PyTorch DataLoader Explained: Datasets, Batches, and Image Folders
PyTorch DataLoader explained: build a Dataset, batch and shuffle CIFAR-10, use transforms.v2, speed up with num_workers, and load your own image folder.
PyTorch DataLoader explained: build a Dataset, batch and shuffle CIFAR-10, use transforms.v2, speed up with num_workers, and load your own image folder.
PyTorch autograd explained: requires_grad, the computational graph, how backward() applies the chain rule, why zero_grad matters, and torch.no_grad.
Learn what a PyTorch tensor is: shape, dtype, device, indexing, view vs reshape, broadcasting, and how to turn images into N, C, H, W tensors and back.
Free PyTorch tutorial for 2026: install PyTorch 2.15, check your GPU, make your first tensor, and start building a tiny diffusion transformer from scratch.
Compare stable diffusion models SD 1.5, SDXL, SD 3.5 and FLUX.1: architecture, text encoders, latent channels, parameters, licenses, and which to use.
How does Stable Diffusion paint an AI artwork? Understanding the tech behind the rise of AI-generated art. Originally posted on My Medium. Most of the recent AI art found on the internet is generated using the Stable Diffusion model. Since it is an open-source tool, any person can easily create fantastic art illustrations from just […]
How does AI artwork work? Understanding the tech behind the rise of AI-generated art. Originally posted on My Medium. The rise of the Diffusion Model can be regarded as the main factor for the recent breakthrough in the AI generative artworks field. In this article, I’m going to explain how it works with illustrative diagrams. […]
Originally posted on My Medium. While everyone is using Stable Diffusion to generate artwork, have you ever realized there is a watermark in the generated images? If you are new to it, first read how Stable Diffusion works. Invisible Watermark The official Stable Diffusion code uses a Python library called invisible-watermark to embed an invisible […]
Paper Explained: Diagonal Attention and Style-based GAN for Content-Style Disentanglement in Image Generation and Translation Originally posted on My Medium. Introduction In image generation, Content-Style Disentanglement has been an important task. It aims to separate the content and style of the generated image from the latent space that is learned by a GAN. This DiagonalGAN […]
Paper Explained: JoJoGAN — One-Shot Face Stylization Originally posted on My Medium. Introduction JoJoGAN is a style transfer procedure that lets you transfer the style of a face image to another style. It accepts only one style reference image and quickly produces a style mapper that accepts an input and applies the style to the […]