Note: I spend a lot of time on these to make sure they are top notch. If you have ANY issues, I'm very responsive. hit me up and I'll resolve them for you.
This is an advanced workflow designed for people familar with Comfyui and who want pro grade results. I encourage you to learn it, but if it is overwhelming, the simple version can be found HERE
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
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 😉
V16.0
Upgraded to Clownshark Samplers
Added a denoise for I2I 🖼️
Swapped out the Qwen Prompt enhancer for the abliterated GGUF one for faster responses
Made it so you an use the original image to color match in post processing 🎨
Minor OCD stuff
V15.0
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 the NSFW ones
Controlnet Update.
Added local bypass nodes so you don't have to zoom and scroll
Added a quality modifier prompt area that follows after Qwen so that they stay preserved.
Major update to notes, especially for detailers
V12.1
Added an Inpaint area
Modified controlnet so it doesn't fault out if a mask isn't loaded without resetting teh switch
Removed the sentence remover (it sucked)
added "banned tag remover" at the metadata saver so you can still process normally
V11.1.2
Updated 📝Prompt Assist
Updated ⚙️ main area
Added back Qwen VL prompt enhancer (now that it's fixed)
Updated 🔎 detailers
Updated 💾 Save area so that you can embed workflows as well as add a simple date to the folders so you aren't endlessly looking for them.
Added an inline ✂️ crop tool in the 🎨Post Production Suite
Ver 10
Improved regional prompt suites
Added IP Adapters for Face, style, and composition for Facial and pose consistency
Improved detailer suite
reworked settings for easier use
Added CivitAI sentence ✂️
Ver 9.0
Qwen nodes keep getting mbroken due to updates. I removed them in V9
Removed outdated sections
Added a 2nd KSampler & model option for refinement
V 8.1 is included in the folder
VER 8
Created a really cool regional prompter.
Works with controlnet
Upgraded detailers to accomodate for it so you can detail each face seperately
This is an all in one workflow:
Controlnet: background remove, canny, openpose, depth, canny/depth
I2I prompt assist
QwenV2 Prompt enhancer.
Florence and Qwen prompt assist
Style selector
Dual Model Loader: Better control
Sage Attention: Speeds up production
Ultimate Upscaler for prescaling and hi res fix
Detailing Suite for face, hands, eyes, and expressions
multi face detailer
Seed VR2 Upscaler to get 4k on low VRAM
Massive Post Production Suite
Smart Noise scrubber
Full tutorial available.
也有中文说明
Description
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 ou don't have to zoom and scroll
Added a quality modifier prompt area that follows after Qwen so that they stay preserved.
Major update to notes, especially for detailers
FAQ
Comments (16)
can't find JTeethSeg.pt,thx
If possible, please make a video to explain it. Your workflow is really difficult for a beginner like me to learn and understand, and I don't even know how to use it.
Hello. I have written an article to help people get it loaded and how to use it as well as several tutorials on ComfyUI https://civitai.red/articles/24678/how-to-use-my-workflows-a-comprehensive-breakdown-and-troubleshooting-guide
Also, as a newcomer, I suggest starting out with one of my simple versions here: https://civitai.red/articles/29606/lonecats-simple-workflows-guide.
If you get really stuck, you can message me
Okay, this is a great help to me, thank you! I'll start with the very basics.
@lonecatone23 I’ve only been using ComfyUI for half a year with no prior relevant background. I’m still totally confused and have no idea how to get started. My ComfyUI installation is a brand-new clean environment without any models pre-installed, so I can’t run anything at all. Many concepts that seem basic to experienced users are really hard for beginners like me to grasp and understand.
There are three major issues I haven’t been able to figure out so far:
No clear guidance on which model version to download: The model download pages you recommended offer many different versions, yet there’s no explanation of which one is suitable or the differences between each version. I have no clue which file to download to match the workflow and don’t know where to begin.
Lack of explanations on how nodes work together: You’ve explained the function of each node separately, but haven’t covered how to combine and connect them. New users can’t learn how the entire workflow operates as a whole, making it impossible to build a logical workflow mindset.
The full workflow is overly complicated and hard to navigate: While the complete workflow covers thorough details, its layout is messy. It takes ages to locate a single specific feature. It would be far easier to learn and reuse individual functions if they were split into separate modular sections.
I’ve spent a lot of time studying this, yet I only picked up scattered bits of knowledge. I still struggle with sorting through different model versions and understanding node combinations, and I’m unable to generate images by operating the workflow on my own.
@539948692712 Okay, you have to be kidding me. Did you even open up the workflow and look at it? Nice job having an LLM write your response for you 👍
I purposely make simple workflows and put a disclaimer at the top of the info page for this. Each section is broken out for what it does and all can be bypassed. This is a pro grade workflow and very organized. I do not make these for newcomers. I assume that people using them have a basic understanding of ComfyUI.
Here is a simple one https://civitai.red/models/2600919/lonecats-simple-workflows?modelVersionId=2921603
That being said, I strive to make my stuff as accessible as possible. I thought the models were self explanatory. I will review and make modifications to my notes.
I love your work & thank you for sharing. One problem I have however is that some of the nodes slow down the way Comf works, and it is not unusual to see 300s gen time when all sparks and whistles are on. On 3090 RTX 24GB and 128GB RAM, so meh not wow. I noticed the postproduction group, even when isolated and copied elsewhere is the culprit. Any hints on how to improve? Since the results are stunning...
which nodes? I have never had this problem. The heavy hitters are the smart noise, optical realism, Lens FX, and Image adjust.
Bypass or remove them one by one and see what happens. I have never heard os this.
Great work but now my comfy installation can't do I2V anymore giving me the following error message:
AttributeError: module 'tensorflow' has no attribute 'Tensor'
and there seems to be no working fix for this, which is sad because i would like to use this workflow. Is there any way around this? Or do we know which node installation is causing this to happen?
turn off background removal. Try that first. Also, turn the I2V switch off to verify that it is causing the problem
@lonecatone23 I installed the nodes for the V15.0.4 and something in the comfy installation changed as a result. It does not generate videos anymore in general giving me the error message I mentioned. I didn't use I2I in the workflow or background removal but I installed all the nodes which are required for everything. It seems like I will just reinstall comfyui. It would just be nice to know which installation is causing this to happen.
@sih9312 are you on desktop?
No nodes would cause that unless you are running on a very old version of Torch or Xformers. Just updating Comfyui would resolve conflicts.
@lonecatone23 I was on desktop when I installed the nodes yes. This could be the reason.
When I start the browser version and update comfyui the error message still remains.
@sih9312 If you are on ComfyUI portable, you shoudl have zero issues with that.
Feed your log through an LLM. You have a version conflict somewhere. I've been using the same node groups for ages due to their stability without issue.
@lonecatone23 I am on portable yes. Anyway, thank you for the replies, I will just reinstall comfyui.