission of the human cognitive paradigm - those imaginations that were once locked up by toolbars are being reconstructed into a new Tower of Babel in the resonance of language and algorithms.
In this recalibrated creative coordinate system, each of us is a descendant of Delacroix and Turing - our sentences are beginning to take on quality, adjectives are gaining color temperature, and every unspoken thought is waiting for the pixel nirvana to which it belongs.
The future is here, look forward to every day~