Tag: Stable Diffusion


  • Introduction I decided to run an in-depth test analizing SDXL checkpoints for realism. I used the best photo-realistic models for AI image generation in SDXL. My list of checkpoints is not huge, I tested many checkpoints and I discarted many of them. At the end I will test 30 different models. I am still not…

  • OneTrainer – My first LoRA

    My first LoRA training with OneTrainer Stable Diffusion models may lead to “standarized” results. Images may be generated with the same face for different prompts. So, to obtain personalized results (a face with specific features, a specific dress/clothing, more detailed eyes, mouth, hands/feet, and so on) Stable Diffusion models (checkpoints) may need a LoRA (or…

  • LoRA in Stable Diffusion

    LoRA in Stable Diffusion (Low-Rank Adaptation) 1. Introduction to LoRA Low-Rank Adaptation (LoRA) is an advanced technique in machine learning that enables fine-tuning of large pre-trained models with minimal additional parameters. It was originally designed to address the challenge of adapting massive models to specific tasks without the prohibitive cost of training them from scratch…

  • AI Image Generation Models – StableDiffusion

    Introduction Artificial Intelligence (AI) has made significant strides in the field of image generation. AI image generation models leverage advanced machine learning techniques to create realistic images from textual descriptions, sketches, or even other images. These models have applications in various fields, including art, design, entertainment, and even medical imaging. This paper provides an in-depth…