Hello, everyone! Today, I’m excited to share some key techniques I’ve learned while experimenting with the Flux model. Over the past few days, I’ve generated about 500 images, tweaking prompts and LoRA to see how different prompt structures can control image layout and background sharpness. In this article, I’ll walk you through these techniques and…
In this article, I’ll guide you through a workflow I recently developed for outpainting using Flux models. It has given me some fantastic results, and I’m excited to share it with you. This workflow not only seamlessly expands backgrounds but can also outpaint complex parts of the human body—like hands and feet—with minimal errors. Image…
Welcome to this guide! Today, I’m excited to share a fantastic workflow using ComfyUI and Flux models that allows you to easily change the background of any photo—be it a person, an object, or virtually anything else. Whether you want to give an image a fresh new look or match it with a different setting,…
The landscape of generative art is constantly evolving, and the recent release of FLUX by Black Forest Labs has sparked significant interest among creators. FLUX is an open-source text-to-image suite of models that, according to official evaluations, outperforms many of the leading models in the field, both open-source and proprietary—including the popular Midjourney. As someone…
Master product photography with AI! Learn how to use MidJourney & ComfyUI, plus discover the latest workflow updates to enhance your visuals. Read more here.
Discover a ComfyUI workflow for stunning product photography. Learn to blend, relight, and enhance images with perfect lighting and details. Read more!
The recent release of Stable Diffusion 3 (SD3) has sparked diverse reactions within the community. While some have praised its advanced text generation capabilities, others have been dismayed by its shortcomings, particularly in rendering human bodies accurately. To thoroughly assess SD3’s performance, I spent considerable time testing and generating numerous images, comparing it to other…
Hello everyone! Today, I’m excited to introduce a newly built workflow designed to retouch faces using ComfyUI. This workflow showcases the remarkable contrast between before and after retouching: not only does it allow you to draw eyeliner and eyeshadow and apply lipstick, but it also smooths the skin while maintaining a realistic texture. Importantly, the…
Today, we will compare three AI face-swapping technologies: PuLID, InstantID, and IP-Adapter’s FaceID-V2, using a ComfyUI workflow. These technologies are built on a face analysis system called InsightFace, which is a deep face analysis library designed for face recognition, face detection, and face alignment. Note that InsightFace requires a commercial license. IP-Adapter FaceID was the…
Today, we’re diving into the innovative IP-Adapter V2 and ComfyUI integration, focusing on effortlessly swapping outfits in portraits. This tutorial simplifies the entire process, requiring just two images: one for the outfit and one featuring a person. By utilizing ComfyUI’s node operations, not only is the outfit swapped, but any minor discrepancies are resolved with…