About the workflow
realistic Skin / No plastic
The details of the picture can be enhanced. Images can be generated with text, or images can be reversed and regenerated through pictures, and then the details can be increased by enlargement.
Two Loras are loaded by default in the workflow. One is for turbo acceleration, and the other is the Lora I trained to improve the reality of realistic portraits. The link is here.
In the part of enlarging the picture in the workflow, new noise points will be automatically injected into the original picture for redrawing, thereby achieving a significant improvement in details, and it is also applicable to illustration styles. Here is an illustration Lora I just trained. You can load it and try. The effect is very good.

Description
FAQ
Comments (12)
All the nodes required for this workflow breaks ComfyUI
I don't understand what you mean. Could you explain it in detail?
are you sure this works? can you show the image of your node setup ?
Sure, if necessary.
This will break your comfyui.
Why do you say so?
@vjleoliu Because the custom nodes needed for this WF are incompatible with the latest comfyui updates, plus it did break mine and can't generate images because of that. This WF needs to be updated.
@luffyd1900566 Oh, you're right. This workflow has indeed been released for some time. Let me think about how to upgrade it. Thank you for the reminder.
@luffyd1900566 Oh, you're right. This workflow has indeed been released for some time. Let me think about how to upgrade it. Thank you for the reminder.
thanks,i love your work.






