you could use sd 2.1 to generate them
you could use sd 2.1 to generate them
F
Fsd 2.1
Fvery interestingly this model is putting a noise color to images
F
F
Fthis exists in majority
F
Fbut the variety of the model excellent
Finteresting fp32 version dont have that
MCan you create an advanced dreambooth video for classification.
I know the video with ohwx man.
I mean a new one where it learns "jumping man mid air towards a hanging rope on the moon" kind of thing.
So how it not only learns a new dataset like a face and adapt the rest it, but also a whole new situation where the rest of dataset can adapt to - while learning multiple new keywords at the same time(is that even possible?).
And the last thing is classification images - if I have a "jumping man towards a hanging rope" - image(like indiana jones) can I create a textfile with the same name as the image, with the keywords for that image? if yes, how do i tell sd to use that textfile - and many other files too(maybe even classification by folder structure? /jumping/man/rope/indianajones001.jpg).
Can I only train the same keywords, so like only "jumping man towards a hanging rope" or can I also mix it with images of only "jumping man", "rope", "jumping man on on the moon"...
I hope the explanation is clear enough. Because I was struggling to find pictures for a situation and in detail classify it (do I use ohwx jumping man, or use the full description for that photo).
To know and understand this would boost my ability to use sd 100x better
I know the video with ohwx man.
I mean a new one where it learns "jumping man mid air towards a hanging rope on the moon" kind of thing.
So how it not only learns a new dataset like a face and adapt the rest it, but also a whole new situation where the rest of dataset can adapt to - while learning multiple new keywords at the same time(is that even possible?).
And the last thing is classification images - if I have a "jumping man towards a hanging rope" - image(like indiana jones) can I create a textfile with the same name as the image, with the keywords for that image? if yes, how do i tell sd to use that textfile - and many other files too(maybe even classification by folder structure? /jumping/man/rope/indianajones001.jpg).
Can I only train the same keywords, so like only "jumping man towards a hanging rope" or can I also mix it with images of only "jumping man", "rope", "jumping man on on the moon"...
I hope the explanation is clear enough. Because I was struggling to find pictures for a situation and in detail classify it (do I use ohwx jumping man, or use the full description for that photo).
To know and understand this would boost my ability to use sd 100x better
Fthose are limited by the 512 px model
Fdistant shots
Fbut i am working on something new
NThank you Sir! I just wanted to know to generate those realistic images as seen in kohya LoRa should I use realisticv20 for training in dreambooth? Also is there a way to generate full body images, I tried full body but then it messes up the face.
Thank you so much. I really like your videos and instructions.
Thank you so much. I really like your videos and instructions.
Fi am working on a new workflow
Fi hope it will make full body better
Nvenv "E:\AI\stable-diffusion-webui\venv\Scripts\Python.exe"
No Python at '"C:\Users\user\AppData\Local\Microsoft\WindowsApps\PythonSoftwareFoundation.Python.3.10_qbz5n2kfra8p0\python.exe'
Press any key to continue
No Python at '"C:\Users\user\AppData\Local\Microsoft\WindowsApps\PythonSoftwareFoundation.Python.3.10_qbz5n2kfra8p0\python.exe'
Press any key to continue
Ni already check the directory and python.exe was there
Ni dont know why this happed suddenly . i was working fine before , i re-installed python but still the same.
DHello, please how important is the availability of a private server on runpod
SImgur
Sgetting the following error: "Revision Not Found for url:
https://huggingface.co/SG161222/Realistic_Vision_V2.0/resolve/fp16/model_index.j
son.
Invalid rev id: fp16"
https://huggingface.co/SG161222/Realistic_Vision_V2.0/resolve/fp16/model_index.j
son.
Invalid rev id: fp16"
AWhat do you mean by this?
Don some of them it says, low availability and high availaility
DLow availability gpu servers can be taken?
AYes, once you have one its yours, just means you might not get one.
DHey, please after launching relauncher.py on the terminal of the jupyter notebook I keep getting these errors. What can I do to fix it Sir
Arun in terminal:
D"Specified filename tcp/3000 does not exist". is what it says
ASorry made a mistake, check my edited message above
D"3000/tcp: 59" is what it said
Ayes that means it killed it, so you can relaunch it now
DHmm, it still did the same thing
Doh alright, thank you. Managed to get it sorted
Swas the revision/branch that needed to be changed, in case anyone else gets this
Fdo a new install. dont install via windows app store
Fnot much. you get sometimes out of gpu in anycase
Fye change revision to main not fp16
S
Sjust incredible with the A100 
Fwow nice
Fi am making deepfake of shawshank redemption
Fwill use nicolas cage :d
ABest movie of all time 
AWow, I wonder how long it is going to take the Dreambooth devs to fix that mess they made of the new release 
Fcurrently installing dev version to a client
Adev version works well for me, just haven't really got the Facebook D-Adaptation Optimizers to work yet 
ARelease notes for Dreambooth say to set LR for D-Daptation Optimizers to 0.25, but Facebook says to said them it to 1 
AI am busy testing an update to my RunPod template to include Kohya_ss
