ComfyUI Workflow

• Requires: ComfyUI_Eclipse 3.3.x

its a very basic workflow that uses 2 nodes from SmartLML Eclipse which supports 8 Backends now:

• transformers

• gguf (llama-cpp-python)

• ollama (docker), vllm (docker), sglang (docker), llama.cpp (docker)

• wd14 (onnx)

• yolo

• One for a image description (VLM / WD14) or text input (LLM)

• One for the Detection (Face, Eyes, Hands, and other areas ;) using Florence2 and Yolo (qwen detections are meh... but its under construction, works very good with huihui qwen 3.5 9b claude 4.6)

try claude for image to prompt descriptions / detection (also very good):

• In most cases, the model doesn't mince words and describes exactly what it "sees".

• transformers: https://huggingface.co/huihui-ai/Huihui-Qwen3.5-9B-Claude-4.6-Opus-abliterated

• ollama: huihui_ai/qwen3.5-abliterated:9b-Claude