any issue with using xformers 0.0.16? i'm on whatever build comes through auto1111 when you do git p
any issue with using xformers 0.0.16? i'm on whatever build comes through auto1111 when you do git pull
Ican't say anything about local installs of a1111 but on runpod xformers 0.16 do not work...
Ialso on the DB github wiki they say only 14 are supposed to work
IGitHub
Contribute to d8ahazard/sd_dreambooth_extension development by creating an account on GitHub.
Aoh for dreambooth
Fye that is why. dreambooth is not compatiable with above 14 i think.not sure for 15 though
F
Fnow i will try different prompts to beautify
F
Fcoma difference
F
Fwith comma
F
Cwell, I am on TI aswell... today I have tried the newest extension custom-diffusion-webui but the girl is not my friend. I couldnt make it working.
On TI the best is to have a setup of good images without the background ("delete" it with paint), some people uses this in the captions "a photo of a man as [name]" and this 0.005:25, 0.001:250, 0.00001 with batch 4 and worked... but not perfect. It depends on the model used afterwards. Protogen doesnt make it perfect... I prefer 2.1 or 1.5... or maybe is the setup of the pictures? I dunno, I just wanted to share with you my little aknowledge, hope it helps. Any thoughts?
On TI the best is to have a setup of good images without the background ("delete" it with paint), some people uses this in the captions "a photo of a man as [name]" and this 0.005:25, 0.001:250, 0.00001 with batch 4 and worked... but not perfect. It depends on the model used afterwards. Protogen doesnt make it perfect... I prefer 2.1 or 1.5... or maybe is the setup of the pictures? I dunno, I just wanted to share with you my little aknowledge, hope it helps. Any thoughts?
Fthese above are from TI
Fsame setup in this video
FYouTubeSoftware Engineering Courses - SE Courses
In this video, I am explaining almost every aspect of Stable Diffusion Textual Inversion (TI) / Text Embeddings. I am demonstrating a live example of how to train a person face with all of the best settings including technical details.
If I have been of assistance to you and you would like to show your support for my work, please consider bec...
If I have been of assistance to you and you would like to show your support for my work, please consider bec...
Cyou said in the video to use 0.005, to leave it as it is, with batch 1
Cwhat about Filewords for images?
Fin TI i didnt use any
Fyou define what you dont want to teach
Fsince i have only my face in training
Fi dont need
FTI sd 2.1 512
Csome people uses this:
"a photo of a man as [name]"
"a photo of a man as [name]"
Cmaybe the solution is to use SD 2.1 512 instead of protogen
Cseriously, I have been thinking about it today
Fyou really should watch entire video
Fthat is my most informative video
Cyeah, done already twice or three times
Chahah
Cis great!
Cbut I love Protogen
Atrain on 1.5 then merge with protogen = 1.5yourface-1.5
Cyou mean dreambooth? I am trying to avoid it...
Aah
Cshe is a friend, Fátima, at least the 70% of her
CTI is hard to achieve. Also I tried to train in protogen infinity but with batch 3 because of lack of VRAM in google colab as long as it has 8Gb of size... I will try with 3.4 + batch 4... maybe that...
CI have been 10 days testing...
F
Cyeah but is not protogen hahahah, is it?
F
Cmaybe there is a cool model in SD 2.1 in civit.ai
Fthis is TI
Cusing 2.1, right?
Fyes
F512
Cprotogen + my friend Emily
Fwhich style should i generate for this video cover
CI mean, 2.1 maybe is powerful... I should try it... in december I used it... ok... maybe it makes it... but I am still in the protogen mood hahahah...
Fprotogen really powerful