Hello there and thanks for checking out this workflow!
What's new in v27? : Major rework with new SubGraphs to streamline and compact the workflow even more, removal of outdated/broken nodes + fixes and optimizations all over!
—Purpose—
Built to provide an advanced, versatile and modular workflow for Flux with focus on efficiency, structure and information.
It 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
SageAttention, EasyCache + Model Compile acceleration
ControlNet with Union support
Flux Tools LoRAs Canny + Depth (alt. to CNet based on LoRA)
Flux Redux (similar to IPAdapter)
PuLID (SVDQuant version only)
Wildcard prompting
Installation and download guide for models and nodes
multiple passes with optional upscales
— 1st : Detail Daemon + Variation Seed
— 2nd : DD. + Tiled Diffusion / UltimateSDUpscale
— ADetailer with dedicated LoRA Loader
— Inpainting
—Custom Nodes—
ComfyUI-nunchaku — SVDQuant version only
All of which can be installed through the ComfyUI-Manager
—Troubleshooting—
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.
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.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.
—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!
Description
v16
— addition of Flux Tools LoRA as ControlNet alternative
— replaced IPAdapter section with Flux Redux
— structural changes to ControlNet and PuLID section
— resized samplers to accomodate live-previews
— turned on saving of .json files of the workflow by default
— expanded "Format Fix" to catch and fix more grammatical pitfalls
— minor changes in ADetailer and Inpainting
— custom node pack changes :
- : x-flux-comfyui
FAQ
Comments (6)
hello! I tried v16 and had some error, now when I use v15 I have an error on the sampler,
Could this be the update's fault?
@ak21 In the note above [ControlNet] it says:
=> Currently does not seem to work with PuLID active (Error)
And in the note above [PuLID] it says:
=> Currently does not seem to work with any ControlNet active (Error)
I will include a more obvious note additionally
@ak21 Just re-uploaded v16 with some minor changes in the notes ̷a̷̶̷n̷̶̷d̷̶̷ ̷̶̷a̷̶̷l̷̶̷s̷̶̷o̷̶̷ ̷̶̷s̷̶̷e̷̶̷t̷̶̷ ̷̶̷t̷̶̷h̷̶̷e̷̶̷ ̷̶̷<̷̶̷I̷̶̷n̷̶̷s̷̶̷i̷̶̷g̷̶̷h̷̶̷t̷̶̷f̷̶̷a̷̶̷c̷̶̷e̷̶̷_̷̶̷p̷̶̷r̷̶̷o̷̶̷v̷̶̷i̷̶̷d̷̶̷e̷̶̷r̷̶̷>̷̶̷ ̷̶̷i̷̶̷n̷̶̷ ̷̶̷P̷̶̷u̷̶̷L̷̶̷I̷̶̷D̷̶̷ ̷̶̷t̷̶̷o̷̶̷ ̷̶̷"̷̶̷C̷̶̷U̷̶̷D̷̶̷A̷̶̷"̷̶̷, as I managed to trigger the error even without ControlNet active and could fix it through this setting. Something in PuLID needs some updating, but the node-pack authors seem a little inactive unfortunately.
@ak21 I still run into this error randomly and even mid-generation and setting the insightface_provider to CUDA is not changing that as I first thought. I just had luck few times in a row when I tested the setting.
No idea how that even happens, but it looks like the PuLID-Enhanced version is more likely to get a fix for this, so I can switch over to that and update the workflow as soon as that happens. I originally went for the regular Flux PuLID pack hoping it would be more stable. Turns out none of them are 😂
@redpinkretro Yes, it's really a random error, it works for me today )))