SDXL conditioning can contain image size! This workflow takes this into account, guiding generation to:<ul><li>Look like higher resolution images</li><li>Keep objects in frame</li><li>Guide image composition to make sense</li></ul><h2 id="installation-and-dependencies-lpq2zwkxg">Installation and dependencies</h2><ol><li>Install <a target="_blank" rel="ugc" href="https://github.com/WASasquatch/was-node-suite-comfyui">WAS Node Suite</a> custom nodes;</li><li>Instal <a target="_blank" rel="ugc" href="https://github.com/evanspearman/ComfyMath">ComfyMath</a> custom nodes;</li><li>Download and open this workflow.</li></ol><h2 id="how-to-use-zglbxx5eu">How to use</h2><ol><li>Select image for img2img;</li><li>Choose to resize or not;</li><li>(optional) Choose Conditioning Scale. It can make your output look like bigger, higher resolution image;</li><li>Queue Prompt.</li></ol>Pro Tip: You can set denoise to 1.0 to use the workflow as usual txt2img, but with size guiding benefits.<h3 id="note-vxxa6ja46">Note</h3>I made some research and find out that v1.0 version of the workflow was total bullshit 😅. If you downloaded previous version, don't use it. Better update.<a target="_blank" rel="ugc" href="https://civarchive.com/user/Postpos/models">Check out my other workflows</a>

SDXL img2img (automatic aspect ratio) | ComfyUI workflow

Total rework.<ol><li>Conditioning parameters are actually helping to get better picture now</li><li>Introducing Conditioning Scale</li><li>Single node from <a rel="ugc" href="https://github.com/evanspearman/ComfyMath">ComfyMath</a> intsead of giant math group</li><li>Crop forces resize</li><li>Compact layout</li></ol>

Files with SHA256: a9ce8fa558e33b79889fd80b1426de8d74cb7155fd0bb3d011c273451555758f