Comfyui Workflow (Image Generation)

• required Custom Nodes:

  • ComfyUI_Eclipse: Version 2.4.49, GitHub, ComfyReg

  • ComfyUI_SmartLML: Version 2.5.4, GitHub, ComfyReg

  • https://github.com/numz/ComfyUI-SeedVR2_VideoUpscaler

  • Ollama Registry: https://registry.ollama.ai/huihui_ai

    • to run qwen3.5 update the ollama image (0.17.7): docker pull ollama/ollama:latest 2>&1

    • remove the eclipse-container: docker rm eclipse-ollama 2>&1

• if you need help installing nunchaku or how to use the nodes check the readme files in the repo readme folder at github.

• llama-cpp-python is needed for the loading_method: GGUF (llama-cpp-python) in the Smart LML Node

  • https://github.com/r-vage/ComfyUI_Eclipse/releases/download/wheels/llama_cpp_python-0.3.16-cp312-cp312-win_amd64.whl

• nunchaku wheels:

  • https://github.com/nunchaku-tech/nunchaku/releases

  • https://github.com/nunchaku-tech/nunchaku/releases/download/v1.0.2/nunchaku-1.0.2+torch2.9-cp312-cp312-win_amd64.whl

• nunchaku model files:

  • https://huggingface.co/spooknik/Fluxmania-SVDQ/tree/main

  • https://huggingface.co/nunchaku-tech/nunchaku-flux.1-dev/tree/main

  • https://huggingface.co/nunchaku-tech/nunchaku-qwen-image

  • https://huggingface.co/nunchaku-tech/nunchaku-qwen-image-edit-2509/tree/main

  • https://huggingface.co/nunchaku-tech

• Wildcards

  • https://civarchive.com/models/20868?modelVersionId=532723

• Version 3 uses a new layout and replaces context pipes with KJ's Set/Get nodes plus 2 additional Eclipse nodes (GetFirst and GetAllActive).

• Why the layout changed: In the old workflow, changing the model or LoRAs triggered a full re-run including SmartLML's image description, which is slow. The new layout decouples this — SmartLML runs once to describe the image, and that result is reused via Set/Get nodes. Subsequent runs skip the description step when the seed/index is fixed. When shuffling images (-4), SmartLML naturally re-runs since the image changes.

• The basic guider is gone — the CFG guider is used for everything (set CFG to 1.0 for Flux, etc.).

• Some rgthree nodes have been ported to Eclipse (Fast Bypasser/Muter, Fast Groups Bypasser/Muter, Repeater, Image Compare). They are converted to work with the V3 API and Nodes 2.0, using a different approach — no LiteGraph.registerNodeType interception or subclassing.

• GetFirst & GetAllActive: Virtual frontend nodes that extend KJNodes' Set/Get system with priority-based variable resolution.

  • Get First resolves the first active (not muted/bypassed) SetNode from a prioritized list of variables — ideal for fallback chains (e.g., try LoRA model first, fall back to base model).

  • Get All Active outputs all active SetNode variables simultaneously, each on its own output slot — perfect for collecting multiple active components.

  • Both nodes feature:

    • Type filtering to show only matching SetNode variables

    • Automatic rename tracking when SetNodes are renamed

    • Reorder context menu (Move to Top / Up / Down / Bottom, Insert Above)

    • Green dot indicators showing which variables are currently active

    • Optional virtual link visualization

•