Software Engineering Courses (SECourses)•3y ago

Hello!! I have a question, why when I try to use the v2 model the samples appear brown?

Jnthn1980•2/12/23, 10:16 PM

Anyone using Invoke Ai, for S.D ? Was it easy to install?

Furkan Gözükara SECourses•2/12/23, 10:19 PM

so i am just back and available now

DDarkestry Awesome Video! @Dr. Furkan Gözükara I'm still trying to create a comic (Asterix...

Furkan Gözükara SECourses•2/12/23, 10:20 PM

i dont know needs a lot of test i think

CCARNUTAURO Amazing video, super professional like always, just a question is there any POD ...

Furkan Gözükara SECourses•2/12/23, 10:20 PM

not sure yet. but could be asked to pod developers

CColored Tonalities @Dr. Furkan Gözükara which video did you do depth map? I want to do for this im...

Furkan Gözükara SECourses•2/12/23, 10:20 PM

i used depth map in this video but it was for text : https://youtu.be/TBq1bhY8BOc

YouTubeSoftware Engineering Courses - SE Courses

How To Generate Stunning Epic Text By Stable Diffusion AI - No Phot...

Discord : https://discord.gg/HbqgGaZVmr. Don't have Photoshop or Artistic skills like me? No need anymore. Use AI to generate EPIC text. 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

Automatic1111 Web UI: https://github.com/AUTOMA...

Furkan Gözükara SECourses•2/12/23, 10:21 PM

however this one can help you significantly : https://youtu.be/YJebdQ30UZQ

YouTubeSoftware Engineering Courses - SE Courses

Transform Your Sketches into Masterpieces with Stable Diffusion Con...

Discord : https://discord.gg/HbqgGaZVmr. In this video, You will see the new amazing Stable Diffusion technology - ControlNet. 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

ControlNet GitHub repo : https://github.com/lllyasviel/Co...

LLain Hi everyone, I downloaded the A1111 Web UI Autoinstaller app and installed it on...

Furkan Gözükara SECourses•2/12/23, 10:21 PM

hi welcome

Furkan Gözükara SECourses•2/12/23, 10:21 PM

you need to apply this

Furkan Gözükara SECourses•2/12/23, 10:21 PM

requirements_versions.txt

Furkan Gözükara SECourses•2/12/23, 10:21 PM

torchsde==0.2.5
safetensors==0.2.7
httpcore<=0.15
fastapi==0.90.1

Furkan Gözükara SECourses•2/12/23, 10:21 PM

add fastapi==0.90.1

Uulisesbt Hello!! I have a question, why when I try to use the v2 model the samples appear...

Furkan Gözükara SECourses•2/12/23, 10:22 PM

could be resolution, yaml and precision problem

Furkan Gözükara SECourses•2/12/23, 10:22 PM

for 2x you need to run training with --no-half

Furkan Gözükara SECourses•2/12/23, 10:22 PM

also make sure to downgrade xformers : https://youtu.be/O01BrQwOd-Q

YouTubeSoftware Engineering Courses - SE Courses

8 GB LoRA Training - Fix CUDA Version For DreamBooth and Textual In...

Our Discord : https://discord.gg/HbqgGaZVmr. This video I am showing how to downgrade CUDA version for proper training and I am showing how to do LoRA training with 8GB GPU.
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

This CUDA ...

FFurkan Gözükara SECourses you need to apply this

FooF•2/12/23, 10:23 PM

hi i have the same error as them and i am confused where do i apply this

FooF•2/12/23, 10:23 PM

sorry im new to all this

FFurkan Gözükara SECourses also make sure to downgrade xformers : https://youtu.be/O01BrQwOd-Q

Pepper•2/12/23, 10:23 PM

this worked for me. do this for sure

Lain•2/12/23, 10:23 PM

Thanks !

FFooF hi i have the same error as them and i am confused where do i apply this

Furkan Gözükara SECourses•2/12/23, 10:27 PM

hi let me give you file to replace

Furkan Gözükara SECourses•2/12/23, 10:28 PM

requirements_versions.txt506B

Furkan Gözükara SECourses•2/12/23, 10:28 PM

replace this file

FooF•2/12/23, 10:30 PM

thank you

FooF•2/12/23, 10:30 PM

that worked

FFurkan Gözükara SECourses for 2x you need to run training with --no-half

ulisesbtOP•2/12/23, 10:39 PM

if i install no half to use v2 model do i have to uninstall it to use v1.5?

FFurkan Gözükara SECourses also make sure to downgrade xformers : https://youtu.be/O01BrQwOd-Q

ulisesbtOP•2/12/23, 10:40 PM

Yeah I've already uninstalled it

Obey•2/12/23, 10:41 PM

hi @Dr. Furkan Gözükara , just finished your selfie --> AI video. Love the results! But I made my prompt "danface" which I think was a mistake. Can I change the instance prompt without retraining the entire model? It's a good model, I just feel I messed up the prompt. Thank you!

Uulisesbt if i install no half to use v2 model do i have to uninstall it to use v1.5?

Furkan Gözükara SECourses•2/12/23, 10:45 PM

no you can use both. --no-half just make it run slower for sd 1.5

OObey hi @Dr. Furkan Gözükara , just finished your selfie --> AI video. Love the resul...

Furkan Gözükara SECourses•2/12/23, 10:45 PM

nope you have to retrain

Obey•2/12/23, 10:50 PM

@Dr. Furkan Gözükara Thank you! Will do

ulisesbtOP•2/12/23, 10:57 PM

I have already used no half and the samples keep appearing brown

Uulisesbt I have already used no half and the samples keep appearing brown

Furkan Gözükara SECourses•2/12/23, 10:58 PM

which model you using

Furkan Gözükara SECourses•2/12/23, 10:58 PM

sd 2.1 512 or 768

ulisesbtOP•2/12/23, 10:58 PM

2.1 512

Furkan Gözükara SECourses•2/12/23, 10:59 PM

are you 100% sure

Furkan Gözükara SECourses•2/12/23, 10:59 PM

your training imges are also 512x512 ?

ulisesbtOP•2/12/23, 10:59 PM

yes

FFurkan Gözükara SECourses your training imges are also 512x512 ?

ulisesbtOP•2/12/23, 10:59 PM

Yes

Furkan Gözükara SECourses•2/12/23, 11:00 PM

you tried to generate imges

Furkan Gözükara SECourses•2/12/23, 11:00 PM

from that model

Furkan Gözükara SECourses•2/12/23, 11:00 PM

from txt2img tab

ulisesbtOP•2/12/23, 11:01 PM

When I use the model to create images, brown images do not appear

ulisesbtOP•2/12/23, 11:01 PM

Only with the samples

Uulisesbt When I use the model to create images, brown images do not appear

Furkan Gözükara SECourses•2/12/23, 11:09 PM

do sd 1.5 work currently

Furkan Gözükara SECourses•2/12/23, 11:09 PM

with same setup

ulisesbtOP•2/12/23, 11:13 PM

When I use the 1.5 model I don't have problems with the samples, only with the v2

Uulisesbt When I use the 1.5 model I don't have problems with the samples, only with the v...

Furkan Gözükara SECourses•2/12/23, 11:15 PM

i can quickly connect your computer to cehck

ulisesbtOP•2/12/23, 11:18 PM

Ok!

Lain•2/12/23, 11:31 PM

I'm just doing a few tests to gain practice. Why is it that when I ask it to generate an image, it creates multiple subjects (people) despite the fact that I ask it "1girl, only" ?

Lain•2/12/23, 11:32 PM

I am taking the commands from https://huggingface.co/gsdf/Counterfeit-V2.5 as an example.

gsdf/Counterfeit-V2.5 · Hugging Face

LLain I'm just doing a few tests to gain practice. Why is it that when I ask it to gen...

Furkan Gözükara SECourses•2/12/23, 11:33 PM

probably related to resolution

Hello!! I have a question, why when I try to use the v2 model the samples appear brown?

Similar Threads

Similar Threads

Similar Threads