Hey everyone. Today, we’re diving into something exciting from Black Forest Lab: the Flux.1 Kontext models. These models have just dropped, and they’re designed to make image editing easier and more intuitive, simply by using text-based instructions. For those who’ve been following along, you may recall a couple of months ago when I showed you…
1 Prompt: Change the white t-shirt to the dark red t-shirt. Keep the woman in the exact same position and pose. The red t-shirt features a prominent white, slightly distressed graphic in the center. The graphic depicts a messy bun hairstyle adorned with a red, white, and blue bandana patterned with stars and stripes. Tiny…
In this article, we’ll walk through an updated workflow that blends a person into a new background while keeping the pose, composition, and details intact, thanks to the Union ControlNet 2.0 model. If you watched my previous video, you already know about the power of the Redux model for maintaining consistency in the face, clothing,…
But today, I’m even more excited to introduce a groundbreaking new image relighting model that outperforms the well-known IC-Light. I’ve tested this model, and its results blew me away — so I can’t wait to show you what it can do and how to use it effectively within ComfyUI. Discovering the LBM Relighting Model This…
Nunchaku isn’t just another Flux model accelerator—it’s a paradigm shift. While testing on a modest Tesla T4 (16GB VRAM), I watched it generate 1024×1024 images in 26 seconds while using under 8GB VRAM—peaking at just 33% utilization. This isn’t brute-force speed; it’s surgical efficiency. The implications are staggering: This is just the baseline. As we’ll…
Welcome to the ultimate showdown between two very different approaches to AI image editing! On one side, we have ChatGPT—the flashy newcomer that edits images through simple text prompts, acting like a “magic box” where you type a wish and poof—it’s done. On the other, ComfyUI—the open-source, node-based powerhouse beloved by tinkerers who want full…
Welcome back, creators! If you’ve read my last two articles, you already know how ACE Plus revolutionizes image editing by preserving intricate details during inpainting. Today, we’re taking that power further. I’ve crafted a specialized ComfyUI workflow that merges ACE Plus with Redux—a dynamic duo that lets you copy and blend objects, faces, or even…
Introduction to Advanced Scene Integration Blending Reality and Imagination in ComfyUI Imagine dropping your portrait subject into any environment – whether a tropical beach at sunset or a cyberpunk cityscape – while preserving their identity and creating seamless interactions with the scene. This article introduces a game-changing workflow that transforms basic background swaps into context-aware…
Last year, I introduced a ComfyUI workflow that revolutionized portrait background replacement, achieving up to 90% facial similarity between the original and generated images. Today, with ACE Plus technology, we’ve pushed that boundary to 99% consistency—a breakthrough that ensures near-perfect facial preservation even in complex edits. This article will walk you through the upgraded workflow,…
Welcome, creators! In this article, I am excited to introduce you to an innovative ComfyUI workflow designed to transform low-resolution images into stunning high-resolution versions. This powerful tool not only enhances the clarity and detail of your images but also preserves the original composition, allowing you to achieve remarkable results with ease. Let’s dive in…