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
Θway
Θwhat gpu do you have?
MI have a strong system. My problem is something else
ΘInstall Python 3.10.6
Θthis is very important
MMy English is poor . I could not convey my wish
I have thousands of low quality photos that I want to bring to the highest level of quality in detail, but the images do not change
I have thousands of low quality photos that I want to bring to the highest level of quality in detail, but the images do not change
MThe client did not accept me. He said his face has changed
Θ@majidzendaniyan lower the denoising strength
Θdisable Restore Faces
MIn this case, it does not give me quality with these details, Something that makes me excited and satisfied. There are unique details of hair and skin texture
Fthis isn't THAT specifically important. More importantly is that python 3.11.x isn't used. I had kernel issues doing AI using 3.10.6. A couple people helping me insisted that i used that to solve all my problems, so i downgraded from 3.10.9 to 6 and it actually started causing me hard system crashes. I suspect it was to do with incompatibilities between windows 11 on alderlake, and python but i never explored those suspicions. what i know is that the hard kernel problems go away when i changed python versions to a newer 3.10.9. i may upgrade to whichver the new 3.10.x is soon.
Θmine wouldnt run if python wasnt exactly 3.10.6
Fmine would run, but slowly, and then crash after a few staggery generations. i have alderlake and 4080 on newest OS. so we might have different needs. It may be a good suggestion for some people though right?
LIs there a way I can have SD start with specific settings already entered for the inpainting section of img2img? I pretty much always use the same prompt, sampler, CFG scale, denoise strength resolution, etc.
LAlso, is there a way I can start SD without internet?
Nstable diffusion is making my face wide, does anyone know how to make it squeeze?
Nnvm let me try randomizing seed