Software Engineering Courses (SECourses)•3y ago

RuntimeError: Error(s) in loading state_dict for UNet2DConditionModel: size mismatch for dow

RuntimeError: 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

DR.Siva•11/29/23, 3:01 PM

how to make resoltion (1024x1024) stick after every restart ? for image creation

Tthewingag RuntimeError: Error(s) in loading state_dict for UNet2DConditionModel: s...

Furkan Gözükara SECourses•11/29/23, 3:03 PM

i really dont use sd 2.1 it is pretty useless

DDR.Siva how to make resoltion (1024x1024) stick after every restart ? for image creation

Furkan Gözükara SECourses•11/29/23, 3:04 PM

edit : ui-config.json

Furkan Gözükara SECourses•11/29/23, 3:04 PM

i should show this

DR.Siva•11/29/23, 3:05 PM

@Dr. Furkan Gözükara you can do basic guide on automatic1111 UI

DR.Siva•11/29/23, 3:05 PM

would set base for many guides imo. Also under settings there is so much to tweak and learn

Furkan Gözükara SECourses•11/29/23, 3:06 PM

i agree

DR.Siva•11/29/23, 3:10 PM

corrected

FFurkan Gözükara SECourses i agree

thewingagOP•11/29/23, 3:10 PM

should i use sd1.5?

DR.Siva•11/29/23, 3:13 PM

ok under defaults also you do the same i guess

DR.Siva•11/29/23, 3:13 PM

Tthewingag should i use sd1.5?

Furkan Gözükara SECourses•11/29/23, 3:19 PM

i prefer sdxl

FFurkan Gözükara SECourses i prefer sdxl

thewingagOP•11/29/23, 3:22 PM

yes. i often train sdxl on PC. but in train lora on colab free

Digital [Starburst]•11/29/23, 3:49 PM

I'm interested in a tutorial on how to set this up: https://stability.ai/news/stability-ai-sdxl-turbo

Stability AI

Introducing SDXL Turbo: A Real-Time Text-to-Image Generation Model ...

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.

Digital [Starburst]•11/29/23, 3:50 PM

I got to try it for all of five seconds before reaching a usage cap. It was working great.

Digital [Starburst]•11/29/23, 3:51 PM

The image updates as you type making designing what you want much easier. There's no waiting 5 to 30 minutes to see the results.

Digital [Starburst]•11/29/23, 3:52 PM

Here's the Hugging Face link: https://huggingface.co/stabilityai/sdxl-turbo

stabilityai/sdxl-turbo · Hugging Face

Digital [Starburst]•11/29/23, 3:52 PM

In the meantime I have been trying to learn to use: https://stable-diffusion-art.com/deforum/

Stable Diffusion ArtAndrew

How to make a video with Stable Diffusion (Deforum) - Stable Diffus...

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.

Digital [Starburst]•11/29/23, 3:53 PM

It's an amazing tool.

Digital [Starburst]•11/29/23, 3:53 PM

But very complex.

MrJoozy•11/29/23, 4:02 PM

wondering 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

AIGambino•11/29/23, 5:01 PM

what is the significance of having the json file in my models folder with my custom train?

virginia•11/29/23, 5:44 PM

Furkan, can kaggle webui be used to do anmiatediff

virginia•11/29/23, 5:45 PM

deforum is out of date, now animatediff is in fashion

mikemenders•11/29/23, 6:09 PM

Here 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!

mikemenders•11/29/23, 6:11 PM

And this time I didn't use an extra correction prompt, just the simple one I wrote yesterday.

mikemenders•11/29/23, 6:20 PM

Now tell me why you use so many reps and spend hours training when it was done in 12 minutes?

Original message was deleted

B0nd•11/29/23, 6:28 PM

Great work, is that using the same config you shared previously or is this an updated one?

Zono50•11/29/23, 6:36 PM

how 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

BB0nd Great work, is that using the same config you shared previously or is this an up...

mikemenders•11/29/23, 6:46 PM

Thank you! It's the same config, I didn't change anything, I just set the d_coef value based on the graph. Nothing else.

MrJoozy•11/29/23, 7:29 PM

hey does anyone have an open source dog regularisation dataset?

Zono50•11/29/23, 7:31 PM

sdxl turbo in comfyui is literally real time

Zono50•11/29/23, 7:31 PM

i'm blown away

ZZono50 sdxl turbo in comfyui is literally real time

MrJoozy•11/29/23, 7:40 PM

do u feel comfyUI is btr than kohya? or are they 2 diff tools?

Zono50•11/29/23, 7:41 PM

koyha is for training models, comfyui is for inference

ZZono50 koyha is for training models, comfyui is for inference

MrJoozy•11/29/23, 7:41 PM

i see so comfyUI is an alternative to Automatic1111? which wld u say is btr in your experience

Zono50•11/29/23, 7:42 PM

yup exactly

Zono50•11/29/23, 7:42 PM

i like automatic1111 better but comfyui is better for low vram systems, so most of my sdxl is run in comfyui

ZZono50 i like automatic1111 better but comfyui is better for low vram systems, so most ...

MrJoozy•11/29/23, 7:44 PM

i see... what gpu do u run? are u using sdxl 0.9 or 1.0 in comfy UI?

Zono50•11/29/23, 7:44 PM

4070 ti

Zono50•11/29/23, 7:44 PM

1.0

ZZono50 4070 ti

MrJoozy•11/29/23, 7:44 PM

yo haha thats stacked, im on a old 2070 super, damn...

MMrJoozy hey does anyone have an open source dog regularisation dataset?

mikemenders•11/29/23, 7:47 PM

If not, you can make them with Furkan's yolo scripts, you can find pictures on Pixabay.

mikemenders•11/29/23, 7:47 PM

Just change it from person to dog

Zono50•11/29/23, 7:47 PM

i want sdxl turbo inpainting

Mmikemenders If not, you can make them with Furkan's yolo scripts, you can find pictures on P...

MrJoozy•11/29/23, 7:52 PM

ah, i see, referring to this patreon post?
https://www.patreon.com/posts/sota-subject-and-88391247

MMrJoozy ah, i see, referring to this patreon post? https://www.patreon.com/posts/sota-su...

mikemenders•11/29/23, 8:02 PM

Yes, that's what I thought

Zono50•11/29/23, 8:42 PM

i'm gonna tell you right now why i love sdxl turbo instant

Zono50•11/29/23, 8:43 PM

It's not the best graphically, but you can cycle through prompts and styles and see exactly what the prompts do, then you can use fooocus or auto1111 or comfyui with high step scheduler and get exactly what you want

Mmikemenders Now tell me why you use so many reps and spend hours training when it was done i...

r1•11/29/23, 8:43 PM

What’s your workflow?

RuntimeError: Error(s) in loading state_dict for UNet2DConditionModel: size mismatch for dow

Similar Threads

Similar Threads

Similar Threads