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 : Major rework with new SubGraphs to streamline and compact the workflow even more, removal of outdated/broken nodes + fixes and optimizations all over!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
v3
— addition of Xlabs sampler img2img
— re-addition of Tiled Diffusion
— custom node pack changes :
+ : ComfyUI-TiledDiffusion
- :
FAQ
Comments (6)
Was working great yesterday!
Updated ComfyUI and got:
Error occurred when executing XlabsSampler: 'DoubleStreamBlock' object has no attribute 'processor"
Hope to see an update soon and thanks for such a great workflow!
Thank you very much!
Yeah, the recent updates all change a fair bit each time. An updated version is coming in the next few hours!
@redpinkretro I just updated and it's working again!
I'm thinking of adding a "Style Transfer" (via IPAdapter) section to this workflow. Getting my head around the virtual connections though, not sure how to insert it into the pipeline.
@civitai204 So far I found the IPAdapter to be very underwhelming and it does not work with .gguf models. So I would hope for some more work on that. Fixing the typos at least... 😅
Strange, I've found it to do a fantastic job. Converted a photo of myself to look like it's painted in very thick and cracked paint done with a palette knife
@civitai204 with more general stylistic influences it does ok, but in terms of precision I found it vastly inferior to other IPAdapter implementations. The implementation for the Kolors model performed better from the moment it released as well, cause it was done by cubiq(Matteo Spinelli) who just knows his way around IPAdapters.
And so far the xlabs people just make very weird decisions in all areas with very suboptimal results in turn, which I am just annoyed by daily, as it is so much worse than existing alternatives they simply decided to gatekeep out by having the ControlNet implementation forced into their nonsense-sampler.
Sorry for the rant, I just facepalmed so often I might have a concussion at this point 😅