Training GPT-2 to win Connect Four game
I wanted to learn training GPT-2 as it is a powerful model. For simplicity, I chose Connect Four. This project serves as a basic example, with future plans for more complex applications. I published the code in my Github repo…
Trying to generate 3D variations of 2D reference and control features of output & test of SV3D
In this article, I explore the capability to generate 3D assets based on 2D reference images. The control over the final results is crucial, particularly when the need arises for exact assets, such as a building with a particular architecture…
Fast comparison of Stable Zero123 and TripoSR
In the previous posts, I explored the results of Stable Zero 123, a tool that can generate 3D models from a single image. Recently, Tripo AI and Stability AI released TripoSR, an open-source model that claims to achieve state-of-the-art performance…
HuggingFace space with Stable-Zero123
I created a simple Hugging Space space with demo of Stable-Zero123
How to Troubleshoot and Solve Crashes in 3D Object Generation with Stable123
While generating assets, I encountered some crashes and failures. In this post, I will share how I debugged and solved some of these issues. First, I wrote a Python script that generated .png files with views of the object, so…
Checking results of text -> Concept art -> 3D assets pipeline with SDXL and Stable zero123
Preparation Creating a complete scene from scratch should be a nice way to check the limitations of this technology. I’m starting with the generation of concept art for some assets with SDXL, with prompts such as: I selected a few…
Generating mesh & texture from results of stable-zero123
In the previous post, I explored how to improve the results of generating 3D objects with zero-1-to-3, a technique that allows us to control the shape and appearance of the objects. For almost any real-life usage of the result of…
Improving results of stable-zero123
In this post, I’m going to iterate on the promising results from my previous post. Let’s start with understanding the method better. How does it work? In short, the method is based on optimizing a neural field (NeRF) with randomly…
3D content creation from image
Introduction In this post, I will continue my previous exploration of 3D content generation methods available in threestudio, a powerful and versatile framework for 3D content creation. This time I’m exploring 3D object generation from a single image. For consistency,…
3D content creation from text prompts
Introduction Text-to-3D generation is an exciting and challenging task that aims to synthesize realistic and diverse 3D objects from natural language descriptions. Recently, there have been many advances in this field, thanks to the development of powerful text-to-image models, neural…
Stable Diffusion Texture Generator For Blender
Water surface simulation with Tensorflow and UE4
TensorFlow model used to generate a water surface around a moving obstacle in an Unreal Engine 4. Part of thesis PL Part of thesis EN Thesis PL Repository:
Kuwahara filter & anisotropic Kuwahara filter implementation
ShaderToy implementations of Kuwahara filters Kuwahara filter anisotropic Kuwahara filter Based on Acerola code
Generation of simplified representations of the city, characters and vehicles for Cyberpunk 2077
3D objects recognition by DNN and CNN
Simple Deep neural networks and Convolutional Neural Networks used to recognize deformed 3D objects generated with Houdini. Sources Details Few different representations of objects ware gathered to determinate which will work the best: Visualisation of filters To understand networks a…
Window blinds creator (PyMel)
PyMel script, that creates simple, randomized blinds for windows.
Paper plane flight simulation by RNN
In Browser demo Simple physics simulation: Recurrent Neural Network predicts a flight of a plane and takes a blowing wind int an account. There are 3 versions of the network that predict: a position of a plane (1 point) a…
CanvasStoryStudio.pl
Technology behind Canvas Story Studio
Flowers images generated by VAE and GAN
Sources Details In-Browser demo Flowers images generated by VAE (variational autoencoder) and GAN (generative adversarial network)
Python API in 3D computer graphics software: examplary scripts
Python API in 3D computer graphics software: examplary scripts Code on GitHub Example of Python scripts for Autodesk 3D Studio Max, Autodesk Maya and Blender. Those scripts use Python API to create simmilar scene in: Autodesk 3D Studio Max, Autodesk…
Image recognition by DNN and CNN
Simple Deep neural networks and Convolutional Neural Networks used to recognise 2D images of deformed objects generated with Houdini. Sources Details
Konstal 105 NA
Step-by-step disassembly of BMO (2016)
It’s a step-by-step disassembly of BMO – Adventure time character. It’s based on „Be more” (episode 28, season 5).Created in Modo, post production in NukeX. I’ve also created two still images. It was just a small fast project made in…
Daily work (2016)
Sennheiser MM 550-X Travel headphones
Created in modo and modo internal renderer:
A project of 3D printer
Robotic arm – made just for fun
Guitar
Rolex Daytona
Surprised alien (2016)
Fast work, created in Modo.
Step-by-step disassembly of BMO
It’s a step-by-step disassembly of BMO – Adventure time character. It’s based on „Be more” (episode 28, season 5). Created in Modo, post production in NukeX. I’ve also created two still images. It was just a small fast project made…