ComfyUI — Flux Advanced — Daemon +Meta

Hello there and thanks for checking out this workflow!

What's new? : Lots of structural changes + NF4 packs optional!

—Purpose—

Built to provide an advanced, versatile and modular workflow for Flux with focus on efficiency, structure and information.

This workflow comes with many notes explaining node settings and recommendations, as well as general guides from instructions to troubleshooting.

—Features—

• Convenient loaders for all common versions of Flux and Clip models

• Full metadata; recognized by CivitAI

• LoRA support

• Wildcard support

• Flux Tools LoRAs Canny + Depth

• ControlNet presets for Canny, Depth and HED

• Flux Redux

• PuLID Enhanced

• LLM prompt assistance

• Installation and download guide for models and nodes

• multiple passes with optional upscales

• — 1st : Detail Daemon

• — 2nd : Tiled Diffusion — or — UltimateSDUpscale

• — ADetailer with dedicated LoRA Loader

• — Inpainting

—Custom Nodes—

• ComfyUI-Allor

• ComfyUI-Custom-Scripts

• ComfyUI-Detail-Daemon

• ComfyUI-GGUF

• ComfyUI-Image-Saver

• ComfyUI-Impact-Pack

• ComfyUI-Impact-Subpack

• ComfyUI-KJNodes

• ComfyUI-List-Utils

• ComfyUI-PuLID-Flux-Enhanced

• ComfyUI-TiledDiffusion

• NF4 version only — ComfyUI_bitsandbytes_NF4

• NF4 version only — ComfyUI_UNet_bitsandbytes_NF4

• ComfyUI_Comfyroll_CustomNodes

• comfyui_controlnet_aux

• ComfyUI_essentials

• ComfyUI_ExtraModels

• ComfyUI_IPAdapter_plus

• ComfyUI_LayerStyle

• ComfyUI_UltimateSDUpscale

• ComfyUI_VLM_nodes

• cg-use-everywhere

• rgthree-comfy

• was-node-suite-comfyui

Most of which can be installed through the ComfyUI-Manager

—Troubleshooting—

1. If nodes show up red (failing to load), check the 'Install Missing Custom Nodes' tab of the ComfyUI Manager for the missing node packs and install them.

2. Please check if all custom node packs load properly after installing, i.e. no (IMPORT FAILED) messages next to any of them in the console upon ComfyUI startup.

3. Always reload/drag'n'drop the original, downloaded workflow file into ComfyUI to reload an intact version of the workflow.

   → The last opened workflow that appears on startup shows a cached version of the workflow, "remembering" group nodes that failed due to missing nodes as failed, keeping them broken even after having everything installed correctly.

██     ███     ███     ███     ███     ███     ███     ███     ███     ███     ███ 

April 17th : ComfyUI has updated its frontend to v1.16, which introduces breaking changes to group nodes without solution.
→ frontend v1.15.13 works perfectly fine and should be used until a solution is found

To do so edit your run_nvidia_gpu.bat file to the following:

.\python_embeded\python.exe -s ComfyUI\main.py --windows-standalone-build --front-end-version Comfy-Org/[email protected]
pause

   ███     ███     ███     ███     ███     ███     ███     ███     ███     ███     █

Specific issues :

• LatentClamp ...
  → Ensure you have the ComfyUI-Allor node pack installed and NOT the LatentClamp pack

NF4 Version Installation Guide :

• For "ComfyUI_bitsandbytes_NF4" the "Channel" setting (Found in the top left of the ComfyUI Manager Menu) needs to be set to "Channel: dev" for it to show up in the search results
  → Important: turn the channel setting back to "Channel: default" afterwards
  

• For "ComfyUI_UNet_bitsandbytes_NF4"

  1. Open a terminal in ComfyUI/custom_nodes

  2. Use this command to clone the repo directly:
     git clone https://github.com/DenkingOfficial/ComfyUI_UNet_bitsandbytes_NF4.git

     → It has the same dependencies as "ComfyUI_bitsandbytes_NF4" so that should be all.
     

• If you encounter "security level" issues, you can modify the "config.ini" file located in ComfyUI\user\default\ComfyUI-Manager (edit with any text editor).
  The entry "security_level" is likely set to "= normal" (default), which did block manual custom node installation in some cases.
  When you change that setting to "= weak", save and restart Comfy, you should be able to install the nodes just fine.

  → Note: I'm sure this setting should not be handled lightly. I can only attest to the node packs mentioned in the list above to have not caused anything suspicious on my end.

—Thanks—

The workflow would not be possible as is without these custom node packs. If you want to support the custom node creators, give them a ⭐ on their github repos! Thank you!

Feel free to ask questions, share improvements and suggestions in the comment section!
Let me know if you encounter confusing points I can elaborate on in the next update!