Error running install.py for extension extensions\sd_dreambooth_extension. Command: "B:\Apps\Stable

Error running install.py for extension extensions\sd_dreambooth_extension.
Command: "B:\Apps\Stable Diffusion\stable-diffusion-webui\venv\Scripts\python.exe" "extensions\sd_dreambooth_extension\install.py"

im getting this error from dreambooth new update

SSιɳɠυʅαɾ Sιɳɠυʅαɾιƚყ Error running install.py for extension extensions\sd_dreambooth_extension. Comma...

Trimac•3/23/23, 4:16 AM

Try back to previous state maybe restore point. Personally i dont update sd extensio if im having good results from current settings

TTrimac Try back to previous state maybe restore point. Personally i dont update sd exte...

Sιɳɠυʅαɾ SιɳɠυʅαɾιƚყOP•3/23/23, 4:17 AM

ok ill try

Trimac•3/23/23, 4:17 AM

Dreambooth still very unstable

blksage•3/23/23, 6:16 AM

Question. I want to make talking avatars, but D-ID and Pipio are too expensive to make the investment worth it. 15 minutes worth of vid for several dollars? Is there a better or at least cheaper alternative?

Garreth210•3/23/23, 10:24 AM

It seems like I am over training my model with my face and I am not sure how I can prevent this ?

TonyHalik•3/23/23, 11:33 AM

i have a question, if I want to train specific outfit, what class should i use in Class Prompt in Dreambooth?

Trimac•3/23/23, 12:14 PM

Anyone notice in generating images that nomatter how you replace your promts or even delete all text and replace new compostion, after web ui has been reset and still the composition and style always generates the same? something like your stuck on the same seed. How to totally get away with that?

GGarreth210 It seems like I am over training my model with my face and I am not sure how I c...

Trimac•3/23/23, 12:18 PM

Personaly i found a good results with the method of 16 images 768,High res, Lr 0.0001, constant, 100epoch.

Garreth210•3/23/23, 12:29 PM

Nice! I will give that a try

Garreth210•3/23/23, 12:29 PM

does anyone know where the sample imgaes get generated in RUnpod ?

Garreth210•3/23/23, 12:41 PM

Alright so I am not sure if I am doing this right. My CFG scale needs to be really low for my face to generate and even then it's not looking great

Garreth210•3/23/23, 12:44 PM

This is with the cfg scale on 1 and that is creepy AF but it's all warped

Garreth210•3/23/23, 1:29 PM

Alright. after some testing, the new version of Dreambooth seems to over train VERY quickly. 150 for the face seems way to much

Garreth210•3/23/23, 1:32 PM

when I go to checkpoint 2 it's already overtrained , no style and my face is not even correct . I do think I might be doing something wrong

Zono50•3/23/23, 1:32 PM

my model keeps getting tripped up and making pictures of the girls drink lmao

Zono50•3/23/23, 1:32 PM

EssaBalls•3/23/23, 1:34 PM

I trained my model in Textual Inversion on SD 2.1. Results were not that bad, but I decided to check SD 1.5 because I was able to do hypernetwork on sd 1.5 and not on 2.1. I used same images and filewords in 1.5 as I used in 2.1. My embeddings have comparable loss value every 500 steps. But it is learning bad. Samples are much worse than in 2.1. Any idea what options or anything that I can change to improve my results? I used 22 images maybe I need to use more?

Garreth210•3/23/23, 1:35 PM

this is the closest I can get my face into any image and then the ears, eyes and mustache is wrong

Garreth210•3/23/23, 1:40 PM

I look like a 50 year old here XD hahahah

Garreth210•3/23/23, 1:40 PM

I don't even have a mustache

Garreth210•3/23/23, 1:41 PM

All of this is on epoch 100 so I need to fine tune a little more . Not sure how

kicedz•3/23/23, 1:41 PM

Hello, it's me again.
I trained the model based on a cup, and it gave me pretty good sample images, but when prompted after training it doesn't give me the result i wanted. I used ohwx mug as a instance prompt and photo of ohwx mug as a sample image prompt

What have i done wrong ? Any ideas how to get the result from the training ?

Kkicedz Hello, it's me again. I trained the model based on a cup, and it gave me pretty...

Garreth210•3/23/23, 1:42 PM

what checkpoint are you using ?

kicedz•3/23/23, 1:42 PM

The ones nearest to the sample prompts in question.

kicedz•3/23/23, 1:44 PM

When Prompted in text2img (with the model at 3000 selected - due to best sanity result) with the keywords : photo of ohwx mug, it gives me random mug images. The gray mug is the image i used (total of 25 images), and it gave me pretty good results during training.

kicedz•3/23/23, 1:47 PM

Maybe the base model i used for training already used ohwx ? maybe that's the problem?

kicedz•3/23/23, 1:58 PM

As a base model i used Realistic Vision 1.3

Garreth210•3/23/23, 1:59 PM

Well here is my reference and the images I managed to generate, bare in mind that my settings seem to be VERY different to any video based on the latest Dreambooth

Garreth210•3/23/23, 1:59 PM

Garreth210•3/23/23, 2:00 PM

the CFG model is literally on 11 for most of these imgaes

kicedz•3/23/23, 2:00 PM

What did you use for the base model for training your images?

Garreth210•3/23/23, 2:06 PM

v1.5-pruned

Kkicedz Hello, it's me again. I trained the model based on a cup, and it gave me pretty...

Furkan Gözükara SECourses•3/23/23, 2:09 PM

no ideas. it should work as in sample prompts very weird

Furkan Gözükara SECourses•3/23/23, 2:09 PM

today

Furkan Gözükara SECourses•3/23/23, 2:09 PM

i will do a new training

Furkan Gözükara SECourses•3/23/23, 2:09 PM

for animation video

Furkan Gözükara SECourses•3/23/23, 2:09 PM

on latest version

Garreth210•3/23/23, 2:10 PM

Yes please. It would be great if you could dive into some of the settings . I feel the videos of 3 weeks ago are all already outdated. Dreambooth development is just moving at a very fast pace.

GGarreth210 Yes please. It would be great if you could dive into some of the settings . I fe...

Furkan Gözükara SECourses•3/23/23, 2:10 PM

actually my latest video just recorded few days ago

Garreth210•3/23/23, 2:11 PM

oh, I must have missed that one then

Furkan Gözükara SECourses•3/23/23, 2:11 PM

https://youtu.be/m-UVVY_syP0

YouTubeSECourses - Software Engineering Courses

Training Midjourney Level Style And Yourself Into The SD 1.5 Model ...

RunPod: https://bit.ly/RunPodIO. Discord : https://bit.ly/SECoursesDiscord. Get your own #Midjourney level model for free via Style Teaching. 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 #StableDiffusion Tutorials, Au...

Furkan Gözükara SECourses•3/23/23, 2:11 PM

it worked very well

Garreth210•3/23/23, 2:12 PM

oh, I saw this and did not watch it. I will for sure try refine my process with this

FFurkan Gözükara SECourses so you compared checkpoints?

Stevens•3/23/23, 2:15 PM

I did not understand this question I don't think.

FFurkan Gözükara SECourses no ideas. it should work as in sample prompts very weird

kicedz•3/23/23, 2:15 PM

is it maybe because i used Realistic Vision 1.3 instead of SDv1.5 model ?

SStevens I did not understand this question I don't think.

Furkan Gözükara SECourses•3/23/23, 2:28 PM

checkpoint comparison is most important part of training

Furkan Gözükara SECourses•3/23/23, 2:29 PM

please watch this video

Furkan Gözükara SECourses•3/23/23, 2:29 PM

https://youtu.be/Tb4IYIYm4os

YouTubeSECourses - Software Engineering Courses

Automatic1111 Stable Diffusion DreamBooth Guide: Optimal Classifica...

Sign up RunPod: https://bit.ly/RunPodIO. Our Discord : https://discord.gg/HbqgGaZVmr. New best training settings for DreamBooth training in Automatic1111 Web UI. 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 #StableDif...

Kkicedz is it maybe because i used Realistic Vision 1.3 instead of SDv1.5 model ?

Furkan Gözükara SECourses•3/23/23, 2:29 PM

if you are able to get during training you should be also get after training as well. but custom models usually not working well with training

EssaBalls•3/23/23, 2:44 PM

someone tested pytorch 2.0 with sd 1.5 textual inversion training?

Error running install.py for extension extensions\sd_dreambooth_extension. Command: "B:\Apps\Stable

Similar Threads