Introduction In our previous article, “Image-to-Image Transformation in ComfyUI”, we explored the fundamentals of building an image-to-image workflow. We discussed how latent space diffusion enables creative transformations while preserving essential elements of the input image. If you’re new to ComfyUI or image-to-image workflows, we recommend reading that article first to understand the basics. In this follow-up … Read more
Introduction Image-to-image transformation is a powerful technique used in AI-driven generative models to modify or enhance images by converting them into a latent space and applying diffusion processes. Unlike starting from noise, this approach allows users to work with existing images, enabling transformations that respect the original content while incorporating stylistic changes. This article explains how … Read more
When working with machine learning workflows, modular sampling can provide a more intuitive and flexible approach to constructing models. In the previous article, I showed you how to set up the Flux model using a standard case sampler node. In this guide, we’ll explore how to set up a modular workflow using the SamplerCustomAdvanced node, focusing on … Read more
FLUX, a cutting-edge family of AI models developed by Black Forest Labs, is gaining attention for its versatility and performance. In this article, we’ll focus on FLUX.1 Schnell, a distilled version of the FLUX model, and walk through its workflow, including setup, configuration, and optimization. If you’re working with limited video memory or exploring advanced AI … Read more
Stable Diffusion 3.5 is the latest iteration in AI image generation technology, offering enhanced performance, better prompt understanding, and compatibility with systems that have limited video RAM. With advancements in model architecture and text encoders, this version enables creators to produce high-quality images quickly and efficiently. This guide provides an in-depth overview of Stable Diffusion … Read more
Introduction The SDXL model offers powerful capabilities for image generation and refinement, making it a popular choice for creative workflows. In this article, we’ll explore how to set up the full SDXL workflow using both the base model and the refiner model. By leveraging these models effectively, you can produce high-quality images with improved details and artistic … Read more
Introduction Latent upscaling is an advanced image enhancement technique that operates within the latent space of stable diffusion models. By processing the image in its compact latent representation, this method allows for significant resolution upgrades and improved detail quality. Unlike traditional pixel-based upscaling, latent upscaling introduces new levels of detail during the rediffusion process, making … Read more
When working with complex graphs, improving clarity is essential to ensure better understanding and maintain productivity. Whether you’re organizing nodes, adding annotations, or optimizing connections, tools like groups, notes, and reroute nodes can streamline your workflow. In this article, we’ll explore these techniques step by step to help you create cleaner, more manageable graphs. Why … Read more
Introduction Upscale images is an essential step in improving their resolution for print, web, or other applications. AI image generation tools like Stable Diffusion and ComfyUI typically produce images with resolutions around 1024 x 1024 pixels (1 megapixel). However, for high-definition (HD) and ultra-high-definition (4K) purposes, higher resolutions are required—HD images are around 2 megapixels, while 4K images are … Read more
When working with AI-powered image generation tools like ComfyUI, understanding inference steps and CFG (classifier-free guidance) scale is essential for producing high-quality results. In this article, we’ll explore how these parameters affect image generation and how to adjust them to achieve the best outcomes. Understanding Inference Steps Inference steps, also known as sampling steps, define … Read more