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
Added Turbo
Minor tweaks
FAQ
Comments (5)
slow as hell out the box for Anima but makes some nice 4k wallpapers
Is there a way to make Florence ignore certain visual traits when generating prompts? I’m using a character LoRA, but Florence keeps describing traits like hair color or race that the LoRA is supposed to control. Is there a method to prevent this, or is manually editing the generated prompt the only option?
Cut & paste the prompt and modify it. You can also use a text replace node as well, or you can try a different setting like short caption, or tags
for zimage it isn't a real I2I workflow right? it's just controlnet? i don't see any denoising controls for I2I and the picture is nothing like that images fed.
denoising controls? I2I has nothing to do with that.
I2I means you take the image and use it as a latent, which this does. It isn't supposed to duplicate the image. I think you mean face swap or inpaint