SEC
Software Engineering Courses (SECourses)
Discuss, ask and learn Stable Diffusion, DreamBooth, Programming, Software Engineering, C#, ASP.NET, MSSQL and more
JoinSEC
Software Engineering Courses (SECourses)
Discuss, ask and learn Stable Diffusion, DreamBooth, Programming, Software Engineering, C#, ASP.NET, MSSQL and more
Joinscript-updates-and-info
okul-school
flux-stable-diffusion-such
programming
tips-info
ai
technology
server-admin
cyber-security
dreambooth-training
work-on-next-list
anouncements
I was starting to play around with one
I was starting to play around with one trainer and an XL checkpoint and noticed the learning rate in the tier_1 10GB json preset was "learning_rate": 1e-05" which seems higher than all your other learning rates you've been moving towards. Is that accurate or should I move it to something like 1e-06 or 8e-07?
teach from youtube + patreon + i work at
teach from youtube + patreon + i work at a private university
Post the full error please. Looks likes
Post the full error please. Looks likes this is not the real error
Just found this, although I haven't
Just found this, although I haven't tried it: https://github.com/kijai/ComfyUI-SUPIR
our configs for DreamBooth not lora
our configs for DreamBooth not lora
whats the consneus on repeat steps? I
whats the consneus on repeat steps? I saw 1 lora video that had it for 25, and the most recent one for full blown dreambooth at 40
any idea why i'm getting an out of cuda
any idea why i'm getting an out of cuda memory error when i try to load my dreambooth checkpoint like this
```
vae = AutoencoderKL.from_single_file(vae_fp16_path, torch_dtype=torch.float16)
pipe = StableDiffusionXLPipeline.from_single_file(
pretrained_model_link_or_path=path_to_weights,...
is there a downside toward generating
is there a downside toward generating 768 by 1024 images with SDXL?
Hi all, I'm a brand new Patreon
Hi all, I'm a brand new Patreon supporter. I'm following the tutorial to make a LoRA training of myself in Kaggle. But I get the following error:
torch.cuda.OutOfMemoryError: CUDA out of memory. Tried to allocate 20.00 MiB (GPU 0; 14.76 GiB total capacity; 13.17 GiB already allocated; 7.75 MiB free; 13.46 GiB reserved in total by PyTorch Here is my training command: `accelerate launch --num_cpu_threads_per_process=2 "./sdxl_train_network.py" --pretrained_model_name_or_path="stabilityai/stable-...First Ever SDXL Training With Kohya LoRA...
Good afternoon (in CET), Im trying to follow the excellent guide in 'First Ever SDXL Training With Kohya LoRA - Stable Diffusion XL Training' (https://www.youtube.com/watch?v=AY6DMBCIZ3A) but am running into OOM when starting up training.
CUDA out of memory. Tried to allocate 2.00 MiB (GPU 0; 10.00 GiB total capacity; 9.15 GiB already
allocated; 0 bytes free; 9.26 GiB reserved in total by PyTorch).
Im a bit of a noob, buy why dont torch use the already allocated memory to train my lora? Any suggestions are more than welcomed. Im on a windows machine with rtx3080...
Help with Dreambooth
Yes, you basically rent a server and its yours to do with as you please within reason. Obviously don't do anything illegal with it.
Any idea 💡 how and and when it s
Any idea 💡 how and and when it's possible to run SDXL with ControlNet? Looking for a Colab ideally 😎
I have watched several different videos
I have watched several different videos out there @Dr. Furkan Gözükara, and I can't express how much information and practical knowledge I gained. I am practicing a lot of stuff with SD recently, but few weeks back I was a complete beginner. But still, I strive with all different SD parameters, weights and settings. Can you please suggest me a complete beginner guide where everything is explained from 0, like which parameters does what etc? Just like a "Java How to Program" of Stable Diffusion....
This doesn t mean anything what is the
This doesn't mean anything what is the full error?
...
ntrolnet/scripts/controlnet.py", line 731, in process
model_net = Script.load_control_model(p, unet, unit.model, unit.low_vram)
ntrolnet/scripts/controlnet.py", line 731, in process
model_net = Script.load_control_model(p, unet, unit.model, unit.low_vram)
```
cd /workspace/stable-diffusion-webui/extensions/sd_dreambooth_extension
git branch
cd /workspace/stable-diffusion-webui/extensions/sd_dreambooth_extension
git branch