Stoke McToke

Understanding Dim and Alpha: Key Concepts for LoRA Training

by StokeAI Tools and Resources, Learning Curve, LoRA Training October 16, 2024October 16, 2024No Comments

Introduction If you’re experimenting with LoRA training, you’ve likely come across different software tools, each using slightly different terminology to refer to the dimensions and scaling parameters of your model. Whether you’re using ai-toolkit, Kohya-ss, or another tool, understanding these parameters is crucial for getting the best results from your model. This article aims to …

Effortless Image Captioning for Flux Models Using Colab

by StokeAI Tools and Resources, Large Language Models October 3, 2024October 3, 2024No Comments

Introduction When it comes to training LoRA models on Flux (such as Flux Dev or Flux Schnell), one of the most challenging tasks can be generating high-quality, detailed captions for your image datasets. That’s where this easy-to-use Colab notebook comes in, offering a powerful yet simple solution for automatically captioning images using the Florence-2 model, …

AI Art for Beginners: How to Get Started for Free

by StokeAI Art Generation, Guides September 12, 2024September 12, 2024No Comments

Introduction Are you ready to dive into the world of AI-generated art without spending a dime? Whether you’re just curious or looking for ways to express creativity with cutting-edge technology, this guide will show you how to get started creating stunning AI art using free tools like TensorArt, CivitAI, and Google Colab. Even better, you …

Flux Models: Why Forge Works but Automatic1111 Doesn’t

by StokeAI Art Generation, AI Tools and Resources September 9, 2024September 9, 2024No Comments

Introduction: The Evolution of Stable Diffusion Stable Diffusion has seen several advancements, from the initial SD1.x releases to the more recent SDXL and SD3. However, the Flux models—such as Flux Dev, Schnell, and BNB NF4—have emerged as a new contender that stands apart in both architecture and performance. These models introduce key innovations like handling …

Flux Models Portrait Image Comparison

by StokeAI Art Generation, AI Tools and Resources September 5, 2024September 5, 2024No Comments

Introduction In the rapidly advancing field of AI-driven art creation, selecting the right model can significantly impact the quality and style of the generated images. With the ability to now run the latest Flux models through the SD WebUI Forge interface, artists and developers now have access to a variety of models, each offering unique …

Unleashing Creativity with FLUX: A Revolution in Generative AI

by StokeAI Art Generation, AI Tools and Resources August 20, 2024August 20, 2024No Comments

Introduction In the ever-evolving world of generative AI, staying ahead of the curve requires innovation and adaptability. Enter FLUX, a groundbreaking text-to-image diffusion model that is quickly redefining what’s possible in the realm of digital art. Developed by a team of ex-Stability AI developers under the banner of Black Forest Labs, FLUX is more than …

SDXL: Stoked Influencer XL

by StokeAI Art Generation, AI Tools and Resources August 15, 2024August 19, 2024No Comments

Days Hours Minutes Seconds MODEL GOES LIVE ONCE TIMER DISAPPEARS Free Credits: Stoked Influencer XL only at Tensor.Art

Find the Perfect SD3 Model for Your Needs

by StokeAI Art Generation, AI Tools and Resources August 7, 2024August 7, 2024No Comments

Introduction Choosing the right Stable Diffusion 3 (SD3) model can be a bit daunting, especially with the variety of options available. Whether you’re a seasoned AI enthusiast or just starting out, this guide will help you find the perfect SD3 model for your needs. Understanding the SD3 Medium Models The SD3 Medium models are popular …

Bringing Still Portraits to Life with LivePortrait

by StokeAI Art Generation, AI Tools and Resources, Creative AI Applications July 25, 2024July 25, 2024No Comments

Introduction In the ever-evolving landscape of AI and image processing, animating still portraits has become a fascinating and achievable task. This article introduces LivePortrait, an innovative framework that efficiently transforms static portrait images into dynamic, lifelike animations. By leveraging cutting-edge techniques, LivePortrait balances computational efficiency, precise control, and high-quality output. Notably, this model uses the …

Mr Stoke: Doom Scroll All Night

by StokeAI Art Generation, Creative AI Applications July 12, 2024July 12, 2024No Comments

I’m excited to share my very first full-length music video with you all. Admittedly, I picked the shortest tune in my music library for this project, but this was all about practice and proving the concept. Dive in, enjoy the vibes, and let me know what you think!