Software Engineering Courses (SECourses)•3y ago

Hey everyone! uhhh what's going on with this? help appreciated

AbigailEldritchOP•3/22/23, 9:22 AM

It’s weird because I already trained one model no problem with this exact text like this

GGarreth210 Hey! I want to know, Can I now run Dreambooth 1.5 on my 3070TI with 24gig of ram...

Furkan Gözükara SECourses•3/22/23, 10:16 AM

3070 ti how much vram you have

Garreth210•3/22/23, 10:16 AM

AAbigailEldritch Hey everyone! uhhh what's going on with this? help appreciated

Furkan Gözükara SECourses•3/22/23, 10:17 AM

hi 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

Stable Diffusion Google Colab, Continue, Directory, Transfer, Clone...

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...

GGarreth210 8

Furkan Gözükara SECourses•3/22/23, 10:17 AM

you cant do dreambooth but you can do lora in dreambooth extension

Furkan Gözükara SECourses•3/22/23, 10:17 AM

also you can do textual inversion

Nn8hawk_no, cmd doesnt react

Furkan Gözükara SECourses•3/22/23, 10:17 AM

very weird. and there is no error message right?

FFurkan Gözükara SECourses hi if you already trained you can skip that part. please watch this video : htt...

AbigailEldritchOP•3/22/23, 10:17 AM

I’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

AbigailEldritchOP•3/22/23, 10:18 AM

(I followed your video to a T and I’m not sure where the difference is from the text)

Garreth210•3/22/23, 10:20 AM

@Furkan Gözükara SECourses I have 2400 RegularizationImages, what would the class images per instance be?

AAbigailEldritch I’m creating a second model, so I don’t know why the indentation is an issue sin...

Furkan Gözükara SECourses•3/22/23, 10:20 AM

copy paste that part from the original link it should fix

GGarreth210 @Furkan Gözükara SECourses I have 2400 RegularizationImages, what would the clas...

Furkan Gözükara SECourses•3/22/23, 10:20 AM

i suggest 50 per instance

Furkan Gözükara SECourses•3/22/23, 10:20 AM

how many training you have?

Garreth210•3/22/23, 10:20 AM

GGarreth210 10

Furkan Gözükara SECourses•3/22/23, 10:20 AM

ok i think still set 50

Furkan Gözükara SECourses•3/22/23, 10:21 AM

so it will use 500

Garreth210•3/22/23, 10:21 AM

perfect

Garreth210•3/22/23, 10:42 AM

Finally before I start training

Garreth210•3/22/23, 10:42 AM

Garreth210•3/22/23, 10:42 AM

I am using Lora so I need to best settings for these sliders

GGarreth210 Click to see attachment

Furkan Gözükara SECourses•3/22/23, 10:50 AM

unfortunately i am yet to run experiments for them

Furkan Gözükara SECourses•3/22/23, 10:50 AM

but kohya uses 128 and 128

Furkan Gözükara SECourses•3/22/23, 10:51 AM

i believe

Furkan Gözükara SECourses•3/22/23, 10:51 AM

another tips for lower vram. under command line arguments :

set PYTORCH_CUDA_ALLOC_CONF=garbage_collection_threshold:0.6,max_split_size_mb:128

set PYTORCH_CUDA_ALLOC_CONF=garbage_collection_threshold:0.6,max_split_size_mb:128

Garreth210•3/22/23, 10:52 AM

Garreth210•3/22/23, 10:54 AM

I assume the PyTorch_Cuda_Alloc_Config command needs to be added before starting SD and not during XD

GGarreth210 I assume the PyTorch_Cuda_Alloc_Config command needs to be added before starting...

Furkan Gözükara SECourses•3/22/23, 10:55 AM

yes. this is for low vram problem having people

Garreth210•3/22/23, 10:56 AM

I am now following your guide to the letter incuding the images. I will train styles later

Garreth210•3/22/23, 10:57 AM

These images that are being sampled do not seem right

Garreth210•3/22/23, 10:58 AM

I am expecting images of me or is this not the case?

Garreth210•3/22/23, 11:03 AM

The face and hair looks kinda like me.. Am I being hopfull XD

sample_700-1c86872d4e79c313dfb027cf9e1c310bd4130fb50.png

Garreth210•3/22/23, 11:08 AM

sample_900-10be463fb1c69826321e1fd9966d62f76237cd088.png

Garreth210•3/22/23, 11:08 AM

Garreth210•3/22/23, 11:09 AM

I am getting really cool accurate ish looking images

GGarreth210 I am getting really cool accurate ish looking images

Furkan Gözükara SECourses•3/22/23, 11:18 AM

great

Furkan Gözükara SECourses•3/22/23, 11:22 AM

i added a spanish subtitle can anyone test it who knows spanish? https://www.youtube.com/watch?v=m-UVVY_syP0

YouTubeSECourses - Software Engineering Courses

Training Midjourney Level Style And Yourself Into The SD 1.5 Model ...

RunPod: https://bit.ly/RunPodIO. Discord : https://bit.ly/SECoursesDiscord. Get your own #Midjourney level model for free via Style Teaching. 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, Au...

Furkan Gözükara SECourses•3/22/23, 11:26 AM

now translating to french

Stevens•3/22/23, 12:12 PM

I let my embed run all night and it is still a monster! This is tough.

SStevens I let my embed run all night and it is still a monster! This is tough.

Furkan Gözükara SECourses•3/22/23, 12:12 PM

could be overtraining. you are following this video right? https://www.youtube.com/watch?v=dNOpWt-epdQ

YouTubeSECourses - Software Engineering Courses

How To Do Stable Diffusion Textual Inversion (TI) / Text Embeddings...

Our Discord : https://discord.gg/HbqgGaZVmr. Grand Master tutorial for Textual Inversion / Text Embeddings. 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 and Google Colab Guide...

Garreth210•3/22/23, 12:43 PM

@Furkan Gözükara SECourses The command you gave does not seem to wrk

GGarreth210 @Furkan Gözükara SECourses The command you gave does not seem to wrk

Furkan Gözükara SECourses•3/22/23, 12:43 PM

which one

Garreth210•3/22/23, 12:43 PM

Garreth210•3/22/23, 12:43 PM

Garreth210•3/22/23, 12:44 PM

also, with Lora my face does not look close to as good as your images you get to generate. I will now try with normal Dreambooth without Lora and then try the XYZ picking

GGarreth210 Click to see attachment

Furkan Gözükara SECourses•3/22/23, 12:48 PM

you need to put set to front

GGarreth210 also, with Lora my face does not look close to as good as your images you get to...

Furkan Gözükara SECourses•3/22/23, 12:48 PM

dreambooth better than lora

FFurkan Gözükara SECourses could be overtraining. you are following this video right? https://www.youtube.c...

Stevens•3/22/23, 12:48 PM

I could not find an embedding video from you! Hooray I am saved. Thank you!

GGarreth210 Click to see attachment

Furkan Gözükara SECourses•3/22/23, 12:50 PM

set PYTORCH_CUDA_ALLOC_CONF=garbage_collection_threshold:0.6,max_split_size_mb:128

set PYTORCH_CUDA_ALLOC_CONF=garbage_collection_threshold:0.6,max_split_size_mb:128

kicedz•3/22/23, 12:53 PM

Hi, i'm having issues with setting up xformers with the A5000 GPU in SD Dreambooth

Whenever i click Generate Class Images i'm getting :

Exception generating concepts: No operator found for memory_efficient_attention_forward with inputs: query : shape=(1, 2, 1, 40) (torch.float32) key : shape=(1, 2, 1, 40) (torch.float32) value : shape=(1, 2, 1, 40) (torch.float32) attn_bias : p : 0.0 flshattF is not supported because: xFormers wasn't build with CUDA support dtype=torch.float32 (supported: {torch.bfloat16, torch.float16}) tritonflashattF is not supported because: xFormers wasn't build with CUDA support dtype=torch.float32 (supported: {torch.bfloat16, torch.float16}) triton is not available requires A100 GPU cutlassF is not supported because: xFormers wasn't build with CUDA support smallkF is not supported because: xFormers wasn't build with CUDA support max(query.shape[-1] != value.shape[-1]) > 32 unsupported embed per head: 40

I've set everything based on your youtube tutorial here https://www.youtube.com/watch?v=Bdl-jWR3Ukc&t=158s

Kkicedz Hi, i'm having issues with setting up xformers with the A5000 GPU in SD Dreamboo...

Furkan Gözükara SECourses•3/22/23, 12:58 PM

generate class images with txt2img

Hey everyone! uhhh what's going on with this? help appreciated

Similar Threads