And should I use separate models? Or merge them after training?
And should I use separate models? Or merge them after training?
DAfter training, i am converting it to ckpt but then I can't download from g drive idk what's happening it keeps saying error when it's almost done, so i have downloaded the weights how do i convert them to ckpt?
DNo don't merge you will lose both, try to train the persons face and then a lora for clothes
DThen try to prompt them together
DYou can also do this with controlnet and inpainting but that's if the model and the clothes are already in a pose you need
KYouTubeTroubleChute
Nvidia has announced HUGE news: 2x improvement in speed for Stable Diffusion and more with the latest driver. Using it is a little more complicated, but the speed boost is there! Exciting things coming in the future of AI. This video covers installing and using the new ONNX/Olive models and converter, as well as converting models, generating ima...
Nthese?
Nstill not working :\
Bhi everyone! wanted to share a demo of running A1111 with a fal-serverless backend. The idea here is that you just run the UI locally but the GPU parts happen in the cloud. So instead of having a machine on all the time, you would only have a machine running when you are generating images which should save some $. Here is a video of it in action: https://www.youtube.com/watch?v=EIxF7TKk6wg
I am looking for feedback. Would you want to use this?
I am looking for feedback. Would you want to use this?
YouTubeFeatures and Labels
In this video we demonstrate a version of AUTOMATIC1111 StableDiffusion UI that runs in a serverless manner using fal-serverless.
AThis is really cool, will be nice if you can implement all the other tabs and especially add support for Dreambooth
Fnever tried
Ftrain cloth. train person. make cloth image. in paint person face
BCan do for sure
BWill start working on the other tabs, but wanted to see if there is enough interest in it first
ADefinitely, it will be very useful for people like me who run a Mac and don't have a proper GPU, I am using cloud services already anyway.
Ffrom video i dont see he managed to make it work am i mistaken?
F- gradient checkpoint
Ntried, still same ;-;
N
Fyou must be making error
Fi just made it work like yesterday on a patreon supporter pc
Fgtx 1080
Fbatch size is 1 right?
Ni'm also a patreon supporter 
Fmessaging you
Nyes
N
PI am getting the same error message with LDSR as I was having with controlnet, [urllib.error:urlopen error ssl certificate verify failed] I did not see any outgoing request through my firewall that was being blocked so I am not sure how to fix the issue. This is a fresh Windows 10 install with fresh Python 3.10.6 and freshAutomatic1111 dev build install on an Auros Master z590 with a 4090, 11700@4.9ghz, 128gb 3200 ram and a 2tb gen 4.0 NVME.
Nwhich?
Purllib.error:urlopen error ssl certificate verify failed
PThat's the last line of it in cmd prompt
Nhmm i think its the websites issue
PFixed it, for now.
The certifi certificate bundle for python 3:10 was outdated.
The certifi certificate bundle for python 3:10 was outdated.
PSave a new python file as test.py with the code from https://gist.github.com/marschhuynh/31c9375fc34a3e20c2d3b9eb8131d8f3
PCreate C:\Program Files\Common Files\ssl
Open cmd prompt as admin, navigate to the location you saved the test.py, (cd your test.py file location) then run python test.py.
Open cmd prompt as admin, navigate to the location you saved the test.py, (cd your test.py file location) then run python test.py.
Fwhat could happen if i'm getting
Couldn't find VAE named vae-ft-mse-840000-ema-pruned.safetensors; using None instead on loadFbut then i go settings, i select vae: "none", apply settings; then vae: "vae-ft-mse...", apply settings. and ...
Fi can select it in the settings but it's always giving error on starting
PDose anything happen that is problematic?
Pload this link https://huggingface.co/stabilityai/sd-vae-ft-mse-original/resolve/main/vae-ft-mse-840000-ema-pruned.safetensors
place the file downloaded from it in
\stable-diffusion-webui\models\VAE
place the file downloaded from it in
\stable-diffusion-webui\models\VAE
Fyeah i have that file there
Fthat's why i can load it with the settings, selecting it
Fbut if I restart a1111, it gives me the error over and over again
Fautomatic loading at start:
manual load via settings:
manual load via settings:
Fit doesn't make any sense xD
PI don't even have that VAE, is that for a specific model you have?
Fit's this one, you linked it
Fit's the generic vae from stabilityai
PSo you have a model that stated it requires it?
If not, it is not necessary for it to exist in the VAE folder.
If not, it is not necessary for it to exist in the VAE folder.
PI presume you downloaded a model that states that VAE is required for it to function.
Fno, but it improves quality