Vibe coded this customizable video game entirely with AI.

You can add custom nano banana tiles and 3D models from Tripo.

It's open sourced (repo at the end) and here's how it works 👇 I’m going to walk you through how it works step by step, how I built it over time, and access to the full code at the end.

But first, you need @tripoai to create usable 3D models, you can do it here. I’ll explain how everything works in a second:

https://x.com/techhalla/status/2002430945866187113

this prompt for Nano Banana will save you a ton of time.

with just 3 variables, it helps you create HD cinematic stills!

examples made in freepik, master prompt below 👇 Nano Banana 2 was released just a few days ago, and the @freepik team has already integrated it into their suite. Not only is it much faster, but it also delivers incredibly high resolution results.

Save these variables to try them out later!

You can lock consistency with just Nano Banana 2 and Kling.

no more random 15s clips.

Full freepik Space breakdown below 👇 I’ve been obsessed with @freepik Spaces lately and this workflow is the perfect example of why.

If you're organized and know some basic prompting, you’re set!

Let’s dive into the details.

This started as a flat 2D floor plan.

and I'm sharing the exact AI method I used to turn it into a 3D tour inside freepik Spaces 🧵 The key in this @freepik Space is keeping the spatial consistency tight using the reference floor plan.

From there, we create different nodes to generate each room cohesively and then assemble the final video.

Let’s get started 👇

Lots of people are selling my prompts and my workflows… I don’t give a fuck.

I’m still sharing everything I know about generative AI for free.

9 essential resources from the last 2 weeks 👇

1. Full workflow to create 3rd-person POV continuous videos

https://x.com/techhalla/status/2022297580747600075

2. Another complete workflow with more than 17 prompts to recreate documentaries

https://x.com/techhalla/status/2021927831169880450

I’ve built a workflow with over 17 prompts for 6 different AI generation models that can recreate documentaries like this.

All on the same platform.

How I did it, including access to the freepik Space, below 🧵 People always ask how I create so much content so fast. It’s all about optimizing my workflow and focusing on the creative part.

That’s where @freepik Spaces helps. Everything in one place, with state of the art models for images and video.

Let’s take a look! 👇

A real example of using AI to generate 3D animations with full control and consistency.

If you want to learn how, I break it all down in this Tripo thread 👇 This workflow has been the base for many pro animation projects I’ve worked on. The key is using AI to speed things up and get amazing results.

We’ll do the 3D modeling with @tripoai, starting from images like these (prompt’s in the screenshot).

I'm sure you've seen tons of AI generated fight videos like this...

and I'm gonna show you how to make them in under an hour using freepik (prompts included) 🧵 Kling 3.0 and Nano Banana Pro are the hottest combo right now, and I’ve put together this workflow to do everything straight from @freepik in record time.

Let’s get to it... We’ll start with the base character. All you need is a photo and the prompt from the screenshot

I asked Kling 3.0 to create a short film from just a single image... and the result blew my mind!

here's how I made this video using Multi-Shot 👇 We’ve already seen tons of videos generated with @Kling_ai 3.0, and they’re seriously impressive, but for me, the best feature is its ability to generate multiple camera angles in a single clip.

This makes it super easy to keep visual consistency throughout an entire project.

new to generative AI?

22 can't-miss resources from the past 2 weeks (with tons of prompts) 👇

1. Compilation of cinematic-style prompts

https://x.com/techhalla/status/2013371049908297833

2. Run LTX-2 video model locally

https://x.com/techhalla/status/2012233272529392025

Less than 24 hours since Google dropped Project Genie and people are already creating wild stuff! The era of vibe gaming starts.

15 insane examples 🧵👇

1. Discarded Pack of Cigarettes in the station
2. Bodycam

https://x.com/i/status/2017024081154232678

This is some of the craziest stuff you can make with AI right now.

All powered by the new LTX Audio to Video.

Everything you need to know is down below 👇 Just giving you a heads-up: @LTXStudio Audio to video is hands down the wildest and most fun model out there right now.

It lets you control every part of a clip using a prompt, image, and audio.

Let’s check out how to get the most out of it.

If you're new to generative AI and want to learn, I've got you covered.

24 must-have resources to level up your skills (with over 70 prompts in total) 👇 1. Transform your videos into epic scenes with Motion Control

https://x.com/techhalla/status/2010725368823771529

You only need 5 prompts to create videos like this.

AI tutorial powered by Leonardo 👇 For this workflow, we’ll only use 2 models: NB Pro for the images and Kling O1 for the animations, both available on @LeonardoAi.

The best part? I’ve created 5 reusable prompts to generate the transitions you just saw, let me show you!

this is the best prompt of 2025

but it's so long I have to make a thread to share it 👇

(powered by Higgsfield AI, includes more examples)


Like I was saying, I tried this prompt on @higgsfield_ai using Nano Banana Pro, and all you need to do is upload the character images separately and use the prompt. Here's the prompt, broken down for you.

(part I)

DIRECTIVE: Generate a "Double Exposure" ...

15 realistic photo prompts to help you learn how to simulate a telephoto lens look.

Made with nano banana pro, powered by Leonardo AI (bookmark this for later) 👇

1. Human Scale vs. Mountain (Landscape Compression)
2. Urban Isolation in Tokyo (Long-Distance Street Photography)

Just 4 steps and 4 prompts to get the perfect shot with Nano Banana Pro.

Use this method to streamline your workflow and get cinematic results in minutes with Higgsfield AI.

All the info, below 👇


A lot of people are using grid prompting and honestly, I’m not surprised, the results are insane.

But with this workflow, you can take it to the next level on @higgsfield_ai!

Let’s break down each step, including the prompts you’ll need.

last 2 weeks in gen AI have completely changed the game.

15 free resources to help you learn how to use all the new models that just dropped! 👇

1. Cinematic grids with Nano Banana Pro (the prompt EVERYONE is using now)

https://x.com/techhalla/status/1994541592729063699

2. Combine NB Pro and Kling O1 to get full character consistency

https://x.com/techhalla/status/1995622791824245204

I asked Nano Banana Pro for a makeover, and here’s what happened...

lemme show you how I made this video in just 37 minutes using LTX Studio 👇 First, go to @LTXStudio and create a 3x3 grid using a reference image. I used my face and the prompt you see in the screenshot.

How would yours turn out?

Let’s keep going.

This is the best combo for total consistency with AI.

Kling O1 + Nano Banana Pro

Here’s everything you need to know to get it on Higgsfield 👇 Just a few hours after its release and @higgsfield_ai has already integrated Kling O1 into its suite, the omnireference model that lets you achieve video consistency like never before.

Let’s get started 👇

these 2 prompts for Nano Banana Pro will save you a ton of time.

just upload an image, generate the cinematic grid, and pull the frames you like!

examples made in Higgsfield AI, and prompts below 👇


First, you need to pick the images you want to pull extra cinematic frames from.

You’ll see it works with both real photos and AI-generated ones, like the one below.

We’re starting in @higgsfield_ai and selecting NB Pro as the model. Let’s keep going!