ComfyUI Workflow
Requires: ComfyUI_SmartLML v3, ComfyUI_Eclipse
its a very basic workflow that uses the 2 nodes of SmartLML (supports 8 Backends now).
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)
try claude for image descriptions:
In most cases, "he" doesn't mince words and describes exactly what "he" sees.
transformers: https://huggingface.co/huihui-ai/Huihui-Qwen3.5-9B-Claude-4.6-Opus-abliterated
ollama: huihui_ai/qwen3.5-abliterated:9b-Claude