Finally, an insanely good pixel art AI

As a 2D game creator, I have been searching for an text-to-pixel art generator AI for a long time. It looks like we have finally arrived! Check out the results I got for the prompt

“a sprite sheet of several pixel art doors”!


Wow! Those are INSANELY good compared to previous pixel art generative AI’s!

So by now you must be dying to know which tool I used to generate those and how much it costs! Well I have good news for chatGPT users! I used Dalle-3, which you can now use for free with a chatGPT subscription! That’s right, since I already subscribe to chatGPT, I generated those awesome images for free!
This is getting really exciting for indie game developers everywhere!

Anyone can try NeRF now with a free app!

The 3D industry has been buzzing about Nvidia’s Instant NeRF (which stands for neural radiance fields) ever since they published their first demo video.

This technology has since been in rapid development and we now have a free iPhone app called Luma AI that anyone can use to capture NeRFs.

I tested the app with a toy robot, here’s a automatically generated video of the result:

The amazing thing about NeRF renders is that they can handle light reflections and bounces in a very realistic manner. This makes it a good fit for VFX work. We can also export a textured 3D-model from the Luma AI app, but it’s not as impressive as rendering with NeRFs. It’s still quite good compared to a basic photogrammetry process, especially considering that the surface of our object was quite reflective. Here’s a screenshot from Blender:

Here is how the mesh looks like (very dense):

Here’s another cool shot from a Robotime Ball Parkour toy:

@oneminutevideotutorial

Wow! NeRFs are going to be great for displaying products like this!

♬ original sound – user635578337916 –

How to fix the “Could not read source map for file” error when trying to setup Tensorflow.js

If you are getting a “Could not read source map for file” error in the console when trying to link to a JavaScript library like Tensorflow, the solution is simple. You propably don’t need the source map anyways unless you are planning to really digging into the code base of the library. So simply:

  1. Open the script file in your code editor
  2. Scroll all the way down
  3. Remove the source map link at the bottom of the file