Layer Diffuse in Forge WebUI & ComfyUI
HTML-код
- Опубликовано: 13 май 2024
- Stable Diffusion normally doesn't make transparent PNGs, but now you can thanks to Layer Diffuse!
Available for both Forge WebUI and ComfyUI, Layer Diffuse does much more than just create single images without backgrounds too.
Links:
github.com/huchenlei/ComfyUI-...
github.com/layerdiffusion/sd-...
== More Stable Diffusion Stuff! ==
* Faster Stable Diffusions with the LCM LoRA - • LCM LoRA = Speedy Stab...
* How do I create an animated SD avatar? - • Create your own animat...
* Installing Anaconda for MS Windows Beginners - • Anaconda - Python Inst...
* Add anything to your AI art in seconds - • 3 Amazing and Fun Upda...
* Video-to-Video AI using AnimateDiff - • How To Use AnimateDiff...
* One image Gets You a Consistent Character in ANY pose - • Reposer = Consistent S...
Want to support the channel?
/ nerdyrodent - Наука
How are you planning to use layer diffuse!?
Onions! (I'll see myself out)
Very carefully and graciously😅 top video btw
Animation, creating the background separately and animate it with svd xt, then creating a starting frame of character and animate it with animate anyone or animatediff while use of layer diffusion to create the "sprites" animation and insert it manually in DaVinci resolve, or inserting them with inpaint controlnet.....maybe a lot of work, and bugs and tears but all are the steps for ai movies
I had been trying for hours to get this to work. After manually downloading all the models and trying different things I finally shut down Forge and tried the "Update" batch file. That did the trick! I'm posting this in case anyone else have had trouble getting this to work for them and haven't tried launching the Update.bat file.
Man I've been struggling for hours. Was just about to give up before seeing your comment. Cheers, thank you so much.
@@abbeyroad.34 You're welcome! I'm glad my comment helped. I figured if I had trouble with it, someone else might have trouble too. 😄
I usually manually remove background and generate characters separately so this should help me quite a bit.
I am just waiting for a completely Layer Based workflow now.
If this is possible and inpaint and outpaint are already present.
nothing is stopping someone from making a full fledged layer based UI like Photoshop.
Image composition has been made so much easier by this.
Best place to ask for this is krita ai diffusion
Factual statement.
Yeah that pull request has been sitting for a week now. I wound up just checking out the PR commit, works well for those of us that like to generate forever overnight and see what generates.
woah super amazing, until now I just had been using some chroma green key for the backs and maybe some online background removal tool, but this is just what i needed :)
This is a revolution 😮🎉
Every day you make a new video, you make my day a happier one! ^_^
Yeah, the one for SD 1.5 it's already out! :D
My first time here, subbed already...just keep making quality contents
Welcome aboard!
THX again man :) very interesting and useful as always...
TypeError: 'NoneType' object is not iterable
I am expecting it to be compatible with ControlNet adapter. this error shows up when I turn on it
funny installed it yesterday and love using it :D
That looks useful. Thanks
It is!
Nerdy!!
that's epic
which are the diffusers that I need installed to use this layer diffusion nodes? thanks.
woow 😀
it creates an emoty folder...Got the option in UI but no models. How do I fix this?
does this work with image to image? making game sprites from renders would be interesting.
how do i get Deforum to work with Forge? please
It doesn't seem to work with a Lightning model hmm
so uninstall a1111 for forge altogether ?
Nice plugin but a pain to upscale, in forge hiresfix doesn't work if you try to use it after a lowres generation and if you tick the hiresfix box and upscale all at one time, it messes with the transparency, utlimate SD upscale in img2img remove the transparency too
Mine installed normal, but not generating 2 images...
I love how if I stop following advancements with stable diffusion for a few days I miss out on multiple new features.
I wonder when Adobe are going to join the game 🤔
Thank you for the valuable lesson. Like and subscribe :). If it's not too much trouble, show me how you installed SadTalker on your Forge?
Possible to get an install guide for Comfyui's Insightface? I'm trying to do the Face ID in the Krita plugin & it seems very complicated for a Custom Comfyui (non-portable) version. 🐭
Unfortunately, anything related to insight face is not for commercial use
So this doesnt work in AUTO1111? couldnt find the extension there
This would have been great in 1996 when I wrote my first html and needed custom transparent .gif files. A bit late, I guess.
Better late than never! ;-)
a1111?
where is the /temp/gradio folder? I've tried and failed to find it.
I found it thanks.