Software Engineering Courses (SECourses)•3y ago

is it possible to batch sd upscale a folder of images but with different prompts ? as if you were to

is it possible to batch sd upscale a folder of images but with different prompts ? as if you were to load the image in to png info , send to img2img and sdupscale using prompt from png info , but in a batch process?

JJcs Hey! Love the tutorials. Im getting stuck at generating images in Automatic1111 ...

Furkan Gözükara SECourses•5/3/23, 7:40 PM

yes you can reduce vram usage greatly

Furkan Gözükara SECourses•5/3/23, 7:40 PM

first try

Furkan Gözükara SECourses•5/3/23, 7:40 PM

--medvram

--medvram

Furkan Gözükara SECourses•5/3/23, 7:40 PM

if still not works add

--lowvram

--lowvram

Furkan Gözükara SECourses•5/3/23, 7:40 PM

don't forget to use

--xformers

--xformers

too

Furkan Gözükara SECourses•5/3/23, 7:40 PM

thee are all command line arguments

TTheRustingDeadAdmin Koyha ss from this video. https://www.youtube.com/watch?v=TpuDOsuKIBo&loop=0 Ge...

Furkan Gözükara SECourses•5/3/23, 7:41 PM

what options have you picked? exactly as me?

Ddave5555 is it possible to batch sd upscale a folder of images but with different prompts...

Furkan Gözükara SECourses•5/3/23, 7:41 PM

no idea about this if there is such extension or not :/

Furkan Gözükara SECourses•5/3/23, 7:45 PM

i am working on high quality sorting algorithm of generated images tutorial

Furkan Gözükara SECourses•5/3/23, 7:45 PM

so lets say you generated 3000 images of your self

Furkan Gözükara SECourses•5/3/23, 7:45 PM

AI will sort them based on your training dataset similarity

FFurkan Gözükara SECourses what options have you picked? exactly as me?

TheRustingDeadAdmin•5/3/23, 7:56 PM

yes exact same

Hiccup•5/3/23, 7:57 PM

has anybody had the no module named clip

Hiccup•5/3/23, 7:57 PM

bard says its cuz i dont have it installed but my computer says it is installed and its in my path

Hiccup•5/3/23, 8:02 PM

okay so i put clip into venv and i guess it fixed that

Hiccup•5/3/23, 8:04 PM

it loaded but it says a bunch of modules are missing

Hiccup•5/3/23, 8:04 PM

where exactly does venv install all this stuff from

Hiccup•5/3/23, 8:06 PM

so the module was in my python install path but it apparently didnt pull it from there

Hiccup•5/3/23, 8:07 PM

well i fixed it i guess

Hiccup•5/3/23, 8:08 PM

dont think its a perminate fix

Hiccup•5/3/23, 8:25 PM

i moved my python path from user variables to system variables and i think that fixed it

Hiccup•5/3/23, 8:28 PM

as im the only user on this computer i dont know why user variables are even on here

Hiccup•5/3/23, 8:32 PM

if i didnt have the brain of a goldfish my life would be so much better

Hiccup•5/3/23, 8:33 PM

lol i start trouble shooting and then i go down paths and forget what im troubleshooting

Hiccup•5/3/23, 8:33 PM

my real life ram is very limited

Hiccup•5/3/23, 8:35 PM

i cant wait for brain implants

TheRustingDeadAdmin•5/3/23, 8:55 PM

which cuda version is best for dreambooth rn?

HHiccup has anybody had the no module named clip

Furkan Gözükara SECourses•5/3/23, 9:06 PM

you can make venv and install things there

Furkan Gözükara SECourses•5/3/23, 9:06 PM

best way

TTheRustingDeadAdmin which cuda version is best for dreambooth rn?

Furkan Gözükara SECourses•5/3/23, 9:06 PM

latest works

Furkan Gözükara SECourses•5/3/23, 9:06 PM

latest cuda and xformers work

TheRustingDeadAdmin•5/3/23, 9:15 PM

Not having luck with any, you are on 12.1?

TheRustingDeadAdmin•5/3/23, 9:15 PM

cuda

FFurkan Gözükara SECourses you can make venv and install things there

Hiccup•5/3/23, 9:18 PM

I solved the issue installing to venv works but it's not a permanent solution having python path setup correctly in system i think is a more permanent solution

TheRustingDeadAdmin•5/3/23, 9:20 PM

changing [optimizer] from AdamW8bit to AdamW solved my issue

Hiccup•5/3/23, 9:21 PM

What do those reducing vram commands actually do?

Hiccup•5/3/23, 9:21 PM

I mean i have vram available i just want it to use the right amount

HHiccup I solved the issue installing to venv works but it's not a permanent solution ha...

Furkan Gözükara SECourses•5/3/23, 9:22 PM

yep. i explained that in this video : http://youtu.be/B5U7LJOvH6g

YouTubeSECourses

How To Install Python, Setup Virtual Environment VENV, Set Default ...

How to install Python, have multiple Python installations, set system wide default Python version. How to compose venv for any Python installation, change Python default path, and install SD web UI properly. Discord: https://bit.ly/SECoursesDiscord.

If I have been of assistance to you and you would like to show your support for my work, please...

TTheRustingDeadAdmin changing [optimizer] from AdamW8bit to AdamW solved my issue

Furkan Gözükara SECourses•5/3/23, 9:23 PM

what was your issue

HHiccup I mean i have vram available i just want it to use the right amount

Furkan Gözükara SECourses•5/3/23, 9:23 PM

use them only if you get out of memory error

FFurkan Gözükara SECourses use them only if you get out of memory error

TheRustingDeadAdmin•5/3/23, 9:24 PM

Error no kernel image is available for execution on the device at line 167 in file D:\ai\tool\bitsandbytes\csrc\ops.cu

Hiccup•5/3/23, 9:24 PM

What do they actually do though? Like does it just push it to cpu or what?

Hiccup•5/3/23, 9:24 PM

Does it slow generations down?

edroh•5/3/23, 9:39 PM

hi, so i followed some of the tutorials and was able to manage to train stable diffusion on myself and got some safetensors from it to use. however, I'm wondering if i can somehow manage to integrate this model with some civit.ai anime model to create anime versions of myself using the civit anime model? Or is providing my own style images the only way to do so after? Sorry kinda new to this whole stable diffusion thing.

TheRustingDeadAdmin•5/3/23, 10:02 PM

from nvidia documentation "For best performance, the recommended configuration is cuDNN 8.9.0 on H100 with CUDA 12.0, and cuDNN 8.9.0 on all other GPUs with CUDA 11.8, because this is the configuration that was used for tuning heuristics." seems like cuda 11.8 is best for now unless you have the h100

TheRustingDeadAdmin•5/3/23, 10:03 PM

https://docs.nvidia.com/deeplearning/cudnn/support-matrix/index.html

Support Matrix :: NVIDIA cuDNN Documentation

These support matrices provide a look into the supported versions of the OS, NVIDIA CUDA, the CUDA driver, and the hardware for the NVIDIA cuDNN 8.9.0 release.

FFurkan Gözükara SECourses Download link already in gist file

dst19•5/3/23, 10:16 PM

I wanted a trained file to play around with and see it's photorealism before deep diving into training it myself. Do you have any trained models? I can't see any links to trained models on your method

Eedroh hi, so i followed some of the tutorials and was able to manage to train stable d...

Furkan Gözükara SECourses•5/3/23, 10:29 PM

yes workflow is same

Furkan Gözükara SECourses•5/3/23, 10:29 PM

instead of base model use anime model

TTheRustingDeadAdmin from nvidia documentation "For best performance, the recommended configuration i...

Furkan Gözükara SECourses•5/3/23, 10:29 PM

thanks .

is it possible to batch sd upscale a folder of images but with different prompts ? as if you were to

Similar Threads

Similar Threads

Similar Threads