Software Engineering Courses (SECourses)•3y ago

"3000/tcp: 59" is what it said

DDavid Ce "3000/tcp: 59" is what it said

ashley•6/2/23, 9:33 PM

yes that means it killed it, so you can relaunch it now

David CeOP•6/2/23, 9:35 PM

Hmm, it still did the same thing

David CeOP•6/2/23, 9:37 PM

oh alright, thank you. Managed to get it sorted

SSequa https://i.imgur.com/CjS0jwN.png shouldn't this work as is? (google colab)

Sequa•6/2/23, 9:42 PM

was the revision/branch that needed to be changed, in case anyone else gets this

NNesith venv "E:\AI\stable-diffusion-webui\venv\Scripts\Python.exe" No Python at '"C:\Us...

Furkan Gözükara SECourses•6/2/23, 9:58 PM

do a new install. dont install via windows app store

DDavid Ce Hello, please how important is the availability of a private server on runpod

Furkan Gözükara SECourses•6/2/23, 9:58 PM

not much. you get sometimes out of gpu in anycase

SSequa https://i.imgur.com/CjS0jwN.png shouldn't this work as is? (google colab)

Furkan Gözükara SECourses•6/2/23, 9:58 PM

ye change revision to main not fp16

Sequa•6/2/23, 10:15 PM

https://i.imgur.com/t9mqKv5.png

Imgur

Sequa•6/2/23, 10:15 PM

just incredible with the A100

SSequa https://i.imgur.com/t9mqKv5.png

Furkan Gözükara SECourses•6/2/23, 10:20 PM

wow nice

Furkan Gözükara SECourses•6/2/23, 10:21 PM

i am making deepfake of shawshank redemption

Furkan Gözükara SECourses•6/2/23, 10:21 PM

will use nicolas cage :d

FFurkan Gözükara SECourses i am making deepfake of shawshank redemption

ashley•6/2/23, 10:22 PM

Best movie of all time

ashley•6/2/23, 10:23 PM

Wow, I wonder how long it is going to take the Dreambooth devs to fix that mess they made of the new release

Aashley Wow, I wonder how long it is going to take the Dreambooth devs to fix that mess ...

Furkan Gözükara SECourses•6/2/23, 10:47 PM

currently installing dev version to a client

FFurkan Gözükara SECourses currently installing dev version to a client

ashley•6/2/23, 10:48 PM

dev version works well for me, just haven't really got the Facebook D-Adaptation Optimizers to work yet

ashley•6/2/23, 10:49 PM

Release notes for Dreambooth say to set LR for D-Daptation Optimizers to 0.25, but Facebook says to said them it to 1

ashley•6/2/23, 10:50 PM

I am busy testing an update to my RunPod template to include Kohya_ss

Furkan Gözükara SECourses•6/2/23, 10:50 PM

there is something new : Dynamic Image Normalization

FFurkan Gözükara SECourses there is something new : Dynamic Image Normalization

ashley•6/2/23, 10:50 PM

What does this do?

Aashley What does this do?

Furkan Gözükara SECourses•6/2/23, 10:53 PM

new option just saw

Furkan Gözükara SECourses•6/2/23, 10:53 PM

says improves likeliness

Furkan Gözükara SECourses•6/2/23, 10:53 PM

man so many new stuff to test

ashley•6/2/23, 10:54 PM

Yeah too many settings

ashley•6/2/23, 11:01 PM

I made a script to get RunPod pricing, sorted by GPU VRAM from lowest to highest

Aashley I made a script to get RunPod pricing, sorted by GPU VRAM from lowest to highest

Furkan Gözükara SECourses•6/2/23, 11:18 PM

community 3090 really good

Furkan Gözükara SECourses•6/2/23, 11:18 PM

usually

FFurkan Gözükara SECourses community 3090 really good

ashley•6/2/23, 11:25 PM

Thanks for the tip, I usually use RTX A5000

ashley•6/2/23, 11:26 PM

Automatic1111 released version 1.3.1 yesterday, so rebuilding my Docker image

https://github.com/AUTOMATIC1111/stable-diffusion-webui/releases/tag/v1.3.1

GitHub

Release 1.3.1 · AUTOMATIC1111/stable-diffusion-webui

Features:

revert default cross attention optimization to Doggettx

Bug Fixes:

fix bug: LoRA don't apply on dropdown list sd_lora
fix png info always added even if setting is not enabled
fix s...

Furkan Gözükara SECourses•6/2/23, 11:27 PM

ashley•6/2/23, 11:27 PM

They seem to have constant issues with XYZ plot these days

Townie•6/3/23, 12:56 AM

Does anyone have a good link on how to create a model of something other than a person using Google Colab notebook?
I used the link in the description for this video https://www.youtube.com/watch?v=mnCY8uM7E50&t=3168
and i uploaded 20 photos like this and the model produce these 4 photos. I haven't been able to get Dreambooth to successfully train a model on my PC because my GPU is only 8gb of VRAM. Not sure what to do.

YouTubeSECourses

Transform Your Selfie into a Stunning AI Avatar with Stable Diffusi...

Our Discord : https://discord.gg/HbqgGaZVmr. How to do free Stable Diffusion DreamBooth training on Google Colab for free. If I have been of assistance to you and you would like to show your support for my work, please consider becoming a patron on

https://www.patreon.com/SECourses

Playlist of Stable Diffusion Tutorials, Automatic1111 and Goo...

TTownie Does anyone have a good link on how to create a model of something other than a ...

Furkan Gözükara SECourses•6/3/23, 1:22 AM

you have prompt error

Furkan Gözükara SECourses•6/3/23, 1:22 AM

you didnt change config correctly

FFurkan Gözükara SECourses i installed it on runpod yesterday.

Nom•6/3/23, 1:38 AM

how do you mean? Do you mean that you dont get error using class images?

Just to clarify I have been using @ashleyk template mentioned here qwen-flux-wan-such and in that version of dreambooth, it errors out when you have classification images > 0

FFurkan Gözükara SECourses do a new install. dont install via windows app store

Nesith•6/3/23, 6:24 AM

what version should i get , 3.10.11?

Nesith•6/3/23, 6:30 AM

still the same , idk why

Nesith•6/3/23, 6:38 AM

julius•6/3/23, 6:56 AM

@Dr. Furkan Gözükara I'm curious after watching a few of your tutorials – what do you currently recommend as the best way to train a model to generate super realistic portraits of yourself? Kohya LoRA? Automatic1111 UI?

julius•6/3/23, 6:57 AM

I'm using a macbook, so currently using rundiffusion.com to be able to generate images. I've been using the popular Google Colab "TheLastBen" to train my dreambooth models previously. It works great thb, but a bit inconsistent, especially now as I started experimenting generating photos for other people

NNesith Click to see attachment

The Elessar [OBOI]•6/3/23, 8:58 AM

hello, this happens because you used the version supplied by the microsoft store. you should download and install the version available through python.org

The Elessar [OBOI]•6/3/23, 8:58 AM

https://www.youtube.com/watch?v=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...

DDavid Ce Hey, please after launching relauncher.py on the terminal of the jupyter noteboo...

Shubham Agnihotri•6/3/23, 9:32 AM

change the port, or a restart will help as there is some application still running on this port

Aashley run in terminal: ```fuser -k 3000/tcp```

Shubham Agnihotri•6/3/23, 9:32 AM

killing the task at this port also works

Jjulius @Dr. Furkan Gözükara I'm curious after watching a few of your tutorials – what d...

Shubham Agnihotri•6/3/23, 9:34 AM

I feel Dreambooth gives the best accuracy, so if you got money, or good pc which means the same, if you got money, dreambooth will give the best results followed by Kohya and lora pretty much at the same level.. It is my experience

SShubham Agnihotri killing the task at this port also works

ashley•6/3/23, 9:36 AM

Takes more effort and more commands to detemine the process id and then to kill it

Shubham Agnihotri•6/3/23, 9:36 AM

restart the PC, the best option.. then

ashley•6/3/23, 9:36 AM

Also if Web Ui crashes during training, there will be multiple process ids to kill, so this command is better.

SShubham Agnihotri restart the PC, the best option.. then

ashley•6/3/23, 9:37 AM

For Windoews, Linux is not garbage like Windows

"3000/tcp: 59" is what it said

Similar Threads