A custom workflow built for the Qwen Image GGUF model that leverages the new Qwen Image 4‑Step Lightning LoRA for both text‑to‑image and image‑to‑image generation, with integrated upscaling nodes for enhanced output quality.I have a free written guide that includes the required models and custom node links, available here -  <a target="_blank" rel="ugc" href="https://www.patreon.com/posts/free-qwen-image-136738711">https://www.patreon.com/posts/free-qwen-image-136738711</a>Usage Notes(Beware - Workflow includes an unofficial/experimental Inpainting feature) :For inpainting, right click on your loaded image in the load image node and click "open mask editor" to create a mask around the objects you want to change. Then your positive prompt to detail the change you want to make in the new image. When inpainting, you may want to play with the denoise value in the Basic scheduler node to maintain some form of consistency until controlnets are released for the model. Results can be very inconsistent but still is fun to play around with a bit.Runpod Template:<a target="_blank" rel="ugc" href="https://get.runpod.io/Qwen-Image-Template">https://get.runpod.io/Qwen-Image-Template</a>If you want a full walkthrough of the workflow and installation process—including manual setup, recommended settings, and tips for both local and cloud deployment—check out my YouTube tutorial linked below: <div data-youtube-video><iframe width="640" height="480" allowfullscreen="true" autoplay="false" disablekbcontrols="false" enableiframeapi="false" endtime="0" ivloadpolicy="0" loop="false" modestbranding="false" origin playlist src="https://www.youtube.com/embed/D8z2i0WN2zQ?rel=1" start="0"></iframe></div>

Files with SHA256: ef8749517eeba3d9fde505d6d035b343e92071ac333619d7350505c4ec5d3b4c