<h3 id="comfyui-workflow">ComfyUI Workflow</h3>Requires: <a target="_blank" rel="ugc" href="https://github.com/r-vage/ComfyUI_Eclipse">ComfyUI_Eclipse 3.5.x</a>its a very basic workflow that uses nodes from Eclipse which supports 8 Backends:<ul><li>transformers, gguf (llama-cpp-python), ollama (docker), vllm (docker), sglang (docker), llama.cpp (docker), wd14 (onnx), yolo</li></ul><ul><li>Image Description (VLM / WD14) + create variations or timeline prompts (e.g. wan)</li><li>Text Input (LLM) + create variations or timeline prompts (e.g. wan)</li><li>Detection (Face, Eyes, Hands, and other areas ;) using Florence2 and Yolo (qwen detections are usally meh... but works very good with huihui qwen 3.5 9b claude 4.6</li></ul>try claude for image to prompt descriptions / detection (also very good):<ul><li>ollama: huihui_ai/qwen3.5-abliterated:9b-Claude</li></ul><h3 id="important-security-notice-running-llms-locally-with-comfyui">⚠️ <a target="_blank" rel="ugc" href="https://civarchive.com/articles/29938/important-security-notice-running-llms-locally-with-comfyui">Important Security Notice — Running LLMs Locally with ComfyUI</a></h3>

Image to Prompt & Detection, Direct Chat, Variations, Timeline, Lyrics

updated version:<ul><li>uses the eclipse sml nodes</li><li>introduces a basic example of the new bridge nodes which allows wireless control (subgraph aware: see iGEN ONE).</li><li>this workflow and the iGEN workflows are shipped with the latest version of Eclipse ;)</li></ul>

Files with SHA256: b8aa4681224459016d2f5071440383733afaa24181e7fed5fbfab6b7b2b40f4d