Google’s DeepMind has revealed “Genie”.
Using Genie is just like you use ChatGPT.
You have to give a text prompt describing what you want.
AI has taken the world by storm, every other day I come here to share a new update coming from the AI industry. We now have models that generate text from chat, we are also seeing the emergence of video models where you can generate full-blown videos by text prompts. But this new AI platform has caught my eye. It can help you generate video games by giving text prompts. Yes, you heard that right! I am talking about Google Genie. Let’s see what this is and what it can do.
Google’s DeepMind has revealed “Genie”. With the help of Genie, you can create interactive 2D video games from a single image prompt or text description. Imagine just like you use ChatGPT, you can use this to create your own video game. This does sound like the future of gaming, development, and even video games.
Also read: Android users, Google Gemini AI magic will soon be at your fingertips
Genies has been developed by Google DeepMind’s Open-Endedness Team. Google even shared that Genie is a “world model” that has been trained on a massive dataset of 200,000 hours of unlabelled video footage primarily taken from 2D platformer games.
How to use Google Genie?
Like I said earlier, using Genie is pretty simple. Just like you use ChatGPT, you have to give a text prompt describing what you want. And if you’re too lazy to do that just give it an image and it will create a video game for you.
How does the Google Genie work?
It is very easy to use Genie but at the same time, you have to be really careful about how things go. Three key components go behind creating a video game.
Video Tokenizer
This efficiently breaks down larger video data into smaller units called tokens. These are the foundation on which Genie creates more complex things.
Also read: Google renames Bard to Gemini, launches paid version of AI chatbot: Know more
Latent Action Model
The second step involves analysing transitions between consecutive frames in the videos. Actions are then identified which range from jumping and running to interacting with objects within the game.
Dynamics Model
This helps Genie predict the next frame in the video sequence and then generates subsequent video results. This continuously happens till a conclusion is reached.
Well, this AI is still in its development phase, let’s see how it turns out when it is fully ready.
Follow Us
Mustafa Khan
Mustafa is new on the block and is a tech geek who is currently working with Digit as a News Writer. He tests the new gadgets that come on board and writes for the news desk. He has found his way with words and you can count on him when in need of tech advice. No judgement. He is based out of Delhi, he’s your person for good photos, good food recommendations, and to know about anything GenZ. View Full Profile
