python: 3.10.6 • torch: 2.0.0+cu118 • xformers: 0.0.17+b6be33a.d20230315
python: 3.10.6 • torch: 2.0.0+cu118 • xformers: 0.0.17+b6be33a.d20230315
FDoes it work when use older version?
FOr did you try without sample image generation during training
Nlet me say it like this: it worked perfect unteil I started updating xformers 
Nthe freezing occurs not while training
Nbut in normal batch creation
FSo must be a bug in extension I will report
FYou can also downgrade meanwhile
FAnd can you try with 0 sample image during training?
Ni will do that after work this eveningg and see if it changed the situation.
F
Nas i said- i did not train after updating as i have these problems already while normal creation.
FAh you can't generate image? Weird
FIt works for me
Ni generate a few images and then it freezes
Ninmid creation
NLoading weights [738697b888] from C:\SD\stable-diffusion-webui\models\Stable-diffusion\ohwx_woolitize_24_1\ohwx_woolitize_24_1_480.ckpt
Creating model from config: C:\SD\stable-diffusion-webui\models\Stable-diffusion\ohwx_woolitize_24_1\ohwx_woolitize_24_1_480.yaml
LatentDiffusion: Running in eps-prediction mode
DiffusionWrapper has 859.52 M params.
Applying xformers cross attention optimization.
Model loaded in 2.9s (create model: 0.5s, apply weights to model: 0.7s, apply half(): 0.8s, move model to device: 0.7s, scripts callbacks: 0.2s).
100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████| 15/15 [00:01<00:00, 7.57it/s]
Total progress: 1
Creating model from config: C:\SD\stable-diffusion-webui\models\Stable-diffusion\ohwx_woolitize_24_1\ohwx_woolitize_24_1_480.yaml
LatentDiffusion: Running in eps-prediction mode
DiffusionWrapper has 859.52 M params.
Applying xformers cross attention optimization.
Model loaded in 2.9s (create model: 0.5s, apply weights to model: 0.7s, apply half(): 0.8s, move model to device: 0.7s, scripts callbacks: 0.2s).
100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████| 15/15 [00:01<00:00, 7.57it/s]
Total progress: 1
NLoading weights [738697b888] from C:\SD\stable-diffusion-webui\models\Stable-diffusion\ohwx_woolitize_24_1\ohwx_woolitize_24_1_480.ckpt
Creating model from config: C:\SD\stable-diffusion-webui\models\Stable-diffusion\ohwx_woolitize_24_1\ohwx_woolitize_24_1_480.yaml
LatentDiffusion: Running in eps-prediction mode
DiffusionWrapper has 859.52 M params.
Applying xformers cross attention optimization.
Model loaded in 2.9s (create model: 0.5s, apply weights to model: 0.7s, apply half(): 0.8s, move model to device: 0.7s, scripts callbacks: 0.2s).
100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████| 15/15 [00:01<00:00, 7.57it/s]
Total progress: 17%|██████████▌ | 225/1350 [03:18<02:57, 6.32it/s]
Creating model from config: C:\SD\stable-diffusion-webui\models\Stable-diffusion\ohwx_woolitize_24_1\ohwx_woolitize_24_1_480.yaml
LatentDiffusion: Running in eps-prediction mode
DiffusionWrapper has 859.52 M params.
Applying xformers cross attention optimization.
Model loaded in 2.9s (create model: 0.5s, apply weights to model: 0.7s, apply half(): 0.8s, move model to device: 0.7s, scripts callbacks: 0.2s).
100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████| 15/15 [00:01<00:00, 7.57it/s]
Total progress: 17%|██████████▌ | 225/1350 [03:18<02:57, 6.32it/s]
Nsorry- missed the last line...
Nthe predicted total running time in the blue progress bar at the top right did not change- normally it would change the predicted time for the complete job as longer it takes. but it only freezes here. AND you do not see an error output under the picture as usal in case something fails...
FUi freezes or image generation
FWhen you hit enter on cmd it continue generation?
Nno, cmd doesnt react
Nui ssems to run - you can at least switch to another tab f.e. image2image and add a new job that gets queued
Nyou can reload the gui, queue a change of image or a job, but nothing happens. is there some was of a beduggin log or sth. else to see where exactly the process freezes?
Nsome way of extended debug logging
GHey! I want to know, Can I now run Dreambooth 1.5 on my 3070TI with 24gig of ram ?
GRunpod just seems to fail on me often so I would like to try have it all run locally
AHey everyone! uhhh what's going on with this? help appreciated
AIt’s weird because I already trained one model no problem with this exact text like this
F3070 ti how much vram you have
G8
Fhi if you already trained you can skip that part. please watch this video : https://www.youtube.com/watch?v=kIyqAdd_i10
YouTubeSECourses - Software Engineering Courses
Our Discord : https://discord.gg/HbqgGaZVmr. This is the video where you will learn how to use Google Colab for Stable Diffusion. 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 Stable Diffusion Tutorials, #Automatic1111...
https://www.patreon.com/SECoursesPlaylist of Stable Diffusion Tutorials, #Automatic1111...
Fyou cant do dreambooth but you can do lora in dreambooth extension
Falso you can do textual inversion
Fvery weird. and there is no error message right?
AI’m creating a second model, so I don’t know why the indentation is an issue since I know it works and never changed it
A(I followed your video to a T and I’m not sure where the difference is from the text)
G@Furkan Gözükara SECourses I have 2400 RegularizationImages, what would the class images per instance be?
Fcopy paste that part from the original link it should fix
Fi suggest 50 per instance
Fhow many training you have?
G10
Fok i think still set 50
Fso it will use 500
Gperfect
GFinally before I start training
G
GI am using Lora so I need to best settings for these sliders
Funfortunately i am yet to run experiments for them
Fbut kohya uses 128 and 128
