v2update: Small workflow changes, better performance, faster generation time, updated ip_adapter nodes."
The workflow can generate an image with two people and swap the faces of both individuals.
Firstly, a mask is automatically generated which controls the respective deviation IP adapter.
An initial image is generated, the faces are automatically recognized, and a face swap is performed with Reactor. Then, the faces are enhanced with two face detailers, each controlled by their own face_id models, and finally, the finished image is upscaled.

Known bugs include it not working if there are more than two people in the picture.
Also, if the individuals are standing too close together, it might result in the wrong faces being swapped.
If you're having trouble with the installation of the ip_adapter, check out the GitHub page and read the installation instructions and the troubleshooting articles.
https://github.com/cubiq/ComfyUI_IPAdapter_plus
Description
FAQ
Comments (8)
Thanks for sharing this workflow.
I am getting totally different face. I dont know what is going on....
Even when i tested reactor node by itself it give me new different face and it is concestant where is it coming from>?
incase you came across this issue before, could you point how to fix this?
Same error,
Error occurred when executing ImpactFrom_SEG_ELT: From_SEG_ELT.doit() missing 1 required positional argument: 'seg_elt' ...
blah blah
Any idea?
Did u update your ComfyUi and the Node Packs ?
Same error after all updates, here is the message in the Comfyui interface:
Error occurred when executing ImpactFrom_SEG_ELT: From_SEG_ELT.doit() missing 1 required positional argument: 'seg_elt' File "D:\comfyui\ComfyUI\execution.py", line 152, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\comfyui\ComfyUI\execution.py", line 82, in get_output_data return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\comfyui\ComfyUI\execution.py", line 70, in map_node_over_list results.append(getattr(obj, func)()) ^^^^^^^^^^^^^^^^^^^^
i got the same error did anyone solve it?
you need to make sure that there are two people in the first generated image (like on the very small summary image on this page). For me, running it without change also resulted in this error. I added "two people in foreground" into the 3rd text prompt, so that it would generate two people.
When you start queue, look at the first scene preview, if there two people in that scene, you get that error, because must be 2 persons in that scene. By the way, I guess that problem source prompt system. It can't correctly identify two people.
cant work (IP Adapter errors)






