Pawel
Shaders define visual effects by transforming inputs into rendered outputs. But what if we could reverse that process—recover shader inputs directly from the final image? Or adjust parameters so that the output matches a given reference? With SlangPY and PyTorch, we can. With SlangPY and PyTorch, shader inputs become trainable parameters. Gradient descent lets you [ ] The post Reconstructing…
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 Game Overview Connect Four is a simple strategy game where two players drop colored discs [ ] The post Training GPT-2 to win Connect Four game first appeared on Pawel .
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 or unique adornments. For this experiment, I went with architecture. The versatility of buildings allows [ ] The post Trying to generate 3D variations of 2D…
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 in fast feedforward 3D reconstruction. How does TripoSR compare to Stable Zero 123? That s what [ ] The post Fast comparison of Stable Zero123 and…
I created a simple Hugging Space space with demo of Stable-Zero123 https://huggingface.co/spaces/p4vv37/Stable-zero123 The post HuggingFace space with Stable-Zero123 first appeared on Pawel .
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 I could analyze each one of them. Here is the code snippet: To illustrate how [ ] The post How to Troubleshoot and Solve Crashes in 3D Object Generation with Stable123 first…
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 examples that looked good and presented some potential problems, that I wanted to test, like: [ ] The post Checking results of text -> Concept art -> 3D assets pipeline…
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 generation, we need to convert it to a mesh with texture, as that s the most [ ] The post Generating mesh & texture from results of stable-zero123 first appeared on Pawel…
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 sampled viewpoints generated by Stable Zero123 network. This NeRF can be later converted to a [ ] The post Improving results of stable-zero123 first appeared on Pawel .
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, I will use an image of this armchair, that looks similar to some results of [ ] The post 3D content creation from image first…