Software Engineering Courses (SECourses)•3y ago

@Dr. Furkan Gözükara my model trained on realistic was unable to get my face at all checkpoints. I d

@Dr. Furkan Gözükara my model trained on realistic was unable to get my face at all checkpoints. I didn't use Lion but 8bit Adam with the settings for 12GB Vram.

PelolisuOP•12/9/23, 12:09 AM

images like this, and duplicated, came close but it's not me.

PPelolisu @Dr. Furkan Gözükara my model trained on realistic was unable to get my face at ...

Furkan Gözükara SECourses•12/9/23, 12:27 AM

you can also try our Kaggle SDXL DreamBooth

Furkan Gözükara SECourses•12/9/23, 12:27 AM

it will be probably better

PelolisuOP•12/9/23, 12:35 AM

ok i will but i have a RTX 3060 Ti 8Gb + 16GB shared virtual

PelolisuOP•12/9/23, 12:35 AM

Kaggle is better graphic card?

PPelolisu Kaggle is better graphic card?

Furkan Gözükara SECourses•12/9/23, 1:00 AM

yep

Furkan Gözükara SECourses•12/9/23, 1:00 AM

it is 15 gb

Furkan Gözükara SECourses•12/9/23, 1:00 AM

shared vram will be ultra slow

PelolisuOP•12/9/23, 1:02 AM

i found that the problem of twins is often

PelolisuOP•12/9/23, 1:02 AM

in realist vision

PelolisuOP•12/9/23, 1:03 AM

because the better resolution is 512X768 but i have used 1024x768

PelolisuOP•12/9/23, 1:07 AM

i used 5.1 but i have 2.0 too

PelolisuOP•12/9/23, 1:52 AM

with 8bit adam and xformers my training took 2:55hs now with lion and without xformers it will take almost 7 hours with 20 images in the dataset i will try kaggle

PelolisuOP•12/9/23, 1:55 AM

but I will also test how it performs on 8bit adam locally at 512x768 and then using a 4x upscaler to generate the images.

PPelolisu after uploading the image, the video and the pose are expected to appear, correc...

thewingag•12/9/23, 2:44 AM

did u install Magic in comfyui? sr, last night, i go to sleep? 1AM in my country

PelolisuOP•12/9/23, 2:45 AM

Yes, I put it to run but it doesn't show any progress. It was in the attention message, can you tell if it takes a long time for the result to come?

PelolisuOP•12/9/23, 2:46 AM

I had to look for an example openpose video to use with my image, but the result was black, I think it takes a long time to process, but it also didn't give any error messages.

PelolisuOP•12/9/23, 2:49 AM

I need a comfyUI tutorial with Magic Animate to see if I didn't do anything wrong.

thewingag•12/9/23, 2:53 AM

ok.

Pflanzen die Tanzen•12/9/23, 4:22 AM

A short story for my niece and nephews:

Tools used:

Stable diffusion
GPT-4

The main goals were these:

give my niece a nice present
create a coherent story
create coherent characters

All in all a rather straight forward process, just putting together several techniques I've learned in the past year.

FiveSAI•12/9/23, 4:35 AM

Even Faster SDXL Dreambooth Training Full BF16 Enabled

FiveSAI•12/9/23, 4:36 AM

Still further testing but results so far amazing

PelolisuOP•12/9/23, 5:03 AM

I'm crying with 8gb vram haha

Someone.in.144p•12/9/23, 5:24 AM

same heh

FFurkan Gözükara SECourses you need to give accurate folder path and it will work

Someone.in.144p•12/9/23, 5:25 AM

it worked :DDDD, thank you so much for the help man, u savd my school project

Someone.in.144p•12/9/23, 5:25 AM

PPelolisu Click to see attachment

thewingag•12/9/23, 8:17 AM

hmm, about 100Gb lol :v

virginia•12/9/23, 11:04 AM

@Pelolisu I usually get exact dozens of images from hundreds of or even thousands of created images on the basis of trained lora, Furkan said dreambooth checkpoint is better than lora. I have not tried yet. If a object is too detailed and styled, lora results are not good, time wasting, many images are not to the standards you require.

PPflanzen die Tanzen A short story for my niece and nephews: Tools used: 1. Stable diffusion 2. ...

Furkan Gözükara SECourses•12/9/23, 11:36 AM

nice

Furkan Gözükara SECourses•12/9/23, 11:37 AM

1 picture it is merged with horse though :d

FFiveSAI Even Faster SDXL Dreambooth Training Full BF16 Enabled

Furkan Gözükara SECourses•12/9/23, 11:37 AM

huge. did you do anything special?

FFurkan Gözükara SECourses 1 picture it is merged with horse though :d

Pflanzen die Tanzen•12/9/23, 11:55 AM

this one? The legs are under the wings

it's supposed to be like that

Pflanzen die Tanzen•12/9/23, 11:56 AM

Or this one, which is also intended.
The protagonist turns into a unicorn and then back into a human.

FFurkan Gözükara SECourses yes i have installer

Sandstormleader•12/9/23, 12:53 PM

i think that's the one i still have installed right now, was hoping there was a working sdlx automatic1111 dreambooth at this point

Superdrew907•12/9/23, 1:09 PM

Hey jet Thank u guys so much

SSandstormleader i think that's the one i still have installed right now, was hoping there was a ...

Furkan Gözükara SECourses•12/9/23, 1:26 PM

the guy left developing

FFurkan Gözükara SECourses the guy left developing

Sandstormleader•12/9/23, 1:26 PM

sad news

Furkan Gözükara SECourses•12/9/23, 1:27 PM

ye he is working for another ai company

Furkan Gözükara SECourses•12/9/23, 1:27 PM

doing similar stuff i think

Vvirginia @Pelolisu I usually get exact dozens of images from hundreds of or even thousand...

PelolisuOP•12/9/23, 3:17 PM

I think the time of 2:55 hours for my training is acceptable with an 8GB RAM GPU. However, the result of the training still didn't satisfy me, but as I'm still learning stable diffusion it may be that I haven't yet set the prompt parameters correctly. I will also try to run it on Kaggle as Furkan suggested to compare the results. I think I can use a Lion optmizer there.

PelolisuOP•12/9/23, 3:19 PM

I will also do some experiments with LoRA

xlads•12/9/23, 5:09 PM

@Dr. Furkan Gözükara or anyone eles in here is there a course on how to do the deepfakes video ?

Lorelai AI•12/9/23, 7:04 PM

I'm trying to get a baseline for SDXL Lora time frames. I see a bunch of different times about train a lora in 30 minutes etc but my use case is different. Most of my SDXL Lora trainings are 12-18 hours. Now I know this has to do in part im using 768X1344. Adjusting Network Dimm seems to reduce and learning rate seems to have an impact on the time but my concern quality will be impacted if I adjust these. My Anime models are coming out great despite the time. My person models are Meh despite following the guides and using the regularization images but I believe I missed something. I'm on an RTX 4090. Any insight?

FFurkan Gözükara SECourses huge. did you do anything special?

FiveSAI•12/9/23, 7:29 PM

Yep im using pagedadamw8bit, similar results to adafactor, still testing, got about 50 more trainings to test, will try prodigy next

LLorelai AI I'm trying to get a baseline for SDXL Lora time frames. I see a bunch of differe...

FiveSAI•12/9/23, 7:30 PM

can you share your json file, also are you using the latest nvidia drivers with Sysmem fallback policy

FFiveSAI can you share your json file, also are you using the latest nvidia drivers with ...

Lorelai AI•12/9/23, 7:33 PM

That’s a good idea to check the drivers. I’ll grab the json when I have a moment

FiveSAI•12/9/23, 7:33 PM

i also have a 4090 my trainings are usually 35 mins to 2 hours depending

Lorelai AI•12/9/23, 7:34 PM

What settings are you using? I know that’s a large request. I’m all over the place even with the trainings and I’m still new.

FiveSAI•12/9/23, 7:35 PM

depends i use different settings, but usually adafactor and the extra arguments with the gradient checkpointing and sometimes xformers not always.

@Dr. Furkan Gözükara my model trained on realistic was unable to get my face at all checkpoints. I d

Similar Threads