Author: Wei Mao

In this article, we’re diving into my latest and greatest improvements to the ComfyUI background replacement workflow. Over the past few months, I’ve released several updates that introduced advanced features like IC-Light for more natural subject integration and Flux-based ControlNet for better results. But now, we’re moving beyond those iterations, bringing you a streamlined, more…

Welcome, creators! In this article, we’ll dive into an advanced ComfyUI inpainting workflow designed for flexibility and efficiency. In my previous article, I covered outpainting and inpainting results using different versions of the Fill model, alongside a practical outpainting workflow. Today, we’re focusing on inpainting, with a special look at how to swap items, fix…

If you’ve ever attempted to replace a portrait background, you know the challenge of ensuring the subject matches the lighting and ambiance of the new scene. Enter the Redux model by Black Forest Lab, which excels at maintaining lighting harmony between the subject and the background. It’s comparable to IP-Adapter in some ways, but with…

Welcome back, creators! Today, we’re pushing the boundaries of what’s possible with Black Forest Lab’s Fill models for inpainting and outpainting. Whether you’re exploring the official 20GB version or the more efficient quantized Q4 and Q5 models, this video will help you unlock their full potential. I’ve also developed a powerful workflow to make these…

The Flux family of models has been generating excitement within the AI community, known for its high-quality results and a variety of applications. However, the diversity of options available—ranging from the official Flux models (Pro, Dev, Schnell) by Black Forest Lab to the numerous fine-tuned variations—can make it difficult to know where to begin or…

In this article, I’ll walk you through my latest portrait beautification workflow designed to elevate your images with just a few clicks. This workflow focuses on natural enhancements, improving skin, hair, and fabric textures without making the photo look overly edited. Whether you’re working with low-light shots, blurred images, or portraits of older subjects, this…

Hello, friends! Wei here. Today, we’re going to explore and compare 3 popular face replacement techniques: Flux-based PuLID, SDXL-based InstantID, and the latest SDXL-based EcomID. You can download the workflow for free: https://openart.ai/workflows/myaiforce/2ATyK62dutoPVCevX8o5 Each of these methods has its own strengths, but none are currently capable of reaching a perfect 100% face match. To address…

Hello and welcome! Today I have something exciting to share with you: RF Inversion. With it, I built a powerful ComfyUI workflow that unlocks creative possibilities I hadn’t imagined before. And the best part? You can download the workflow for free: https://openart.ai/workflows/myaiforce/p3tGdtbvkAfzODW6MkiP When paired with Alimama’s Turbo LoRA, image generation using Flux becomes incredibly fast,…

Welcome back, creative minds! In this article, we’ll dive into a new and simplified workflow for replacing backgrounds using the Flux ControlNet Depth model. This approach is a more streamlined version of my previous background-changing method, which was based on the Flux model. Although the old workflow was powerful, it was quite complex and ran…