i never got any useful info from these statistics for stable diffusion :/
i never got any useful info from these statistics for stable diffusion :/
Vokay
MThese graphs are only displayed when normalization is enabled for Lora (it is not enabled for DB). Based on the developer's description, I watch these two values to see if the maximum normalization reaches 1 (it is supposed to be good then) or not over normalizing, so how much it deviates from the original model, how much Lora needs to be improved. And from my observations, for cosine type training, these two graphs give very useful results under Prodigy.
FWell I would prefer full DreamBooth and extract LoRA
MGitHub
This PR adds Dropout and Max Norm Regularization [Paper] to train_network.py
Dropout randomly removes some weights/neurons from calculation on both the forward and backward passes, effectively trai...
Dropout randomly removes some weights/neurons from calculation on both the forward and backward passes, effectively trai...
MThat's what I was looking for in DreamBooth training, because it helps a lot to make a good model, and since I use it with cosine under Prodigy, I get absolutely good results when I watch the graph. I can see at a glance how good or bad Lora will be (see above), and tests have confirmed this.
BHi everyone,
I'm having serious problem with dreambooth, I always get terrible results and for the good ones, the face is not the same per dataset. I'm training everything on epicPhotogasm.
Of course it's my fault, this is my setup (apart from the A100 80G):
20 pictures of the same person (always portrait shot, not fullbody) in 1024x1024
2000 train steps
100 class images
lr 1e-6 100 validation steps
(please let me know if you need more details on the settings, but everything else is set as default)
Do you suggest to use 100/200 pictures and increase both train steps and class images? Or if you have better suggestions I'm open to everything!
Thank you!
I'm having serious problem with dreambooth, I always get terrible results and for the good ones, the face is not the same per dataset. I'm training everything on epicPhotogasm.
Of course it's my fault, this is my setup (apart from the A100 80G):
20 pictures of the same person (always portrait shot, not fullbody) in 1024x1024
2000 train steps
100 class images
lr 1e-6 100 validation steps
(please let me know if you need more details on the settings, but everything else is set as default)
Do you suggest to use 100/200 pictures and increase both train steps and class images? Or if you have better suggestions I'm open to everything!
Thank you!
MAnd here's the graph of the winning Lora, with d_coef=0.6 and 23 images. While I like to train it a bit stronger, I also let the Hires Fix work, which I used to boost the initial face to 0.96 for the very first generation. You can see in the image that I achieved normalization 1 on the right graph (yellow color), so it made a good model and only adjusted the normalization a few times.
Fare you using my patreon config?
Bunfortunately no 
I sent you a dm btw, I'd appreciate if you can reply, thank you!
I sent you a dm btw, I'd appreciate if you can reply, thank you!Fchecking dms in a moment hopefully sorry for delay
TRuntimeError: Error(s) in loading state_dict for UNet2DConditionModel:
size mismatch for down_blocks.0.attentions.0.proj_in.weight: copying a param with shape
torch.Size([320, 320]) from checkpoint, the shape in current model is torch.Size([320, 320, 1, 1])
my model: stable-diffusion-2-1-768v
resolution = 768
can u help m? thanks
size mismatch for down_blocks.0.attentions.0.proj_in.weight: copying a param with shape
torch.Size([320, 320]) from checkpoint, the shape in current model is torch.Size([320, 320, 1, 1])
my model: stable-diffusion-2-1-768v
resolution = 768
can u help m? thanks
Dhow to make resoltion (1024x1024) stick after every restart ? for image creation
Fi really dont use sd 2.1 it is pretty useless
Fedit : ui-config.json
Fi should show this
D@Dr. Furkan Gözükara you can do basic guide on automatic1111 UI
Dwould set base for many guides imo. Also under settings there is so much to tweak and learn
Fi agree
Dcorrected
Tshould i use sd1.5?
Dok under defaults also you do the same i guess
D
Fi prefer sdxl
Tyes. i often train sdxl on PC. but in train lora on colab free 
![Digital [Starburst]](https://cdn.discordapp.com/avatars/220961909447458817/8ecbbb3132fc6e44312f3d6d2ae3df69.webp?size=40)
DI'm interested in a tutorial on how to set this up: https://stability.ai/news/stability-ai-sdxl-turbo
Stability AI
SDXL Turbo is a new text-to-image mode based on a novel distillation technique called Adversarial Diffusion Distillation (ADD), enabling the model to create image outputs in a single step and generate real-time text-to-image outputs while maintaining high sampling fidelity.
DI got to try it for all of five seconds before reaching a usage cap. It was working great.
DThe image updates as you type making designing what you want much easier. There's no waiting 5 to 30 minutes to see the results.
D
DStable Diffusion ArtAndrew
Deforum is a tool to create animation videos with Stable Diffusion. All you need to provide the prompts and settings for how the camera moves.
DIt's an amazing tool.
DBut very complex.
Mwondering whats an estimate fine tune training time i can expect for using Nvidia 2070 Super for training a face with 5200 512x512 regularisation images and 40 training images with 40 repeats. using RealisticVision5.1 is it normal for 1 epoch to take 7 hours according to my tqdm? im also already using AdamW8bit
Awhat is the significance of having the json file in my models folder with my custom train?
VFurkan, can kaggle webui be used to do anmiatediff
Vdeforum is out of date, now animatediff is in fashion
MHere are some more pictures from an actress and a Tensorboard diagram.
I trained with 30 images this time, and here again d_coef=0.75 was enough, absolutely perfect Lora was taken, and there doesn't even have to be a close face in the generated images. I generated 512x512 images without Hires Fix, ReActor or Adetailer. I love it!
I trained with 30 images this time, and here again d_coef=0.75 was enough, absolutely perfect Lora was taken, and there doesn't even have to be a close face in the generated images. I generated 512x512 images without Hires Fix, ReActor or Adetailer. I love it!
MAnd this time I didn't use an extra correction prompt, just the simple one I wrote yesterday.
MNow tell me why you use so many reps and spend hours training when it was done in 12 minutes?
BGreat work, is that using the same config you shared previously or is this an updated one?
Zhow come i keep getting these undefined boxes in comfyui, but nothing shows under missing modules, already updated my comfyui, restarted and refreshed the web page
MThank you! It's the same config, I didn't change anything, I just set the d_coef value based on the graph. Nothing else.
Mhey does anyone have an open source dog regularisation dataset?
Zsdxl turbo in comfyui is literally real time
Zi'm blown away
Mdo u feel comfyUI is btr than kohya? or are they 2 diff tools?
Zkoyha is for training models, comfyui is for inference
Mi see so comfyUI is an alternative to Automatic1111? which wld u say is btr in your experience
Zyup exactly
Zi like automatic1111 better but comfyui is better for low vram systems, so most of my sdxl is run in comfyui
Mi see... what gpu do u run? are u using sdxl 0.9 or 1.0 in comfy UI?
