To be honest -- I'm not sure what you've posted there. I asked you to post a "before" and "after" image, but it seems like you only posted a picture of your "text2img" generated image and the model you want to use the face of -- but not the final result. I can't see any face swap in the images you've posted.
Here's what you should have posted instead if you want any help on how to improve your outcome:
1) Image created by txt2img (this is just a quick and dirty ComfyUI workflow, no upscaler, no redifiner etc. ...):
2) Image you want to use the face of in ReActor:
3) Result you got:
4) Here's how you got the result:
Again: this is in no case an optimized workflow, it's a quick and dirty test to reproduce something you should've posted. But I think you get the idea: we do need to see a "before" and "after" picture if you want to get help on how to improve the outcome.