Murphylanga_SDXL_Ultimate_2024_v1.10
small optimizations and different conditioning combinations added
fix new custom nodes Version 22.01.2024
Murphylanga_SDXL_Ultimate_2024_v1.6
minor optimizations
Murphylanga_SDXL_Ultimate_2024_v1.5e
additional workflow that can be slimmed down and installed completely via the manager
Murphylanga_SDXL_Ultimate_2024_v1.5
many new optimizations
Murphylanga_SDXL_Ultimate_2024_v1.3
minor optimizations + different models test with the workflow on my Murphy Langa - YouTube
Murphylanga_SDXL_Ultimate_2024_v1.0
An assembly of my best workflows with new shortcuts and buttons for quick navigation
Completely new Ultimate workflow.
I merged my best workflows into one and added switches and shortcuts for easier use.
txt2img, img2img, inpaint, outpaint, highresfix, ultimate upscale, faceopt, faceswap, facecrop, loras, controlnet, image optimization and coloring, automatic translator, remove object, extra strength, deepblip,...
This is the video of an older workflow from me. But even to understand how to work with this workflow, the video is still helpful. This workflow here is more advanced. Groups can be switched using shortcuts, and many switches can be easily operated with buttons. I don't have the motivation to create a new video. If you want that, write it in the comments and subscribe to my YouTube channel to motivate me. :-)
Unfortunately, I deleted all my stars while cleaning up here :-( .... whatever...
Yeah! My workflow won a prize, I wish you a nice year 2024 :-)
installation Guide:
1. ) Install ComfyUI Manager Manager
https://github.com/ltdrdata/ComfyUI-Manager
2.) Install all other custom nodes using the manager
or do it manually, here are all the nodes used
ComfyUI's ControlNet Auxiliary Preprocessors
Here the Install.bat can help.
I use the config.yaml
For my 3070 I changed the last line there to be able to use the ONNX models: EP_list: ["DirectMLExecutionProvider", "OpenVINOExecutionProvider", "ROCMExecutionProvider"]
Here the Install.bat must be called separately so that the Blip models work
AlekPet/ComfyUI_Custom_Nodes_AlekPet
is not loaded via install missing custom nodes. But you can search and install manually in the manager
pythongosssss/ComfyUI-Custom-Scripts
SDXL Prompt Styler (customized version by wolfden)
Save Image with Generation Metadata
If you want to make it easier for yourself, you can simply delete the FaceSwap group:
FaceSwap I think this is still needed for the Reactor Node
ReActor Node for ComfyUI (read Installation Guide!!)
I strongly recommend making a backup beforehand!
I had several failed attempts to get the reactor node to run after the Cuda12.3 update.
I even crashed my comfy !!!
I found a solution for myself:
as described on the page of ...
Gourieff/comfyui-reactor-node: Fast and Simple Face Swap Extension Node for ComfyUI (github.com)
under ....Troubleshooting:
Download Insightface and install it as described. Usually the version for Phyton 3.11
If it works well, if not you can try the following, that led to success for me:
uninstall everything with the following command in the comfyUI main directory:
python_embeded\python.exe -m pip uninstall onnx onnxruntime onnxruntime-gpu
Then install the following versions with the command:
python_embeded\python.exe -m pip install onnxruntime-gpu==1.16.3 onnxruntime==1.16.3 onnx==1.14.0
I can't guarantee whether this will work for you and I don't know what else it could have an impact on. If you do that, it is your own risk.
Best regards, Murphy
If you don't understand something, here is some information I wrote down about previous workflows:
Use refresh website (F5) for large workflows.
Groups and nodes can be switched on/off and bypassed using the right mouse button. This was used to be able to add additional things step by step. I have added a description to the more complex workflows to better understand them.
Many different custom nodes were used, how to install them is described below in the earlier versions.
The easiest way is to use the manager and the install missing custom nodes function
Right click on a group or node to switch on or off or set bypass
pythongosssss new add -> select pictures display at model and lora and many other cool things. maybe you have to solve the node at checkpointloader with the right mouse button over pin and delete the special characters with title
Another note about the groups in ComfyUI!
Right click on the group.
Set group node to never (Turns off the nodes in the group completely).
Bypass group nodes (skips the nodes in the group and the workflow can go through).
set group node to always (turns the nodes in the group back on)
To create a mask, right click on the image.
-> open in MaskEditor
Face Restoration Models
https://github.com/TencentARC/GFPGAN/releases/ https://github.com/TencentARC/GFPGAN/releases/download/v1.3.4/GFPGANv1.4.pth
https://github.com/sczhou/CodeFormer/releases/ https://github.com/sczhou/CodeFormer/releases/download/v0.1.0/codeformer.pth
Face detection models:
https://github.com/xinntao/facexlib/releases/download/v0.1.0/detection_Resnet50_Final.pth https://github.com/xinntao/facexlib/releases/download/v0.1.0/detection_mobilenet0.25_Final.pth https://github.com/sczhou/CodeFormer/releases/download/v0.1.0/yolov5l-face.pth https://github.com/sczhou/CodeFormer/releases/download/v0.1.0/yolov5n-face.pth
You have to follow the rules and instructions of the custom nodes!
Disclaimer:
This software is meant to be a productive contribution to the rapidly growing AI-generated media industry. It will help artists with tasks such as animating a custom character or using the character as a model for clothing etc.
The developers of this software are aware of its possible unethical applicaitons and are committed to take preventative measures against them. We will continue to develop this project in the positive direction while adhering to law and ethics.
Users of this software are expected to use this software responsibly while abiding the local law. If face of a real person is being used, users are suggested to get consent from the concerned person and clearly mention that it is a deepfake when posting content online. Developers and Contributors of this software are not responsible for actions of end-users.
By using this extension you are agree not to create any content that:
violates any laws;
causes any harm to a person or persons;
propogates (spreads) any information (both public or personal) or images (both public or personal) which could be meant for harm;
spreads misinformation;
targets vulnerable groups of people.
Note!
If you encounter any errors when you use ReActor Node - don't rush to open an issue, first try to remove current ReActor node in your workflow and add it again
ReActor Node gets updates from time to time, new functions appears and old node can work with errors or not work at all
Description
fully workflow has been optimized a bit further and some switching options have been added. Additional comments added so that the possibilities and working methods can be better understood.
FAQ
Comments (11)
((noob alert))
hello! i played a bit with your wonderful workflow. when i try to make a faceswap it looks that comfyui keeps working on the original face instead on the "swapped" one. am i missing something? (yes, a part from a lot of knowledge and good english :) ) ty for your hard work and for any help.
Hello, i get these nodes missing errors.
LoadImagesFromDir undefinedundefinedInspire
GlobalSeed undefinedundefinedInspire
where can i find these?
Hello,i get these node errors.
SDXLPromptStylerAdvanced
i have installed sdxl_prompt_styler node latest,
how can i find these? thank u
Looks like a great workflow, I went thru it but when I press Queue, nothings happen, any idea ?
Hi, great workflow! Just a suggestion. As mentioned on the LoadImageWithMetadata GitHub page, it's no longer being maintained (the repo is archived), and they suggest using the SD Prompt Reader Node instead. I'm using it here and it works perfectly, as you can see in this Screenshot.
can you explain. how to use outpaint?
I see a nice update, but I'm missing the translate nodes, painternode and posenode, and don't find it in your instructions...
I version 2.01 is the latest, but that doesn't match up with the other versions. Should we be downloading v2.01 or v16?
It looks cool but i can't use it because ReActor is not working at all. No matter what i did and do it always says "Import failed".Besides that my DeepTranslatorTextNode is missing
Workspace uses the ConfyUI portable version. Is it possible to download the built version with all add-ons somewhere? I am using an Nvidia 3070 graphics card. I've tried to install several versions, but errors pop up in plugins in one place or another. It would be cool if you could share an archive with a working build with all plugins connected. Or maybe a script for automatic sequential installation?
Your last few workflows kill my browser (Chrome on Linux). I have 64 GB ram and a top I9 CPU. Each time I run Comfy it then hangs while loading your workflow and until I clear cache I can't load anything else.
Looks like we don't have an active mirror for this file right now.
CivArchive is a community-maintained index — we catalog mirrors that volunteers upload to HuggingFace, torrents, and other public hosts. Looks like no one has uploaded a copy of this file yet.
Some files do get recovered over time through contributions. If you're looking for this one, feel free to ask in Discord, or help preserve it if you have a copy.