Software Engineering Courses (SECourses)•3y ago

trying without the --. I thought that is how the args are being separated

Garreth210OP•3/22/23, 1:00 PM

nope

Garreth210OP•3/22/23, 1:00 PM

does not work

GGarreth210 trying without the --. I thought that is how the args are being separated

Furkan Gözükara SECourses•3/22/23, 1:00 PM

let me show you

Furkan Gözükara SECourses•3/22/23, 1:00 PM

you are writing incorrectly

Garreth210OP•3/22/23, 1:00 PM

I see now

Garreth210OP•3/22/23, 1:00 PM

ahahah

GGarreth210 oh

Furkan Gözükara SECourses•3/22/23, 1:00 PM

Garreth210OP•3/22/23, 1:00 PM

Yup

Garreth210OP•3/22/23, 1:01 PM

I was being stupid

Garreth210OP•3/22/23, 1:01 PM

fingers crossed this works

Garreth210OP•3/22/23, 1:01 PM

then I will try train again with drambooth, set some checkpoints and then XYZ select from the checkpoints

GGarreth210 then I will try train again with drambooth, set some checkpoints and then XYZ se...

Furkan Gözükara SECourses•3/22/23, 1:04 PM

i think dreambooth still wouldnt work on 8 gb :d

Furkan Gözükara SECourses•3/22/23, 1:04 PM

but worth to try let me know

Garreth210OP•3/22/23, 1:04 PM

will do

Garreth210OP•3/22/23, 1:04 PM

I am just finding that runpod is harder than running it locally on windows

Garreth210OP•3/22/23, 1:05 PM

but I don't get close to the image quality your SD is producing

FFurkan Gözükara SECourses generate class images with txt2img

kicedz•3/22/23, 1:06 PM

On text2img im still getting the same error
NotImplementedError: No operator found for memory_efficient_attention_forwardmemory_efficient_attention_forward with inputs: query : shape=(2, 4096, 8, 40) (torch.float16) key : shape=(2, 4096, 8, 40) (torch.float16) value : shape=(2, 4096, 8, 40) (torch.float16) attn_bias : <class 'NoneType'> p : 0.0 cutlassFcutlassF is not supported because: xFormers wasn't build with CUDA support flshattFflshattF is not supported because: xFormers wasn't build with CUDA support tritonflashattFtritonflashattF is not supported because: xFormers wasn't build with CUDA support triton is not available requires A100 GPU smallkFsmallkF is not supported because: xFormers wasn't build with CUDA support dtype=torch.float16 (supported: {torch.float32}) max(query.shape[-1] != value.shape[-1]) > 32 unsupported embed per head: 40
Time taken: 1.82sTorch active/reserved: 2230/2246 MiB, Sys VRAM: 3577/24257 MiB (14.75%)

What could be wrong? I'm using SD 1.5.ckpt, and probably the text2img has nothing to do with Dreambooth

kicedz•3/22/23, 1:07 PM

python: 3.10.6 • torch: 1.13.1+cu117 • xformers: 0.0.17+6d62b0e.d20230322 • gradio: 3.16.2 • commit: a9fed7c3 • checkpoint: 4c86efd062

I'm currently new to this, apologies if i ask pretty basic questions.

Garreth210OP•3/22/23, 1:09 PM

No luck with dreambooth on a 3070ti 8gig of vram

Zono50•3/22/23, 1:10 PM

quick question, i can download LORA files from the civit.ai and not have to use prompts to invoke them, how can I do that with my lora model i'm training?

Zono50•3/22/23, 1:22 PM

also my models eyes are super blue and red, not sure why that is, i took the models photos, did face restoration, then used the face restored photos for my dataset

sample_24890-2534c6b563d6b2513f10b445e9279e057ac1cd58b.png

Garreth210OP•3/22/23, 1:31 PM

Trying to get dreambooth up and running on Runpod this monring and I can't seem to get it working again

Garreth210OP•3/22/23, 1:31 PM

did something change ?

Garreth210OP•3/22/23, 1:32 PM

Kkicedz On text2img im still getting the same error NotImplementedError: No operator fo...

Furkan Gözükara SECourses•3/22/23, 1:33 PM

ok looks like that card not supporting

Furkan Gözükara SECourses•3/22/23, 1:33 PM

install another xformers

Furkan Gözükara SECourses•3/22/23, 1:33 PM

let me tell you version

Furkan Gözükara SECourses•3/22/23, 1:33 PM

try this

Furkan Gözükara SECourses•3/22/23, 1:33 PM

0.0.17.dev476

Furkan Gözükara SECourses•3/22/23, 1:34 PM

pip install xformers== 0.0.17.dev476

kicedz•3/22/23, 1:34 PM

Will do it right now sir

GGarreth210 No luck with dreambooth on a 3070ti 8gig of vram

Furkan Gözükara SECourses•3/22/23, 1:34 PM

i see

ZZono50 quick question, i can download LORA files from the civit.ai and not have to use ...

Furkan Gözükara SECourses•3/22/23, 1:34 PM

that means auto loaded pt files

GGarreth210 Click to see attachment

Garreth210OP•3/22/23, 1:35 PM

I've updated the versions as well

Garreth210OP•3/22/23, 1:35 PM

Garreth210OP•3/22/23, 1:35 PM

so I am not sure what is happening

ZZono50 also my models eyes are super blue and red, not sure why that is, i took the mod...

Furkan Gözükara SECourses•3/22/23, 1:35 PM

i am also getting blue eyes usually :d i think related to prompts

GGarreth210 Click to see attachment

Furkan Gözükara SECourses•3/22/23, 1:35 PM

your xformers version probably not compatible

Furkan Gözükara SECourses•3/22/23, 1:35 PM

activate venv

Furkan Gözükara SECourses•3/22/23, 1:36 PM

delete xformers

Furkan Gözükara SECourses•3/22/23, 1:36 PM

pip install xformers== 0.0.17.dev476

kicedz•3/22/23, 1:36 PM

Yes sir. Thank you very much

much love Cok Guzel

Furkan Gözükara SECourses•3/22/23, 1:36 PM

they removed xformers version from there

Garreth210OP•3/22/23, 1:36 PM

do you have a vide I can follow?

GGarreth210 do you have a vide I can follow?

Furkan Gözükara SECourses•3/22/23, 1:37 PM

i have this video for runpod

Furkan Gözükara SECourses•3/22/23, 1:37 PM

https://www.youtube.com/watch?v=oI0GEnrySS0

YouTubeSECourses - Software Engineering Courses

How To Install New DreamBooth Extension On RunPod - Automatic1111 W...

RunPod: https://bit.ly/RunPodIO. Discord : https://bit.ly/SECoursesDiscord. How to install and start using #DreamBooth extension on #RunPod SD Web UI template. 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

DreamBooth extension: ht...

kicedz•3/22/23, 1:38 PM

works as a charm now

thanks to you of course.

Furkan Gözükara SECourses•3/22/23, 1:38 PM

if you support us on patreon i would appreciate very much

trying without the --. I thought that is how the args are being separated

Similar Threads