Explore your creativity with Doodle Guide, an AI audio and visual experiment.
Gaël Hugo, artist in residence at Google Arts & Culture Lab, was interested in helping anyone with their doodles using AI Audio. Sketch onto the canvas and receive feedback and tips for improvement. For inspiration a sketch style image based on your drawing is generated by Google AI to offer you visual cues for improvement. This first experimentation is focusing on the structure and style of your artwork, with more to come in the future.
How it works:
To understand your doodle we use Gemini - Google’s Multimodal Large Language Model - which allows for multiple input modalities including text & images, text & audio. Your doodle is analyzed by the model to understand what it is.
From the analysis of the doodle, Gemini generates a script about the drawing, how to improve it and a prompt to generate a sketch style image.
Image generation and Audio Output Once the image prompt is created, it is fed into an Image model to generate a sketch and the script sent to a Google AI Audio Model to generate the audio in real time.
This experiment uses AI generated content that may not represent Google's views.
Responses are generated by AI and may contain inaccurate or harmful content.
start to draw and receive feedback from the doodle master
you haven't drawn enough, keep going to get feedback
