Google unveils Whisk generative AI

Listen to article

Google は、生成型人工知能(AI)のための新しいプログラムを発表しました。

Whick は、画像プロンプトを使用する生成型 AI プログラムです。ユーザーは、プログラムに画像をドラッグするだけで、詳細なテキストプロンプトを入力せずに作成を開始できます。

The generative AI uses deep-learning models to create content based on existing data. Whisk allows anyone to customize how the image will come out. It allows specific image inputs for the main subject, the scene, and preferred art styles.

Behind the scenes, the Gemini model automatically writes a detailed caption of chosen images. It then feeds those descriptions into Google’s latest image generation model, Imagen 3. This process captures the subject’s essence, and doesn’t create an exact replica. They can then also remix their subjects, scenes, and styles to create something that is uniquely theirs.

Interested users can try out Google's Whisk right here.

React to this article:
Written by
Cristina Joy Valerio

Cristina Joy Valerio

Senior Writer

Cristina Joy D. Valerio, more commonly known as CJ to most, is a Multimedia Producer at Yugatech. She has an interest in the evolving world that is technology. Apart from that, she organizes D&D sessions, plays video games, and watches anime to kill time. CJ's alma mater is iACADEMY and graduated with a Bachelor of Science in Information Technology specializing in Web Development.

View all posts by Cristina Joy Valerio →

0 Comments

Leave a Reply

Loading next article...