I have this same issue even though the file exists, probably a bug in A1111
I have this same issue even though the file exists, probably a bug in A1111
Fi see. we're mates in bugs Xd
AMaybe we should see if the .ckpt version works
Pcould be, I don't know being I don't use VAE files unless a model specifically requires it and 99% of any model worth using has it baked in now days.
Fi think it's a bug because i'm using the dev branch, so this things are common from time to time
Fit was working fine before, with the safetensors
AI am not even using dev branch, I am using main branch
Foh, i'm using dev
ASo if it is a bug, its been there for a while then
Pboth have bugs dev just has "some" of them resolved.
Fit appeared to me today
Fyesterday it was fine
Pdid you update A1111?
FGitHub
Is there an existing issue for this? I have searched the existing issues and checked the recent builds/commits What happened? I always get an IndexError while applying cross attention optimization ...
MCan you help me with this error?
Fthere it is
Fdownload the model again
PWhat UI is that?
Fnmkd gui
Fit's the biggest font on the capture xd
MDr. Furkan Gözükara introduced me to pix 2 pix, but I still haven't succeeded
Fuse automatic1111
Fit can pix2pix too
PI wouldn't be surprised if the UI was the issue and not the model.
AHappens with the ckpt version too:
Mhow is it possible In the past telling me that feature has had problems and caused me to delete the whole app once which caused a lot of damage, is there an update?
Fyeah, it's reported already on github
Pto automatic1111? the updates never end...
Fcaused you a lot of damage to remove a folder?
Fpix2pix works fine on automatic1111
F
Fit just kinda sucks
Fbut that's pix2pix
Ndaymm
Ncan it also make me look slimmer lol
Fanybody got any ideas? i'm trying to use kohya for the first time and i've got it getting this far, but for the life of me i can't figure out why it stops here. Left it on all night to see if it would get past this point but it doesn't. It seems to just be not active and stopped without any error message. I can even do other stuff in the GUI and the terminal reports progress on that, so it's not engaged with the training and this is just the last line printed by the process
Fdont mind my ugly transparent terminal background
BAs a work around you could try adding a cmd line param to the webui-user.bat on windows set COMMANDLINE_ARGS=X:\\path_to_file\\vae-ft-mse-840000-ema-pruned.safetensors
Fi've been seeing that error a lot lately in automatic1111's webui. i go into settings and select my vae again and it loads fine
Fthink it's a bug in the startup code and most people don't notice it because generations still work
Ndoes anyone know how much wound it cost me if I use stablediffusion finetuning (say 15 training images) on amazon sagemaker
AI haven't used sagemaker, usually just use a g5.2xlarge spot EC2 instance
AI have Python code to calculate a bid price for a spot instance, and terraform code to launch an instance here: https://github.com/ashleykleynhans/stable-diffusion-terraform
GitHub
Create an AWS EC2 GPU Spot Instance to Run Stable Diffusion WebUI and DreamBooth using Terraform - GitHub - ashleykleynhans/stable-diffusion-terraform: Create an AWS EC2 GPU Spot Instance to Run St...
NOo
Nhow much does it cost for g52xlarge for your usecase'
Nthanks
Ahaha i dont know enough about comp sci. But the idea that software is the roadblock and not hardware was interesting for LLMs that run on GPUs that aren't NVIDIA
Θis this better thatn automatic1111 webui?
MNo . Unfortunately, I haven't been able to get any of them working yet
Θbro no facking