This is an advanced workflow designed for those familiar with ComfyUI who want pro grade results. It is custom node heavy and has numerous options designed for those who want granular control over their end result. I encourage you to take the time to learn it. If you feel overwhelmed, you can start with my simple workflow 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 that I give away for free. If you enjoy it, Please make sure to 👍like and post to my workflows. That is how you support me. Also, 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 user and troubleshooting guide including 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
V8.0
added my B&W to Color Plus suite
V7.0
Added the Moodboard:
V6.0
So here's the thing....
I love tinkering and figuring things out. I figured out how to get around a 🤡clownshark sampler's conflict with normal sampler names, spent probably 8 hours making a regex list, redid all my workflows, then realized I could just use two seperate sigma schedulers and a custom advanced Sampler 🤔
Updates:
Found an insanely good set of Style 👠👗 nodes.
Updated the entire Left side of the workflow. everything works better.
You can now use prompt enhance, I2I, image reference, and style selectors together (if you're that crazy. Hey, I like options 🤔)
Redid the entire 🧠 brains region so that you have the entire option list between regular or 🤡 Clownshark samplers
Added a quite lengthy set of 💡tips and tricks.
V5.0
Added Controlnet
Added Clownshark converter regexes
added Clownshark Sampler Selector
Fixed a broken node in Optical RealismAdded Controlnet
V4.2
Man, I hate detailers. I really do. They either make an image or tear it up. I spend more time trying to find the right combination of these that actually do something, only to find each model is different.
I've upgraded these to Sam3 detailers. They are much cleaner, especially on the face and eyes.
You can also use them for inpainting.
added a spare detailer
added blend mode sliders
I improved the LLM instructions.
Added word ✂️ nodes in teh Florence area to get rid of watermarks, logos, etc.
Improved CivitAI 🚩 filters
Made a few minor tweaks.
V3.1
Not enough to change the version number, but important enough to re-release:
Repair hi res fix slider get/set break
Redid sigma math on Karras (try it....)
Added a link for the 🚫abliterated Text encoder
Adjusted some settings for out of the box realism
V3.0
Fixed an error in the Image Edit area 🙄
Added LLM instruct prompt selector 📝 (modified from @FaboroHacks )
Added a really cool style selector node
setting tweaks
updated notes.
V2.0
made some tweaks
added Image edit
Note: This is not as good as I thought it woud be. I need to find a model or LoRA that helps it. If someone finds one, let me know.
Note: I've used several .GGUF versions of this, especially from this site. They are not good. I left the GGUF option there for it, but it is a very VRAM friendly model
Updated notes
V1.0:
Pompt Assist
Includes Florence Prompt to extract a prompt from an image
Includes a GGUF abliterated version of Qwen Promper Enhancer.
Image Options:
Select the aspect ratio or set it to match the original
Includes I2I 🖼️
Advanced Sampler section
Custom schedulers (unique setup) that allow you to choose between preset sigmas
Detailer Daemon
Denoise slider
simple one location setup for your base settings
Ultimate Upscaler with VRAM assistance
Full array of advanced SFW & NSFW detailers
Full post production Suite
multiple photo effects
Color adjust to a loaded image or to the original image
Clarity FX
Lens FX
Arcane Bloom
📷 Optical Realism Suite
Inline crop & edit suite
Description
So here's the thing....
I love tinkering and figuring things out. I figured out how to get around a 🤡clownshark sampler's conflict with normal sampler names, spent probably 8 hours making a regex list, redid all my workflows, then realized I could just use two seperate sigma schedulers and a custom advanced Sampler 🤔
V6.04 fixed draft stop bug
Updates:
Found an insanely good set of Style 👠👗 nodes.
Updated the entire Left side of the workflow. everything works better.
You can now use prompt enhance, I2I, image reference, and style selectors together (if you're that crazy. Hey, I like options 🤔)
Redid the entire 🧠 brains region so that you have the entire option list between regular or 🤡 Clownshark samplers
Added a quite lengthy set of 💡tips and tricks.
FAQ
Comments (14)
hey ! where should i put the control net lora . which folder ?
Just the regular LoRA folder. nothing special
thank you for your help. I'm running into some trouble.
Problem: The dropdown list in the AILab_QwenVL_GGUF_PromptEnhancer node cannot find my Qwen3-VL model.
The files (Qwen3-VL-8B-Instruct-c_abliterated-v3.Q4_K_M.gguf and mmproj-Q8_0.gguf,etc.) are placed in: ComfyUI\models\LLM\GGUF\
There is no "missing plugin" error, but it only reports that the qwen3-vl file is missing.
I have already tried editing gguf_models.json and creating custom_models.json with both relative and absolute paths, and restarted ComfyUI multiple times, but it still doesn't show up.
https://github.com/huchukato/ComfyUI-QwenVL-Mod
You can find most of your solutions here
After 4 days of usage of this workflow, it's more useful than the others' one~
By the way, recently I have noticed a new type of junction (maybe~?) that can LET YOU DRAG the 3D module in the widget to shift the light source.
As the same author, a another junction can let user to drag 3D module and camera source to shift the view angle instead of word describe~
So, Mr. Lonecat~ Do you have any plans to add this function to your Workflow in the future version?
Here's the link about the junction I said before: https://www.bilibili.com/video/BV15XKg6uEcm/?spm_id_from=333.1007.top_right_bar_window_history.content.click&vd_source=82ea1db40cb1b9e58c9833f93406134c
Thanks a lot~~
Best wishes.
This is totally useless without a link to the repo.
@lonecatone23
Sorry, Mr. lonecatone. I found a previous version, in ref1 you can find in the current Comfyui Manager:
ref1: https://github.com/jtydhr88/ComfyUI-qwenmultiangle
But you can see more interesting junc on his Github platform~~~
ref2: https://github.com/jtydhr88
It seems like junc (Creat camera info), but the original one seems not so straight to understand the param of it, while this junc (ref1) uses an upload image then adjust the sight to control the sight angle out put.
While the video link is, the junc author wants to shift the junc like a 3D workstation to control the camera angle to the target (see ref2).
May this info help you ~~
Best Wishes.
@qingyun6663 I can build a workflow for this, sure
@lonecatone23
By the way, maybe this junc is just like a reference. I think you are a master at identifying if it is really helpful or not. LOL~~
The reason why I submitted the comments is that I sometimes found the Krea 2 (T2I) output img angle does not play what I want. Even I restart the Comyfui, it still does not follow my order (I make sure I have unloaded all those lora).
If you have more useful advice, plz tell me more~~
Thank you.
@qingyun6663 That can be resolved with reference imsges and controlnet, but unfortunately Krea2 does not like either.
I'll look at it and see. I just see it as a huge suite that might be better served as it's own, but I'll mess w ith it
@lonecatone23
Thanks a lot~
Maybe the future version of the junc and Krea module can solve these......
You are my lord~hhhhhhhh
I submitted some images under your Krea 2 workflow, hope useful~~~
Have a nice day~
@qingyun6663 Thank you. You as well 🙏
@qingyun6663 This is for Qwen. The block weights do not align. I did however post a moodboard that has camera angle options
@lonecatone23
Thanks~~~
I have just noticed that your update about workflow~~~
underthis, I still update another image as comments~~
prompts are so heavy that I am too lazy to paste them....lol~~~~
By the way, I think this image can be my next gen screen background (Maybe it is not SAFE FOR WORK.......lol)~~~