I've been learning how to use generative AI in general and ComfyUI in particular for some time now, and I believe I finally have a workflow worth sharing.It's based on various sources and a lot of experimentation, and works for any model which will accept a natural language prompt.<h2 id="the-core">The core</h2>Through leverage of wildcards it obtains endless diversity. The expanded wildcards get sent to Ollama. Through use of either a generic system prompt, for models like e.g. Flux Dev, or the specific Z-Image system prompt these expanded wildcards get transformed into a well-defined prompt.<h2 id="added-goodies">Added goodies</h2><ul><li>SeedVR2 Upscaling</li><li>Color Grading</li><li>Image enhancement</li><li>Image saving with Civitai metadata</li></ul><h2 id="used-custom-nodes">Used custom nodes</h2>All can be installed through ComfyUI Manager<ul><li><a target="_blank" rel="ugc" href="https://github.com/ltdrdata/ComfyUI-Impact-Pack">ComfyUI-Impact-Pack</a></li><li><a target="_blank" rel="ugc" href="https://github.com/chflame163/ComfyUI_LayerStyle">ComfyUI Layer Style</a></li><li><a target="_blank" rel="ugc" href="https://github.com/rgthree/rgthree-comfy">rgthree-comfy</a></li><li><a target="_blank" rel="ugc" href="https://github.com/yolain/ComfyUI-Easy-Use">ComfyUI-Easy-Use</a></li><li><a target="_blank" rel="ugc" href="https://github.com/kijai/ComfyUI-KJNodes">ComfyUI-KJNodes</a></li><li><a target="_blank" rel="ugc" href="https://github.com/numz/ComfyUI-SeedVR2_VideoUpscaler">ComfyUI-SeedVR2_VideoUpscaler</a></li><li><a target="_blank" rel="ugc" href="https://github.com/cubiq/ComfyUI_essentials">ComfyUI_essentials</a></li><li><a target="_blank" rel="ugc" href="https://github.com/ClownsharkBatwing/RES4LYF">RES4LYF</a></li><li><a target="_blank" rel="ugc" href="https://github.com/TTPlanetPig/Comfyui_TTP_Toolset">Comfyui_TTP_Toolset</a></li><li><a target="_blank" rel="ugc" href="https://github.com/stavsap/comfyui-ollama">comfyui-ollama</a></li><li><a target="_blank" rel="ugc" href="https://github.com/ltdrdata/ComfyUI-Inspire-Pack">ComfyUI-Inspire-Pack</a></li><li><a target="_blank" rel="ugc" href="https://github.com/calcuis/gguf">gguf</a></li><li><a target="_blank" rel="ugc" href="https://github.com/bash-j/mikey_nodes">mikey_nodes</a></li><li><a target="_blank" rel="ugc" href="https://github.com/ltdrdata/was-node-suite-comfyui">was-node-suite-comfyui</a></li><li><a target="_blank" rel="ugc" href="https://github.com/PGCRT/CRT-Nodes">CRT-Nodes</a></li><li><a target="_blank" rel="ugc" href="https://github.com/edelvarden/comfyui_image_metadata_extension">comfyui_image_metadata_extension</a></li></ul>The sampler and scheduler that are configured in the workflow seem to work best for me, but as always YMMV ;-)<h2 id="additional-info">Additional info</h2>A good source for free LUTs (used in the Layer Style nodes) is <a rel="ugc" href="https://freshluts.com">https://freshluts.com</a>, the specific Rec709 LUT I use is <a rel="ugc" href="https://freshluts.com/luts/1440">Rec.709 Film Look</a>

Files with SHA256: 678da463ab51c8228d649a9464b17ee245c2c49fe16f30afe25c7463c7138b64