Software Engineering Courses (SECourses)•3y ago

I'm trying to do an exorcist style image, with the girl kind of upside down, but the face wont attac

I'm trying to do an exorcist style image, with the girl kind of upside down, but the face wont attach or make the same pose, any advice on how to do this

Kallamamran•11/30/23, 10:36 PM

I'm impressed with PixArt, but I can't really use it for anything, so I'm sticking with A1111 and SDXL for now

AAIGambino I'm trying to do an exorcist style image, with the girl kind of upside down, but...

Kallamamran•11/30/23, 10:40 PM

Stabel Diffusion sucks at up-side-down!

Kallamamran•11/30/23, 10:41 PM

Try in Dalle-3 and then inpaint in A1111

KKallamamran So when do we get models with higher quality I wonder. Focus seem to be on speed

Furkan Gözükara SECourses•11/30/23, 11:19 PM

i agree. all recent ones focuses on speed

MMishroom Hi! I have some issues with Dreambooth Kohya, I tried to start learning but it s...

Evan•12/1/23, 12:42 AM

has anyone tried realistic vision v6 yet?

Rae•12/1/23, 1:02 AM

@Dr. Furkan Gözükarahigher quality than what? good prompts can generate insane photoreal pictures with 1.5, SDXL is even beyond that, what else in quality do we need? we need easier ways to finetune, tag, and prompt and generate.

Rae•12/1/23, 1:03 AM

it looks like most attention is at getting these photos to videos, every single day you can see the videos getting better and better.

AIGambinoOP•12/1/23, 2:22 AM

Any idea why my inpaint isn't inpainting my ohwx man?

AAIGambino Any idea why my inpaint isn't inpainting my ohwx man?

Furkan Gözükara SECourses•12/1/23, 8:35 AM

make it fill with latent noise

virginia•12/1/23, 9:31 AM

fooocuse does not work well

AIGambinoOP•12/1/23, 4:42 PM

If training a style, is that any different than training a person?

AIGambinoOP•12/1/23, 4:42 PM

Like if I want a certain type of interior of a home, can I just train all images on that style of interior of a home?

GravNolan•12/1/23, 4:50 PM

hi all
i have a problem
i have made a community pod and whenever i stop and came back it is gone, means no Gpu
so, i have make a secure but this time too, it is gone. then what is the sense of secure cloud.
what should i do to make my pod accessible after reopening, i am creating large amount of data and when i come back after sleep, i have to redo it. please help

Lorelai AI•12/1/23, 8:11 PM

Question, the Patreon regularization images, is there a batch for Anime or can you use realistic?

AIGambinoOP•12/1/23, 10:44 PM

Is there something new with IPAdapter going on or what? I'm seeing tons of temporally consistent videos coming out today

AIGambinoOP•12/1/23, 10:50 PM

I see people are using ipadapter and animatediff to create some crazy consistent animations but no workflows out there with it

AIGambinoOP•12/1/23, 11:05 PM

And how do we make sure our character isnt always looking away in our scenes

GGravNolan hi all i have a problem i have made a community pod and whenever i stop and came...

Furkan Gözükara SECourses•12/1/23, 11:42 PM

you need to make a network volume

Furkan Gözükara SECourses•12/1/23, 11:42 PM

mount it to any available pod from secure cloud

Furkan Gözükara SECourses•12/1/23, 11:42 PM

that is the way of keeping data

LLorelai AI Question, the Patreon regularization images, is there a batch for Anime or can y...

Furkan Gözükara SECourses•12/1/23, 11:42 PM

realistic

Furkan Gözükara SECourses•12/1/23, 11:43 PM

actually real images

Furkan Gözükara SECourses•12/1/23, 11:43 PM

let me show

Furkan Gözükara SECourses•12/1/23, 11:44 PM

Furkan Gözükara SECourses•12/1/23, 11:44 PM

AAIGambino Is there something new with IPAdapter going on or what? I'm seeing tons of tempo...

Furkan Gözükara SECourses•12/1/23, 11:44 PM

no idea yet

AMMAR |COTE|•12/2/23, 12:03 AM

Hi everyone. I needed a little help I have a rtx 3070 ti which kind of training suits my pc specs. Specs are ryzen 7 5800x 32gb 3200mhz ram galax rtx3070ti i am trying to teach stable diffusion my face by using textual embedding training but its too slow for some reason even with xformers on.

AMMAR |COTE|•12/2/23, 12:04 AM

AMMAR |COTE|•12/2/23, 12:05 AM

AMMAR |COTE|•12/2/23, 12:07 AM

It’s well over 4 hours and i have completed only 624 steps with the settings shown in photos

Rae•12/2/23, 12:29 AM

anyone adept at training fashion lora / dreambooth?

FFurkan Gözükara SECourses realistic

Lorelai AI•12/2/23, 12:38 AM

Thanks for the help I joined the Patreon. I’ll be using most of my time training character Loras. I’ve done decent so far but know I can do better. I don’t necessarily need the notebook I have a computer with a 4090 and one with 4070 and each have 32gb of ram. I’m going to try your stuff, my concern with anime and regularization images using realistic people is anime makes the adult women look like children. I use girl as the class prompt instead of woman for that reason. I’ve never tried woman though so I wouldn’t know the results

shortdwarf•12/2/23, 12:41 AM

Does anyone know which video talks about how to filter results using face recognition? I'm about to go looking for it but figured I'd ask first

ogkai•12/2/23, 8:23 AM

@Dr. Furkan Gözükara Furkan hocam is it possible to train SDXL Turbo with kohya? I tried one but after the training turbo model just became as slow as sdxl1.0 :x

Digital [Starburst]•12/2/23, 9:10 AM

So Speccy and Sys Info do not detect the full amount of VRAM your card has. It always detects 4 GB of VRAM regardless of how much your card has. Is there a setting I'm missing here?

Digital [Starburst]•12/2/23, 9:10 AM

I now have 12 GB of VRAM installed.

Digital [Starburst]•12/2/23, 9:11 AM

I believe my 3060ti had 8 GB not 4 GB.

Niklas•12/2/23, 2:15 PM

Hi, is it possible somehow to morph png images in stable diffusion?

DDigital [Starburst]So Speccy and Sys Info do not detect the full amount of VRAM your card has. It ...

Lorelai AI•12/2/23, 4:14 PM

Could be a number of things but making sure you have an updated bios on your motherboard could be it

AIGambinoOP•12/2/23, 6:18 PM

Can someone share their settings in dreambooth for sd 1.5

B0nd•12/2/23, 6:28 PM

How can I do inpainting with SDXL in automatic1111?

ZZono50 What's the best way to upscale human photos to get the best detail?

Maelstromboni•12/2/23, 7:21 PM

Did you find a proper workflow for this? I tried using @Dr. Furkan Gözükara 's Controlnet scripting, thinking it was the most comprehensive, but was still getting blurry or "smudged" results when attempting to upres.

AAMMAR |COTE|Hi everyone. I needed a little help I have a rtx 3070 ti which kind of training ...

Furkan Gözükara SECourses•12/2/23, 8:27 PM

hello welcome. how much vram your gpu has

LLorelai AI Thanks for the help I joined the Patreon. I’ll be using most of my time training...

Furkan Gözükara SECourses•12/2/23, 8:27 PM

you can give it a try

Furkan Gözükara SECourses•12/2/23, 8:28 PM

rtx 4090 is amazing

Sshortdwarf Does anyone know which video talks about how to filter results using face recogn...

Furkan Gözükara SECourses•12/2/23, 8:28 PM

here https://youtu.be/343I11mhnXs

YouTubeSECourses

How To Find Best Stable Diffusion Generated Images By Using DeepFac...

If you are also getting tired of trying to find good images among thousands of generated images you don't have to anymore. By using #DeepFace AI library, you can sort images by their similarity to your target images and quickly find the best Stable Diffusion #DreamBooth LoRA trained model generated images. I am explaining everything step by step...

Furkan Gözükara SECourses•12/2/23, 8:28 PM

the scripts are further improved right now

Oogkai @Dr. Furkan Gözükara Furkan hocam is it possible to train SDXL Turbo with kohya?...

Furkan Gözükara SECourses•12/2/23, 8:28 PM

i am yet to research

DDigital [Starburst]So Speccy and Sys Info do not detect the full amount of VRAM your card has. It ...

Furkan Gözükara SECourses•12/2/23, 8:29 PM

yes it is 8 gb

Furkan Gözükara SECourses•12/2/23, 8:29 PM

open cmd and type nvidia-smi

I'm trying to do an exorcist style image, with the girl kind of upside down, but the face wont attac

Similar Threads