<ol><li>Uses <a rel="ugc" href="https://github.com/mit-han-lab/ComfyUI-nunchaku">ComfyUI-nunchaku </a>for load optimizations</li><li>Uses <a rel="ugc" href="https://github.com/hassan-sd/comfyui-image-prompt-loader">comfyui-image-prompt-loader</a> for loading either local image or civitai image with or without metadata, copies prompt/seed/step values into workflow</li><li>Runs image through Depth</li><li>HighRes Fix is then run</li><li>Outpainted 3 times incrementally instead of a large singular outpaint</li><li>Ultimate Upscaled</li><li>2 x Detailer nodes (Face/Person/whatever extra detailing you want)</li></ol>Use CaseGrabbing an image you scraped with either civitai, gallery-dl or other tools for AI gen images that contain prompts, so you can:<ul><li>Reproduce the image</li><li>Tweak or iterate in a slightly different way from original image</li><li>Just grab prompt only from original image</li><li>Just use original image for depth</li><li>Expand and upscale original image</li><li>All of the above in one single flow or individually if wanted</li></ul>

Files with SHA256: 1e5f03bc95c7efc31b42a8cd3f7b23b3f34fed393cb6e54e5e3f7ce6cbedd435