This is an advanced workflow designed for those familiar with ComfyUI who want pro grade results. It is node heavy and has numerous options. I encourage you to take the time to learn it. If you feel overwhelmed, you can start with my simple model HERE
也有中文说明
Instagram: https://www.instagram.com/synth.studio.models/
Buy me a☕ https://ko-fi.com/lonecatone
This represents hundreds of hours of work. If you enjoy it, please 👍like, 💬 comment , and feel free to ⚡tip 😉
Note: If you have ANY issues with nodes not downloading, read the notes or reach out. There's nothing that special about any of them that aren't core modules. Most issues can be resolved by updating everything
⛔⚠️🛑✋ Read the notes completly before using. Most common install and node problems are listed in the directions
A complete user and troubleshooting guide inclusing a list of common error messages can be found here https://civarchive.com/articles/24678/how-to-use-my-workflows-a-comprehensive-breakdown
V14.0
Because it is not in my nature to leave things alone....
Gutted the stock face detailer nodes and replaced them with a SEGS suite for infinately better results
Note: Yes, I will be going through all my workflows and replacing them, including teh NSFW ones
Controlnet Update.
Added local bypass nodes so you don't have to zoom and scroll
Major update to notes, especially for detailers
V13.0
Overhauled the Controlnet:
Now you can select the aspect ratio of the original image without having to "guess" it with the aspect ratio node
Left room for the resize node so you can choose which side to crop the image by
Redid the dependencies so that every tie you shut it on and off, you don;t need to reset the switches so it will not give you an error 😡
Massively improved the notes throughout
Minor layout tweaks
V11.3
Detailers are now able to handle float32 models, so I rewmoved the SDXL Based checkpoint.
Please give me feedback with any issues on this, especailly RAM related.
Added a crop section so you can...well... crop images easily
Updated several areas
Added the ability to use a simple date with the metadata folder
added a "remove banned tags" node
V8.0
Removed Florence Prompt assist and replaced it with Qwen Advanced.
Reorganized the controlnet section because it bugged me. Now it's easier to use.
Added a LoRa controller for the detailer for better character facial and eye consistency as well as a localized prompt
Gutted the backend of the post production suite and added 📷optical realism, giving a significantly better way to fine tune your images.
Fixed some backend mathAdded a 📂 subfolder generator that seperates the metadata files according to the name you give the file for easier use.
V7.0
Added KSampler Configure Nodes so you can leave the setting in place for both ZIT and base without having to change them
Removed some problematic nodes
Removed Qwen Prompt enhancer. I refuse to put an API one in there.
global scheduler and samplers for consistency
Better math
Improved notes throughout.
All in 1 workflow:
Controlnet
Checkpoint option for merged models
I2I
Prompt generation
Prompt enhancement
Lora Loader
Advanced KSampler
Draft mode for making corrections without having to rerun the workflow.
Seed variance enhancer
Ultimate Upscaler for prescaling and hi res fix
Detailing Suite for face, hands, eyes, and expressions
Seed VR2 Upscaler to get 4k on low VRAM
Massive Post Production Suite
JPEG Scrubber
Smart Noise scrubber
Full tutorial available.
也有中文说明
Check out my other models:
My NSFW version with Anantomy Correctors:https://civarchive.com/models/2270894/zit-nsfw-anatomy-corrector
For ultimate Anime detail and control: https://civarchive.com/models/2220766/zimage-ultra-anime-detail-workflow-get-the-most-out-of-your-generations
For Realism and variety over the base model: https://civarchive.com/models/2231181/z-image-ultra-real-workflow
Description
Added SEED VR2 upscaler
Added a denoise filter in post processing
Rearranged the central console for easier adjustments
Upgraded Cnet
Fixed a few loose ends
Improved instructions
FAQ
Comments (22)
can i know what is resizeimagenode? only that node i can't install
any resize image node will do. Just plug teh controlnet image into the input, then teh two get nodes (Width and height) in accordingly)
I personally use this one:
lets you pick which metric to use for resizing (dimensions, megapixels, etc etc), lets you also resize masks in the same node. its simple, yet versatile and just works!
https://github.com/quasiblob/ComfyUI-EsesImageResize
@Bragonborn all that is is a very long version of what can be accomplished in a smaller node. Yeah, It's great and if I wanted that much control over the image size, I would. Less is more hen you are creating workflows for other people. A noob would be lost.
As far as masks go, and this is where everyone has issues. If you resize the mask and image seperately (i.e. after creation, which even this node does) you are risking alignment issues. Peopel often solve this with blur or feathering, but then you lose th crispness no mater what you do. Resize the image down to 720p or so BEFORE you create the mask.
Rant over. Tanks for the advice though.
@lonecatone23 The workflow use ResizeImageNode and ResizeLongestToNode. Googling resulted to comfyai.run a comfy cloud service. (https://comfyai.run/documentation/ResizeLongestToNode)
I'm assuming that everyone that downloaded this workflow will get this error. So if any resize image node will do, then why not use one that is available through GitHub so when we "install missing custom nodes" everything will be resolved.
I appreciate the work put into this workflow.
@resikel836 I think I already swapped it out and reloaded it, but I'll check. I know I did on my Illustrious workflow.
I appreciate the heads up.
@resikel836 I've replaced them. It is now 4.0.1 with generic nodes.
@lonecatone23 awesome! thanks.
Hi this is a beautiful workflow and im excited to get it working. Can you explain please how to inpaint using this workflow?
I tried this: CNET image off > CNET mask on > made a mask in mask editor but also tried importing my own. This is how i thought it would work but i got no inpainting result and just an entire new image. Do i need to connect the nodes different, toggle settings different? can you also tell me if the mask needs to be white or black colored?
Turn all teh nodes on and off. every time you bypass it, it does that. Then make sure you are using eithee teh image or teh mask by the control on teh top right. Also, you need to switch off every type of mask you do not want. Let me know if you have any further issues. I thought I expalined it well enough in the notes. Tell me what I could improve
@lonecatone23 I'm still having trouble, but it think its more my fault because I am new to comfyui. would you mind doing a short video tutorial on maybe changing a shirt color using inpainting while keeping everything else the same.
@whitejt2 wait. Are you commenting on the right workflow? I have a workflow specifically for that. This is not what this is designed for. This is a pro generator
https://civitai.com/models/2237592/zit-any-swap-low-vram
@lonecatone23 Hi yes! I was giving a simpler example, but In the description it says the other model is not generative yet. I guess a better example would be how could I mask a dress and have it replaced with a blouse. I am trying to find a way for the generation that comes from this workflow (which is amazing!) to only be applying to a masked area. I really love all the upscaling and noise generation happening in this workflow so i would want to keep that for stuff like doing face swaps with masks and then detailing
@whitejt2 I faceswap on PIcsi.ai. The PulID and the FLUX Pilid nodes in Comfyui are broken. Generate the photo to the general vcicinity of what you want and then do that.
Right now the Preview Bridge node if broken or I would already have both workflows do this. You'd have to reload the finished pic noow
@whitejt2 I'll make a version with Sam3 built in probably today.
@lonecatone23 you are amazing thats exactly what i was looking for, will it allow for loras/checkpoints/controlnet for the inpainting too? sorry to ask a lot im working on figuring out how to do this all on my own
@whitejt2 It will change item colors and remove stuff. It's already done. I'm running it through testing now
It is done and it's badass. 10 hours worth of work. You're welcome
@lonecatone23 i love you so much <3
@whitejt2 Then buzz me 👍⚡
@lonecatone23 done c:
There's a whole Module for it, and you make the mask in teh mask editor
