do you have a vide I can follow?
do you have a vide I can follow?
Fi have this video for runpod
FYouTubeSECourses - Software Engineering Courses
RunPod: https://bit.ly/RunPodIO. Discord : https://bit.ly/SECoursesDiscord. How to install and start using #DreamBooth extension on #RunPod SD Web UI template. 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
DreamBooth extension: ht...
https://www.patreon.com/SECoursesDreamBooth extension: ht...
Kworks as a charm now 
thanks to you of course. 
thanks to you of course. 
Fif you support us on patreon i would appreciate very much
KWill do!
ZIt looks pretty close, but how can i fine tune it further? it's a lora extended model
Zi'm at around 220 epochs right now
Gthat is looking great
Zthank you
Zunfortunately she is very particular about features like the eyes n stuff
GHey all ! I made a very abrieviated version of the RunPod video. These are the steps I take to get the model training or started. These are not the perfect settings but you can edit the settings and keep them as a reference each time you use RunpPod.
GHope it helps
G@Furkan Gözükara SECourses on RunPod how can I open a terminal to see the progress of the training if I connect via tcp 3000
Gthe UI froze for me
Ahow do i uninstall sd? i want to change it's location and clear some space from my c drive, i will install it to another drive when i'll be getting my delivery of a new ssd
ZSome of my samples look just like my subject, and then 5 epochs later, i'll get sample images that don't look like her, what can i do to narrow in the accuracy?
GI feel the same
GI can't change the bacground of my iamges
GCan somebody drop their negative and positive promps here please
G@Furkan Gözükara SECourses I have it trained on my face really accuratly however I can't seem to change my background etc
Fhi everyone
GMy propts are not doing anything
GNo matter my prompt, my images don't change
SOvertrained - that happened to me.
SI wanna hook my SD install to my Discord. Has anyone ever done that? Is it even possible?
HNice. I started doing stuff like this in Notion
Qhello all. love the videos!
Zgot a strange error during training "Returning result: Exception training model: Inference tensors cannot be saved for backward. To work around you can make a clone to get a normal tensor and use it in autograd.
"
"
RI'm trying to install Stable Diffusion on my computer, I have followed all the steps carefully, but when I try to run it by clicking "webui-user.bat" the result is like this, and not as shown in the tutorial. anyone know what mistake i did? can anyone help me how to fix this?
Qhmm nvm i did. let me look whats diffrent with mine
Qit looks like your commit hash is none you try launch.py
Qyour missing the hash. it sohuld be Commit hash: a9fed7c364061ae6efb37f797b6b522cb3cf7aa2 or something
SHey i have a question I trying to train a checkpoint with dreambooth using the Realistic Vision V1.3 as the base model. What i am attempting to do is train the following yoga pose dataset https://www.kaggle.com/datasets/niharika41298/yoga-poses-dataset into realistic vision so the model will be able to generate people in various yoga poses. would I just download all the images and then label each of them with the selected pose? Any pointers or is there any resources available for me 2 look at for a task like this. Thank you
Qyou should look into controlnet posing with stable diff.
Qthere is a openpose editor
Q
SI can do it with controlnet no problem, but the application i am making I want to be able to generate these on demand
Qhmm sorry then i dont know how i can help you still learning alot with training my own models. if you found it out. i would love to hear it
Shoping the Dr. @Furkan Gözükara SECourses will have some insight on this. I have been watching his videos all day long today
Fyou cant. you have to kill initial one and start another terminal. still you can connect via 3000 port after that
Fjust delete entire folder do a fresh install . i explained in the beginning of this video : https://youtu.be/tXaQAkOgezQ
YouTubeSECourses - Software Engineering Courses
Discord : https://bit.ly/SECoursesDiscord. New fantastic style transfer feature via T2I-Adapter added to the #ControlNet extension. 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, #Automatic11...
https://www.patreon.com/SECoursesPlaylist of #StableDiffusion Tutorials, #Automatic11...
Fif you cant change background than you need to modify your training dataset and make different backgrounds
Fthat means model memorized them
Fhi welcome
Fit is easy with invoke ai
Fhello welcome and thanks
Fhappens when generating preview or after that?
Fhi welcome
Fwhen you type python to new cmd what do you get
Fprobably you need reguler dreambooth training