just curious, but is anyone else have xformers break training on any commit of dreambooth? im using
just curious, but is anyone else have xformers break training on any commit of dreambooth? im using a 4090
CThe ratio I have of good eyes is amazing with my model.
Prompt: African woman
Prompt: African woman
C
Cdoes it look like midjourney to you guys?
Cprompts?
CLet see if you get the same thing as I do
C1girl, earrings, forehead, jewelry, lips, looking_at_viewer, ponytail, portrait, realistic, red_lips, solo 1girl, earrings, forehead, jewelry, lips, looking_at_viewer, ponytail, portrait, realistic, red_lips, solo
KVery nice
CDo you get similar results?
Cthis is with my model LMAO
Chaha
CLooks like your profile pic
Cso I suppose its good stuff 
Cjust finished it today the results are amazing
KNice, naked chick
Cty
KWith big boobs
COriginal model
C1girl, black_hair, breasts, cleavage, glasses, lips, looking_at_viewer, medium_breasts, multiple_boys, red_background, short_hair 1girl, black_hair, breasts, cleavage, glasses, lips, looking_at_viewer, medium_breasts, multiple_boys, red_background, short_hair
Coh nice
C@Dr. Furkan Gözükara forgive the text? Its danbooru and I use my own methodology for textual inversion 
C
CDefinitely Midjourney is trained in similar methodology, im sure of it
Fye looks like too old :/
Fwhich video you followed exactly? probably your classification image batch size too big
Fhow many did you set it?
Fwhich xformers version you using?
Fuse 0.0.14
FYouTubeSoftware Engineering Courses - SE Courses
Our Discord : https://discord.gg/HbqgGaZVmr. This video I am showing how to downgrade CUDA and xformers version for proper training and I am showing how to do LoRA training with 8GB GPU. 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/SECourse...
https://www.patreon.com/SECourse...
Cthanks
Calso it auto installed 0.0.16
Fye it is not working for dreambooth atm
F0.0.14 or 0.0.17 dev version. use 0.0.14 for now
Csounds good ill downgrade before training again, i ended up finishing my model w/o xformers and it still didnt take too long and the results are phenominal
Fyes actually without xformers
Fit is better
Fxformers reduces quality
Fbut you need like 24 gb vram for that
Cfor real, it saturated most of my 4090's vram
BF for Respect, sir. thank you very much for your contribution to AI community
Ftrue. for sd 2.1 i had to enable xformers on runpod
Fcurrently post editing runpod tutorial
F
Fthank you so much for great comment. if you are able to become patron i would appreciate very much that
MFirstly thanks for the top videos. Super useful. I'm a little confused by ControlNet, does anyone know how to access this via API yet?
C1girl, breathing_fire, burning, embers, explosion, fiery_hair, fiery_wings, fire, flame, lips, looking_at_viewer, molten_rock, moon, orange_theme, red_moon, red_sky, red_theme, solo, sun, sunset, torch 1girl, breathing_fire, burning, embers, explosion, fiery_hair, fiery_wings, fire, flame, lips, looking_at_viewer, molten_rock, moon, orange_theme, red_moon, red_sky, red_theme, solo, sun, sunset, torch
Fi think you can use their native script they have api there
FYouTubeSoftware Engineering Courses - SE Courses
Our Discord : https://discord.gg/HbqgGaZVmr. In this video, You will see the new amazing Stable Diffusion technology - #ControlNet. 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, Automatic111...
https://www.patreon.com/SECoursesPlaylist of #StableDiffusion Tutorials, Automatic111...
OHi I'm trying to use Shivam colab with a custom mode ( Realisticvision 1.3) from hugging face. It has all the diffusers data. In the colab, I can run the inference without problem and generate images, but when I try to train it exits with errors. I commented out the "fp16 revison" flag and changed the VAE parameter to " --pretrained_vae_name_or_path="SG161222/Realistic_Vision_V1.3/vae" "
I got "subprocess.CalledProcessError: Command '['/usr/bin/python3', 'train_dreambooth.py', '--pretrained_model_name_or_path=SG161222/Realistic_Vision_V1.3', '--pretrained_vae_name_or_path=SG161222/Realistic_Vision_V1.3/vae', '--output_dir=/content/Rv2_weights/zwx']' returned non-zero exit status 1.
"
Do you know what the issue is? Please see the screenshots for more details. Thanks!
I got "subprocess.CalledProcessError: Command '['/usr/bin/python3', 'train_dreambooth.py', '--pretrained_model_name_or_path=SG161222/Realistic_Vision_V1.3', '--pretrained_vae_name_or_path=SG161222/Realistic_Vision_V1.3/vae', '--output_dir=/content/Rv2_weights/zwx']' returned non-zero exit status 1.
"
Do you know what the issue is? Please see the screenshots for more details. Thanks!
Fthey have only main branch