[Stable Diffusion] Prompt Sharing and Learning Thread

deadshots2842

Member
Apr 30, 2023
163
279
Bro, none of this stuff you are using comes from a commercial project. The whole automatic1111 toolset and all the plugins etc are just some "Anon"s volunteering their time and efforts to put a relatively usable front end on the free Stable Diffusion models released by StabillityAI. They are just anon hackers who are sharing cool tech with the rest of the world for free.
I'm taking about pyproject.toml that's giving me error. I'm always getting some kind of error when I'm trying to install Reactor lol. This is why I'm asking people for example photo of how good this extension is so I can decide if it's worth all this trouble.
 
  • Like
Reactions: osanaiko

Sharinel

Member
Dec 23, 2018
498
2,060
I'm taking about pyproject.toml that's giving me error. I'm always getting some kind of error when I'm trying to install Reactor lol. This is why I'm asking people for example photo of how good this extension is so I can decide if it's worth all this trouble.
I have no idea what that file is, I installed reactor from within Auto1111, and pressed the button to apply and restart, and that was it. Literally 1 button press to install - check the bottom of the screenshot. I have no idea what you're doing to get that file showing as not working. Did you install it from the 'install from URL' tab?

1717280581680.png
 

devilkkw

Member
Mar 17, 2021
295
999
Now?? Even when I install project do I have to install poetry or something like that too?
The problem seem a compile error, and reading location of your buildtool, it's in program files, so try to run process with admin right. or compile it manually (i had same problem with cuda dll) or find precompiled version on the web.
 

deadshots2842

Member
Apr 30, 2023
163
279
The problem seem a compile error, and reading location of your buildtool, it's in program files, so try to run process with admin right. or compile it manually (i had same problem with cuda dll) or find precompiled version on the web.
Solved that part I think now I'm seeing problem from above image.
 

theMickey_

Engaged Member
Mar 19, 2020
2,112
2,649
I did get it to work but result are lower then expected. Maybe any tips to improve my result anyone?
Post your "before" and "after" images as well as the face you're using to replace the original face, and post your workflow, too (sorry, but I'm a ComfyUI user, but I guess something similar to a "workflow" exists in Auto1111 as well...?!). It's impossible to tell you how to do it properly without knowing what you actually did.
 

deadshots2842

Member
Apr 30, 2023
163
279
Post your "before" and "after" images as well as the face you're using to replace the original face, and post your workflow, too (sorry, but I'm a ComfyUI user, but I guess something similar to a "workflow" exists in Auto1111 as well...?!). It's impossible to tell you how to do it properly without knowing what you actually did.
Here.
 

theMickey_

Engaged Member
Mar 19, 2020
2,112
2,649
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. ...):
1717461671411.png

2) Image you want to use the face of in ReActor:
1717461730762.png

3) Result you got:
1717461750251.png

4) Here's how you got the result:
1717462149329.png

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.
 

felldude

Active Member
Aug 26, 2017
500
1,477


ComfyUI_00700_.jpeg


I've released the checkpoint I have posted teaser images of 2k ultra realistic etc.

Over 20GB of training data, BLIP-2 training enforcement over 100,000 steps.

Try it out
 

deadshots2842

Member
Apr 30, 2023
163
279
Here. output image was already recreated before i just png infoed that from there.
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.
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.
You mean u want the orginal and
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.
here before and after using reactor.
 

Synalon

Member
Jan 31, 2022
202
626
You mean u want the orginal and

here before and after using reactor.
Reactor replaces faces, so get a nice picture of the face only. 512x512 is acceptable, higher res is better. Try again with just the face.
If its drawing arealistic face when you don't want it to try turning off restore faces.
 
Last edited:

theMickey_

Engaged Member
Mar 19, 2020
2,112
2,649
here before and after using reactor.
Seems to me like it's working -- what exactly is your issue? I must say though, the model you're using to generate the "original" image and the image from which you want to use the face have (very) different art styles, so the "after" image is exactly how I'd expect it to be -- the face of the "after" image is not matching the art style of the rest of the image.

If you want to get a better result, maybe try to use the face you want to use for replacement and do an img2img transformations with the same model you're using to generate the "before" image, hopefully to get a better matching art style of just the face. And then use the transformed face in ReActor. Not sure if that's working, but that's how I would try to get a better result.
 

Sepheyer

Well-Known Member
Dec 21, 2020
1,526
3,596
Dudes, would anyone know why Face Restore stopped working in CUI after a long while and if it has a fast fix? Naturally, there are error messages, etc., I am checking to see if someone ran into this very issue, i.e.: oh yea, the custom_node interface got trashed, you need to re-dl this [1, 2, 3]. Else I'll be diving into the error list which clearly is FML.
 

Sharinel

Member
Dec 23, 2018
498
2,060
Can you explain with example for auto1111 i didn't understand what you're saying.
What everyone is telling you and what you are ignoring is that in the example images you attached in your previous post, Reactor is working exactly how it should. You just don't like the end result.

Here, I'll even post examples that you demand in every one of your messages

This was the original that I used following your prompt, except for the lora
00651.jpg

Now here she is with Reactor adding on the face you wanted.

00652.jpg

Your reactor image isn't really compatible with the checkpoint you are using. I then used the following pic as the Reactor face instead

Demiportrait 2.png

Which gave me this result

00653.jpg

It all depends entirely on the image you use for the reactor face. Using a full body picture when all you are cloning is the actual face is not the best method of doing it. Try and find a high resolution image of just the face and shoulders
 

Synalon

Member
Jan 31, 2022
202
626
Can you explain with example for auto1111 i didn't understand what you're saying.
If you upload the 2 images I asked for I will do a screenshot guide for you.

Sharinel is also correct that you will probably need an anime checkpoint to do anime.

Now Upload the picture you want the face on. And upload the picture of the face you want to apply.
 

Synalon

Member
Jan 31, 2022
202
626
He already posted the original image and the face he wants to swap with. He also already did the actual face swap, so he knows how it's done. He just don't like the result, and we've already discussed why that might be the case (art styles not matching).
I see, theres nothing left I can do then.
I added a picture I made using Face ID in controlnet, still doesn't match the face he wanted in the picture though.
 
  • Like
Reactions: deadshots2842