Welcome to my personal workflow.
This does not generate videos. I use this to make the images that i use with kling.
Change Log:
Remade LoRA stack to make it capable of bypassing all LoRA's or one by one
Put IMG2IMG into its own ksampler group, so now you dont need to connect it to TXT2IMG group anymore.
You may have noticed things look a lot different but don't worry it all works the same as the last version.
Moved the bypasser to a more convenient spot
updated some notes to reflect these changes
Features:
First i added an easy group bypasser from rgthree-comfy. No more right clicking and searching for the bypass button.
Second the workflow is using advanced LoRA loaders, in order to pull LoRA keywords directly into ComfyUI. So no more tab switching to find your needed keywords. Nodes are from ComfyUI-Lora-Auto-Trigger-Words
You will need to download the two previous features using ComfyUI Manager. Once you have the manager installed, Open the manager find "Install Missing Custom Nodes" and install the ones it shows you. Then restart the UI.
Requirements:
ComfyUI: comfyanonymous / ComfyUI
ComfyUI Manager: ltdrdata/ComfyUI-Manager
Human Brain, I think.....
Also if you want it to look as clean as the one in the image. You will need to change your links to straight. To do this navigate to Settings > Lite Graph > Graph > Link Render Mode. Change it to straight.
If you are new to ComfyUI id advice that you watch a few tutorials on what nodes are and how they work together.
You can use this workflow with one click "BUT" id advise against it. You'll get better results if you turn off groups until you need them, or until you have an image you want to continue with.
I highly recommend you to get ComfyUI manager. It will help you download all the required nodes and models needed to use this workflow.
Please read the notes i placed around the groups. They will help you understand what each group does, and how they work together.
PS. Thank you for trying out my workflow. If you'd like to support me just give me a follow on Civitai, or Buzz me if you feel like it.
Description
Change Log:
Remade LoRA stack to make it capable of bypassing all LoRA's or one by one
Put IMG2IMG into its own ksampler group, so now you dont need to connect it to TXT2IMG group anymore.
You may have noticed things look a lot different but don't worry it all works the same as the last version.
Moved the bypasser to a more convenient spot
updated some notes to reflect these changes
FAQ
Comments (3)
I'm also confused by this... I'm trying to cartoonify something, the first pass on the latent image does a great job of that, but then the upscaler just upscales the latent and not the cartoonified render... What's going on?... I've tried like 10 times now and I just have 10 slightly different upscales of the latent image.
the upscale node may be connected wrong. Check if its connected to the lora you are using to cartoonify.
GarouAI I'm not using a lora, I'm using the King of Toons checkpoint with no loras... The Upscale node is connected to Image Sharpen, which connects to the Upscale Refiner, which then has spaghetti connections all over the place, but the pink line goes down to the connection point you made for the IMG2IMG node.

