Guide Installing Stable Diffusion Webui & Nudifying (Inpainting) Guide
- Thread starter softarchitect
- Start date
-
Welcome to the Fakes / AI / Deepfakes category
When posting AI generated content please include prompts used where possible.
A new update just fixed all. Also it fixed preview while its doing the work.
I'm glad I installed it as portable, I'll just save this state as an archive, so I can use it offline if a new patch breaks stuff again.
I haven't used shirtlift, but to incorporate poses, you need to use ControlNet. I haven't tried it yet but here are some examples:
Edit: I downloaded shirtlift and I think it only works at txt2img section. Not for inpaint. For inpaint it works if the hands are already up there or you need to use Masked Content:Original and inpaint the bottom of shirt & breast area and the arms &hands. But it doesn't always holds the shirt up, need to make a bunch. Haven't tried with ControlNet.
Last edited:
Oh wow that's really interesting. You were able to get the unpainted subject to actually use their own arms to lift the shirt with enough iterations?
What prompt did you give it when I painting. Just what you want to inpainted region to do or also the entire image
Hello, I'm having issues with my webUI not launching despite it saying it will. When I run webui-user.bat it simply says: (see picture)
It doesn't give me the localport to launch the UI in a broser. I'm running on windows and I've followed several guides, most prominantly: and the first guide on this post.
Any help would be greatly appreciated, thanks in advance.
It doesn't give me the localport to launch the UI in a broser. I'm running on windows and I've followed several guides, most prominantly: and the first guide on this post.
Any help would be greatly appreciated, thanks in advance.
No, Arms were unpainted, hand was holding a phone so I painted the hand and bottom of shirt and breast are of the shirt, so the hand looked like its holding the shirt. Tried 10 similar images only one worked. And I made like 6-9 of that image so this isn't a viable process. I think this model is very strict to use with inpaint, also has same huge boobs I couldn't get rid off.
Maybe some prompts should fix it (you should look the other examples at the site) but I haven't changed the prompt I have from this guide.
Edit: Found another working photo: Seems like the hand should be up above for it to work. Masked Content is at "Fill" because it has no skin to work on there.
Last edited:
Ok, I think I manage to solve your problem. I don't have many shirt pictures to work but I think I got it working pretty well. First you need to put the picture at the inpaint sketch. And delete one arm/hand with a white color or a background color of the image with the brush. No need to be precise that much. After that draw a small hand at the location you wanted with a flesh color of the model has, connect it to the shoulder like an arm. Then use the button below to copy the image to inpaint and just put a mask to all of those, select Fill and press Generate. This should work.
I don't know what's your problem but your cpu & ram is really low. I think you'll need to wait like 1,5 minute per image if you happen to run the server. So I suggest just use the Google cloud. There's another guide for that in this forum. Also try installing the portable version.
Last edited:
Thank you for looking into this!
i see the goal is to trick the model a bit by massaging the original image to an ideal setup
when you say draw a small hand. do you really mean just free form draw a hand?
Last edited:
hi i try to aim similiar image like this, but mostly the cloth are gone / 100% nude, what prompt / tips to leave some cloths on?
my lora currently
sexy nude asia girl, nipple slip, masterpiece, RAW photo of a young asia girl, shaved, pink nipple, good proportion body,slim, petite
( <lora:inniesBetterVulva_v11:0.35> <lora:realisticVaginasGod_godpussy1V2:0.35> <lora:realisticVaginasGodPussy_godpussy2Innie:0.35><lora:breastinclassBetter_v14:0.2><lora:breastHelperBetaLORA_betaV2:0.2>) medium_tits,spread legs
I recommend to do a nude photo first. When you're happy about the nude section; drag the right generated image to the left inpaint area and inpaint the parts you want clothes on. Then you can use lingerie models and prompts to get what you want. Trying to get some part nude, some part clothes on is very hard, you need to do in two steps. Check civitai site for lingerie models, and click pictures to see what prompts they used for them.
hi i have question for boobs area, i use realistic vision20_v13 inpainting, whenever the breast are visible, the ribcage inbetween below boobs are very prominent. i also try use lora <lora:breastinclassBetter_v14:0.3><lora:breastHelperBetaLORA_betaV2:0.3>), it still there, how to make this ribcage less visible? any tips or some promt i miss with?
Hi, Im having this text when running the webui-user.bat
venv "G:\stable-diffusion-portable-main\venv\Scripts\Python.exe"
Python 3.10.9 (tags/v3.10.9:1dd9be6, Dec 6 2022, 20:01:21) [MSC v.1934 64 bit (AMD64)]
Commit hash: 5ab7f213bec2f816f9c5644becb32eb72c8ffb89
Traceback (most recent call last):
File "G:\stable-diffusion-portable-main\launch.py", line 352, in <module>
prepare_environment()
File "G:\stable-diffusion-portable-main\launch.py", line 257, in prepare_environment
run_python("import torch; assert torch.cuda.is_available(), 'Torch is not able to use GPU; add --skip-torch-cuda-test to COMMANDLINE_ARGS variable to disable this check'")
File "G:\stable-diffusion-portable-main\launch.py", line 120, in run_python
return run(f'"{python}" -c "{code}"', desc, errdesc)
File "G:\stable-diffusion-portable-main\launch.py", line 96, in run
raise RuntimeError(message)
RuntimeError: Error running command.
Command: "G:\stable-diffusion-portable-main\venv\Scripts\python.exe" -c "import torch; assert torch.cuda.is_available(), 'Torch is not able to use GPU; add --skip-torch-cuda-test to COMMANDLINE_ARGS variable to disable this check'"
Error code: 1
stdout: <empty>
stderr: Traceback (most recent call last):
File "<string>", line 1, in <module>
AssertionError: Torch is not able to use GPU; add --skip-torch-cuda-test to COMMANDLINE_ARGS variable to disable this check
Anyone can help me?
venv "G:\stable-diffusion-portable-main\venv\Scripts\Python.exe"
Python 3.10.9 (tags/v3.10.9:1dd9be6, Dec 6 2022, 20:01:21) [MSC v.1934 64 bit (AMD64)]
Commit hash: 5ab7f213bec2f816f9c5644becb32eb72c8ffb89
Traceback (most recent call last):
File "G:\stable-diffusion-portable-main\launch.py", line 352, in <module>
prepare_environment()
File "G:\stable-diffusion-portable-main\launch.py", line 257, in prepare_environment
run_python("import torch; assert torch.cuda.is_available(), 'Torch is not able to use GPU; add --skip-torch-cuda-test to COMMANDLINE_ARGS variable to disable this check'")
File "G:\stable-diffusion-portable-main\launch.py", line 120, in run_python
return run(f'"{python}" -c "{code}"', desc, errdesc)
File "G:\stable-diffusion-portable-main\launch.py", line 96, in run
raise RuntimeError(message)
RuntimeError: Error running command.
Command: "G:\stable-diffusion-portable-main\venv\Scripts\python.exe" -c "import torch; assert torch.cuda.is_available(), 'Torch is not able to use GPU; add --skip-torch-cuda-test to COMMANDLINE_ARGS variable to disable this check'"
Error code: 1
stdout: <empty>
stderr: Traceback (most recent call last):
File "<string>", line 1, in <module>
AssertionError: Torch is not able to use GPU; add --skip-torch-cuda-test to COMMANDLINE_ARGS variable to disable this check
Anyone can help me?
It's something GPU compatibility related. Read this: