I've been told numerous times that a lot of the workflows that I put out there are complex and intimidating. I wanted to put something out there that was easy to use and understand, but without sacrificing the quality and level of organization that has become my trademark.
These are simple versions of my workflows broken down into easy to understand sections with plenty of notes and limited options for the person new to Comfy.
LUT folder should be included. If not, it can also be seperately download above
A complete user guide can be found here: lonecats-simple-workflow-guide
也有中文说明
Features
Controlnet (except Anima)
I2I (except Anima)
Florence prompt assist
Ultimate Upscaler for prescaling and hi res fix
Detailing Suite for face, hands, & eyes
Full tutorial available.
也有中文说明
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.
Instagram: https://www.instagram.com/synth.studio.models/
Buy me a☕ https://ko-fi.com/lonecatone
This represents many of hours of work. If you enjoy it, please 👍like, 💬 comment , and feel free to ⚡tip 😉
Description
Krea 2 version:
Includes I2I
Upscaler
detailers
Prompt assist
FAQ
Comments (20)
Useless to keep clothes/faces. I used it to rotate camera's view of a couple at the beach, so we can see the land, and it changes the face and the clothes. Check it: https://imgur.com/a/314fEti
Thank you for you effort.
Fake account says what???
None of my workflows are set up to do that, bot.
seed set to random yet images come out mostly the same.
The prompt enhance node doesn't appear to exist in its relevant custom_node repo. Or rather, it does exist, but the workflow isn't using the "right one" so it shows as missing no matter what I do. I tried to wire up the one that the nodepack actually has, but I must have made a mistake somewhere because I can only produce random images!
https://github.com/1038lab/ComfyUI-QwenVL.
It's also in the manager. I just looked. You need to update.
You can sleo wire roght past it by connecting the prompt input to the next node over. It's there to help format the prompt into a language the model understands better
@lonecatone23 the workflow you're providing wants "huchukato/ComfyUI-QwenVL-Mod (1)"
@lonecatone23 and swapping it for the alternative repo you linked doesn't work.
what i say swapped:
```
cd ComfyUI/custom\_nodes
. ../venv/bin/activate
git clone https://github.com/1038lab/ComfyUI-QwenVL.git
git clone https://github.com/huchukato/ComfyUI-QwenVL-Mod.git
cd ComfyUI-QwenVL
pip install -r ./requirements.txt
cd ../ComfyUI-QwenVL-Mod
pip install -r ./requirements.txt
```
@civitaicomdolphin346496 Feed it through an LLM. You probably have other conflicts.
downloaded the krea2 workflow. if that is simple i wouldnt want to know what complicated is.
You're kidding, right? This is beginner level stuff. I even wrote a guide for it here: https://civitai.red/articles/29606/lonecats-simple-workflows-guide
If you have questions, feel free to ask.
@lonecatone23 S/he is right, this is far more complicated than most people's workflows. Maybe it produces amazing results but it's not suitable for people new to ComfyUI
@njmurov614 Man, if you cannot figure this out, then it’s hopeless. It literally has instructions and a guide for every step, and the settings are super easy. This is really basic stuff.
@lonecatone23 Thanks for sharing the workflow in any case. A beginner's workflow would include only the things that are absolutely necessary for running the model plus maybe one single LoRA. Once you start adding stuff such as custom nodes, upscaling, face detailing etc., it is highly likely that you won't get the expected results right off the bat and then you will have a whole bunch of parameters to tweak. For a beginner, it can be quite puzzling.
@njmurov614 where did I use the word "beginners"? These are very simple and easy to understand workflows. There are plenty of notes and a tutorial. Plus, they are many hours of work and the most solid ones out there, and I give them away for FREE. Plus, I have tutorials for beginners here: https://civitai.red/articles/28131/workflows-a-beginners-tutorial-and-hands-on-walkthrough-part-1
If you truly can't handle these, then use the "getting started" workflows included with ComfyUI.
@lonecatone23 Thanks again for all your work. I thought you were open to mild critique as, for example, you asked for feedback in your beginner tutorials. But if you're not interested in feedback, that's fine, too. If you're doing it for free, why would you want to improve?
@lonecatone23 Thanks for your work, mate! You said feel free to ask, but you come across rather agressive to people asking. Just saying. Regarding the workflow itself...I have tested about a dozen Krea2 workflows, have installed many nodes already, yet when I import your workflow it gives me 17 errors. No other workflow started out with that many things to fix. I would agree that this is not simple at all.
Даже привести это в рабочее состояние уже квест, это просто, чтоб оно заработало, не говоря уже о понимании самого процесса. Или это такой выпендрёж, типа смотрите , что для меня "ПРОСТО"
Любой, кто пользуется ComfyUI больше двух секунд, сможет в этом разобраться. Пакеты нод простые, а настройка лёгкая. Если ты не можешь это понять, то для таких «особенных» деток в шаблонах ComfyUI есть целая секция "Getting started".
Все нормально, просто не ясно куда было кидать Lut. Это специфическая нода, укажите куда конкретно ее кидать, а то гуглить пришлось) Еще очень долго происходит детализация лица и глаз. Можно это как то ускорить? Руки я думаю в Krea лишне детализировать, она и так хорошо с ними справляется, пережиток прошлого.
@dirtysem Помести папку с LUT напрямую в папку models. Расположение показано на дереве папок внизу в заметках:
Можешь уменьшить steps, но что касается детайлеров — я их почти не использую в Krea. В новых обновлениях я убрал все, кроме face one.





