正在加载视频...

视频加载失败

Wow Gemini 2.0 Flash's new native image generation is REALLY good You can basically edit any image in natural language 🔥 Not only the ones you generate with Gemini 2.0 Flash but also existing ones. Accessible 100% for free in AI Studio (More below)

188,244 次观看 • 1 年前 •via X (Twitter)

10 条评论

Paul Couvert 的头像
Paul Couvert1 年前

Unlike many other image generation models, Gemini 2.0 Flash leverages world knowledge to create the right image. And you can ask it to generate multiple images (and text) in a single prompt!

Paul Couvert 的头像
Paul Couvert1 年前

To use these new capabilities: → Access Google AI Studio (free): → In the menu on the right, select the "Gemini 2.0 Flash Experimental" model. → Make sure "Images and text" is selected And you're all set!

NOVOS Labs 的头像
NOVOS Labs1 年前

How young do you look? Try our free NOVOS FaceAge AI Tool for an accurate facial age assessment, correlated to your biological age. Trained on millions of images + validated by experts + free tips to improve your score. Understand your skin's health:

Julian Harris 的头像
Julian Harris1 年前

AIs don’t like full glasses of wine it seems

George Siosi Samuels 的头像
George Siosi Samuels1 年前

my god, it works! thanks Paul! so many use cases for this in my own workflows

Mark Gadala-Maria 的头像
Mark Gadala-Maria1 年前

I've been wanting this type of functionality for a while, good stuff

Paul Couvert 的头像
Paul Couvert1 年前

Same! We had seen something similar with GPT-4o but they never released it. Google and DeepMind did!

スラバ 的头像
スラバ1 年前

World is already building AI agents but Google still use this terrible material design in their apps. There is no agent called a UI designer yet?

Paul Couvert 的头像
Paul Couvert1 年前

I like this UI. Material UI is really good imo.

nox player74 的头像
nox player741 年前

I turned ALL safety settings to OFF but still can't edit the image: “Probability of unsafe content Content not permitted” With these filters it's useless. Besides, the resulting file only has a resolution of 1024 and a watermark.

相关视频