do i need to install tensorrt to get rid of the libnvinfer shared library issue?
do i need to install tensorrt to get rid of the libnvinfer shared library issue?
Fyou shouldnt be have to
Bpossible to train for style with a couple hundred images? i saw the recent midjourney video uses thousands of images for the style training... i tested with a few hundred and got decent results but i was not able to drive the output via the prompt (results looked good... but mostly just random images in my style regardless of prompt)
what should i change in my training to get better prompt weight in my outputs?
what should i change in my training to get better prompt weight in my outputs?
Fi think possible
Ftoday i will try with 274 images
Fto teach style
Fand 137 images to train myself
Bcool, will there be a video with the results?
Fto get more prompt weight probably more training
Fye
Fi am working on corridor crew style video
Fanimation
Byeah i didn't train much since it takes so damn long. it was looking really good so i stopped the training, i guess i need to try much more
Fyep training takes huge time
Fwhen more images to train
Fi will post more classification images to patreon. aesthetic and photo of man
IHello again, after a fresh install of A1111 and no xformers, I can confirm that everything is running fine, and loading faster than before. But I am not using A1111 for training. Dreambooth has to be installed manually, but it's OK.
IAs to the training, I was able to get 60% of images that look like the subject trained, nothing as good as in your videos.
IWhen I do it with SD 2.1 or Protogen, it gets worse, no resemblance at all. Also the biggest problem in general is that if use toke + class I get some results, if I just do the usual "closeu portrait photo of...." I get other people!!!
GPerhaps a slight side step from current conversation, but I'm interested in training SD on some pixel art characters for use in a platform game. I've tried training it to understand that I want a white background around each image but I haven't had any luck. This was with textual inversion. Does anyone have any suggestions? (The image below is the kind of output I'm after, white background surrounding the subject)
IBy the way Dr. Furkan, I still seem to have some confusion with numbers of steps/epochs, because the UI says "steps-epochs" and it's confusing. So I trained with values from 150-300 (whatever that is) and got models that go up to 12.000 (whatever that is). Could you please explain this in simple way?
ILR I'm using 0.000001 and not sure if go lower will be better. Like 1.0e-7 will that help?
Fi explain these in videos actually
Fi will also mention in next video
IYes, I saw all the videos, but it's OK. I did some research on the Internet, to clarify this further.
IWhat about the other problem? Using your exact settings, I can't work with prompts. token + class generates some images, then as soon as I write a prompt, I loose the subject. In your video that didn't happen. I'm using SD 1.5 and Protogen, same exact settings.
SI got the bot working on my server with my home install! I used a thing a dude put on github. Will not post the link unless/until doc approves but it's pretty cool.
Fsomething must be off. if you are our patreon supporter i can setup a training on your computer if you wish
Fif anyone interested they can message you i think
Fi am starting a new training with newest dreambooth
Fin a minute
SThanks, doc! What level patron gets troubleshooting help? I
F/workspace/photo of man 6080
/workspace/aesthetic 10598
/workspace/training images 137
/workspace/style_512 274
/workspace/aesthetic 10598
/workspace/training images 137
/workspace/style_512 274
Fwell if it is easy basic level is sufficient . if you need longer help please get gold :d
Ftime to train
F
Fmulti concept at once
SHello. I don't know who works on the youtube tutorials that led me here but he's a beautiful human beign.
Fthank you . i am
Fwelcome
Fcaching latents
SNo, i thank you! 
This is so detailed, dammn
This is so detailed, dammnFtraining started
F
Fall working good first checkpoint saved. i am not generating any previews . saving checkpoints every 4 epoch
F
ZI can't figure this out, my training data looks perfect, saved the weights, converted to checkpoint, when i use the prompt in txt2img, it looks nothing like my subject
Zmy sample data looks perfect but when i use the lora file, it's a completely different person
Fyou are blending your training into many tokens
F
Zshould i simply do photo of woman instaed?
