I can confirm that this works, I have used the process once or twice for 'educational' purposes. I also do the exact opposite and use AI to clothe naked JAV girls in panties
Photorealistic AI Generated Images
- Thread starter SUNBO
- Start date
-
Akiba-Online is sponsored by FileJoker.
FileJoker is a required filehost for all new posts and content replies in the Direct Downloads subforums.
Failure to include FileJoker links for Direct Download posts will result in deletion of your posts or worse.
For more information see this thread.
#fluff
Some random images from the new W.I.P. checkpoint I'm building:
Some random images from the new W.I.P. checkpoint I'm building:
Created these last month and forgot to post. Also tried my hand at LTX Video using ComfyUI. Didn't put sound in it. A string of 5sec clips. It's a safe link to a Mega.nz file.
(stream - the action resolution is 1024x576 but since HTML isn't allowed I can't use the Mega provided embed code for the correct size)
(stream - the action resolution is 1024x576 but since HTML isn't allowed I can't use the Mega provided embed code for the correct size)
thank you so much . i dont know how he can do it
i try to do with fluck inpaint and its funny lol
Attachments
I need to get stuck into Comfyui but it's a bit terrifying to look at compared to Flux or EasyDiffusion. The fact you can use Comfy to create videos may be deal clincher.Created these last month and forgot to post. Also tried my hand at LTX Video using ComfyUI. Didn't put sound in it. A string of 5sec clips. It's a safe link to a Mega.nz file.
#fluff
Created with Forge & lusterij_no1 checkpoint. Character, clothing etc from my own loras
Created with Forge & lusterij_no1 checkpoint. Character, clothing etc from my own loras
I've only used ComfyUI for videos, I'm still stuck on Automatic1111 for image generation. Once you get nodes for different Workflows to try installed and get to understand the various available models and their sizes, strengths, and limitations (plus ALL the many settings tweaks) it is so much fun experimenting. But unless you have a super strong box be prepared to wait a lot. I, myself, have a 3060 GPU with 12GB of VRAM and 32GB of RAM, so for me it does take at least 4 minutes per generation or more depending on the Workflow and model.
I have a very similar setup, gave Comfy another look yesterday After spending 25 minutes trying to get the bugger installed I quit and went back to Forge.
I suspect I'll move to Comfy at some point, but not just yet
Still using A1111? Why? Forge works the same, looks the same, but runs like 35–40% faster. What's keeping you on A1111?
I struggled with installing Comfy too, but finally got it working on the third try.I have a very similar setup, gave Comfy another look yesterday After spending 25 minutes trying to get the bugger installed I quit and went back to Forge.
I suspect I'll move to Comfy at some point, but not just yet
If you’re into video generation, it’s definitely a must-have.That said, I still use Forge for images to this day. If you just want to polish a single image to perfection, I find Forge much more comfortable and intuitive.
But for automating complex workflows, Comfy really shines. Just takes some getting used to.
First thing I learned on i guess
EDIT! I'm embarrassingly confused now. It certainly looks like I'm using Automatic1111 but my shortcut points to:
C:\GEN\webui_forge_cu121_torch231\run.bat
run.bat
@echo off
call environment.bat
cd %~dp0webui
call webui-user.bat
webui-user.bat
@echo off
set PYTHON=
set GIT=
set VENV_DIR=
set COMMANDLINE_ARGS= --theme dark
@rem Uncomment following code to reference an existing A1111 checkout.
@rem set A1111_HOME=Your A1111 checkout dir
@rem
@rem set VENV_DIR=%A1111_HOME%/venv
@rem set COMMANDLINE_ARGS=%COMMANDLINE_ARGS% ^
@rem --ckpt-dir %A1111_HOME%/models/Stable-diffusion ^
@rem --hypernetwork-dir %A1111_HOME%/models/hypernetworks ^
@rem --embeddings-dir %A1111_HOME%/embeddings ^
@rem --lora-dir %A1111_HOME%/models/Lora
git pull
call webui.bat
EDIT AGAIN! I think I am using Forge...
Last edited:
What I imagine the casting couch would look like for the future release of BOBB-999 from ABC Art Body Collection
Tryouts here!
Tryouts here!
I'll give Comfy a proper look this weekend, (finally got it to install), I may swing back here for tips on animations if it all goes well