Software Engineering Courses (SECourses)•3y ago

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

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 ?

kicedzOP•3/23/23, 1:42 PM

The ones nearest to the sample prompts in question.

kicedzOP•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.

kicedzOP•3/23/23, 1:47 PM

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

kicedzOP•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

kicedzOP•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 I feel the videos of 3 weeks ago are all already outdated.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

kicedzOP•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?

EEssaBalls someone tested pytorch 2.0 with sd 1.5 textual inversion training?

Furkan Gözükara SECourses•3/23/23, 2:48 PM

i havent yet

Furkan Gözükara SECourses•3/23/23, 2:48 PM

currently working on animation

Furkan Gözükara SECourses•3/23/23, 2:48 PM

frames extracted

Furkan Gözükara SECourses•3/23/23, 2:48 PM

EssaBalls•3/23/23, 2:50 PM

Nice

EssaBalls•3/23/23, 2:51 PM

To intall pytorch from scratch all I have to do is delete venv folder and open webui-user.bat right?

EssaBalls•3/23/23, 2:51 PM

and it will install

EEssaBalls To intall pytorch from scratch all I have to do is delete venv folder and open w...

Furkan Gözükara SECourses•3/23/23, 3:01 PM

yes that will downgrade

Furkan Gözükara SECourses•3/23/23, 3:01 PM

install default version from scratch

EssaBalls•3/23/23, 3:06 PM

I should train embedding with hypernetwork added to the model, or not?

EssaBalls•3/23/23, 3:07 PM

I think i should not, but I just want to be sure

EEssaBalls I should train embedding with hypernetwork added to the model, or not?

Furkan Gözükara SECourses•3/23/23, 3:44 PM

hypernetwork is different i think it also requires a lot of hyper parameter tuning

FFurkan Gözükara SECourses Click to see attachment

felixsanz•3/23/23, 4:24 PM

training inception

Ffelixsanz training inception

Furkan Gözükara SECourses•3/23/23, 5:51 PM

i am doing experimental stuff lets see how it goes

Zono50•3/23/23, 6:03 PM

auto111 lora lion, i can't get my model to look like my subject

ZZono50 auto111 lora lion, i can't get my model to look like my subject

Furkan Gözükara SECourses•3/23/23, 6:14 PM

i didnt test lora yet

Furkan Gözükara SECourses•3/23/23, 6:14 PM

today i will do another dreambooth hopefully

Lorphos•3/23/23, 6:22 PM

hi, i am looking at the Lora + Dreambooth video and when starting automatic1111 it complains about libnvinfer missing

Lorphos•3/23/23, 6:24 PM

here is the complete error message:
2023-03-23 18:03:19.866094: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer.so.7'; dlerror: libnvinfer.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /workspace/stable-diffusion-webui/venv/lib/python3.10/site-packages/cv2/../../lib64:
2023-03-23 18:03:19.866207: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer_plugin.so.7'; dlerror: libnvinfer_plugin.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /workspace/stable-diffusion-webui/venv/lib/python3.10/site-packages/cv2/../../lib64:
2023-03-23 18:03:19.866225: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Cannot dlopen some TensorRT libraries. If you would like to use Nvidia GPU with TensorRT, please make sure the missing libraries mentioned above are installed properly.

Lorphos•3/23/23, 6:27 PM

do i just need to do "pip install tensorrt"?

LLorphos hi, i am looking at the Lora + Dreambooth video and when starting automatic1111 ...

Furkan Gözükara SECourses•3/23/23, 6:29 PM

you are on runpod right

Furkan Gözükara SECourses•3/23/23, 6:29 PM

did you follow this video?

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

Similar Threads

Similar Threads

Similar Threads