I have some new and amazing upscale workflows available on my Patreon! Anyone joining the "Creators Lounge" tier also gets access to my Discord, for more workflows, images and ideas. Click here...
GalaxyTimeMachine AI Imagery | AI art in the form of digital images | Patreon
XLPlus_v3.5 is the latest version of my SDXL workflows.
This is the workflow used to create the example images for my latest "XLPlus_v3.5" model. It includes an LLM prompt enhancer, Portrait Master nodes, hands/face/eye detailers and a controlnet tile upscale.
In v4.0, the "KRestartSampler" node can be installed from:
https://github.com/ssitu/ComfyUI_restart_sampling
The dequality node is included in the zip file, and you just need to add it to your custom_nodes directory and restart ComfyUI.
v2.x now uses the new ComfyUI nodes for Cascade. Make sure you update it and install the models as recommended:
https://huggingface.co/stabilityai/stable-cascade/tree/main
stage_b.safetensors and stage_c.safetensors (you can use the bf16 versions) go in ComfyUI/models/unet
stage_a.safetensors goes in ComfyUI/models/vae
and this: https://huggingface.co/stabilityai/stable-cascade/blob/main/text_encoder/model.safetensors goes in the ComfyUI/models/clip/ folder to be loaded with the Load CLIP node in the workflow
The SDXL workflow includes wildcards, base+refiner stages, Ultimate SD Upscaler (using a 1.5 refined model) and a switchable face detailer.
Now with controlnet, hires fix and a switchable face detailer.
I'd recommend installing all the custom node packs shown in the resources, and also these:
https://github.com/chrisgoringe/cg-use-everywhere
https://github.com/bash-j/mikey_nodes
https://github.com/twri/sdxl_prompt_styler
https://github.com/Derfuu/Derfuu_ComfyUI_ModdedNodes
https://github.com/BadCafeCode/masquerade-nodes-comfyui
https://github.com/space-nuko/ComfyUI-OpenPose-Editor
Description
This is a 2 stage workflow for SD1.5 that I find produces EXTREMELY good results. I recommend using a semi-real model for the first pass and a photoreal model for the second pass. My "ForYou-SemiReal" and "ForYou-Photo" models are ideally suited to this.
FAQ
Comments (15)
When loading the graph, the following node types were not found:
* Text box
Where do I get this node?
Thank you!
I thought the text box was just a standard node, but it's not important for the flow to work. Is it the box in the face detailer switch panel? That's only there for information.
It's actually part of https://github.com/Derfuu/Derfuu_ComfyUI_ModdedNodes
@galaxytimemachine Thank you!
Does not work. Getting errors with 2 missing nodes, b/c the base nodes did not install.
0.0 seconds (IMPORT FAILED): C:\Users\xxxx\Deep\ComfyUI\ComfyUI\custom_nodes\was-node-suite-comfyui
Traceback (most recent call last):
File "C:\Users\xxxx\Deep\ComfyUI\ComfyUI\nodes.py", line 1596, in load_custom_node
module_spec.loader.exec_module(module)
File "<frozen importlib._bootstrap_external>", line 940, in exec_module
File "<frozen importlib._bootstrap>", line 241, in callwith_frames_removed
File "C:\Users\xxxx\Deep\ComfyUI\ComfyUI\custom_nodes\was-node-suite-comfyui\__init__.py", line 1, in <module>
from .WAS_Node_Suite import NODE_CLASS_MAPPINGS
File "C:\Users\xxxx\Deep\ComfyUI\ComfyUI\custom_nodes\was-node-suite-comfyui\WAS_Node_Suite.py", line 37, in <module>
from numba import jit
ModuleNotFoundError: No module named 'numba'
Cannot import C:\Users\xxxx\Deep\ComfyUI\ComfyUI\custom_nodes\was-node-suite-comfyui module for custom nodes: No module named 'numba'
That's a problem with your nodes, not the workflow.
follow the instructions to install WAS from the Github page. I think now he has an easy install.bat file that you can run from a cmd window if you're on windows.
Disconnecting the "Face Detailer Switch" causes other nodes to error unless I mute all of the face detailer nodes. How can I make it a one-click switch?
I'm using the same flow and it only errors in the FaceDetailer if the switch is disconnected. This is the expected behaviour. If nodes are erroring before the switch, it's something else in your setup.
@galaxytimemachine Right - it only errors in each of the nodes after the switch. I think there are three nodes I have to mute - the model loader, the face detailer, and the save image. Based on your comment I guess that is expected behavior, but wouldn't it be nice if the nodes could detect that there is no incoming image and mute themselves?
@FeralDiffusion Perhaps in a future version (I don't know how to do that yet!). The errors should only go to the console and not stop normal operation anyway.
How did you get the nodes to "Link Render Mode: Straight"?
I cannot find any information or instruction on how to do this on the ComfyUI-Custom-Scripts. Just a screen that it can be done.
It's in the settings, after you install https://github.com/pythongosssss/ComfyUI-Custom-Scripts
@galaxytimemachine Finally an end to the spaghetti salad. Thanks!
I can't get ComfyUI-Custom-Scripts to load. I've tried a bunch of things. Its this happening to anyone else?