CreatorsOk
Furkan Gözükara

Furkan Gözükara

patreon


Furkan Gözükara posts

Massed Compute Installers - Upgrade Automatic1111 - Coupon Code - ControlNet - ADetailer - Facefusion - Reactor & More

This post is obsolete New post : https://www.patreon.com/posts/105735932

This post is obsolete New post : https://www.patreon.com/posts/105735932

-

-

-

Patreon exclusive posts inde...

View Post

Sampling method DPM++ 2M SDE vs DPM++ 3M SDE with Schedule type Uniform vs Karras vs Exponential

Sampling method DPM++ 2M SDE vs DPM++ 3M SDE with Schedule type Uniform vs Karras vs Exponential — I think winner is DPM++ 3M SDE Uniform — Tested on fairly overtrained DreamBooth RealVisXL V4.0 based SDXL model

I wanted to the test newest Sampling method and Schedule types

I think my new favorite is DPM++ 3M SDE Uniform

The tests are concluded on a fairly overtrained RealVisXL V4.0 based Kohya DreamBooth model

Kohya recently made some changes so my older LR values...

View Post

Stable Cascade 1 Click Installer & Advanced Gradio APP For Windows, RunPod, Linux, Massed Compute & Kaggle

Patreon exclusive posts index

Join discord and tell me your discord username to get a special rank : SECourses Discord

16 May 2024 Update:

Shopify / Background Replacement, 1-Click installers for Windows, RunPod, Massed Compute and Kaggle - This App is for replacing background of anything such as Product Images

Patreon exclusive posts index to find our scripts easily, Patreon scripts updates history to see which updates arrived to which scripts and amazing 2024-04-23 21:01:00 +0000 UTC View Post

OneTrainer Fine Tuning vs Kohya SS DreamBooth & Huge Research of OneTrainer's Masked Training

OneTrainer vs Kohya training. Moreover, comparative study of Masked Training effect. Full research.

  • As some of you know, I have been doing huge research on OneTrainer recently to prepare the very best Stable Diffusion training. For this purpose, I have been for days working on the effect of masked training feature of the OneTrainer.

  • Patreon exc...

    View Post

Full Tutorial : How to Clone a Smaller Boot Disk onto a Larger Disk for Free with Clonezilla & Delete Disk Partition

If you want to clone your existing Windows / C drive into a new bigger size disk for free, this tutorial will show you how to use open source Clonezilla to transfer all the data including booting information step by step. So by following this tutorial, you will have exact clone of your disk with including booting and partition information and if disk size is bigger, with bigger disk size. I will also show you how to fix and overcome potential problems during this process and will give you a l...

View Post

Best Text To Speech coqui-ai/TTS Auto Installer, Trainer & Gradio App Scripts

Patreon exclusive posts index

Join discord to get help, chat, discuss and also tell me your discord username to get your special rank : SECourses Discord

Coqui .ai is the very best text to speech open source model.

2024-03-31 00:04:49 +0000 UTC View Post

Compared Effect Of Image Captioning For SDXL Fine-tuning / DreamBooth Training for a Single Person, 10.3 GB VRAM via OneTrainer

Compared Effect Of Image Captioning For SDXL Fine-tuning / DreamBooth Training for a Single Person, 10.3 GB VRAM via OneTrainer, WD14 vs Kosmos-2 vs Ohwx Man

Join discord and tell me your discord username to get a special rank : SECourses Discord

View Post

Now You Can Full Fine Tune / DreamBooth Stable Diffusion XL (SDXL) with only 10.3 GB VRAM via OneTrainer

Now You Can Full Fine Tune / DreamBooth Stable Diffusion XL (SDXL) with only 10.3 GB VRAM via OneTrainer — Both U-NET and Text Encoder 1 is trained — Compared 14 GB config vs slower 10.3 GB Config

Full config and instructions are shared here : https://www.patreon.com/posts/96028218

Used SG161222/RealVisXL_V4.0 as a base model and OneTrainer to train on Windows 10 : 2024-03-26 04:44:32 +0000 UTC View Post

A New Gold Tutorial For RunPod & Linux Users : How To Use Storage Network Volume In RunPod & Latest Version Of Automatic1111 With All ControlNet Models, InstantID & More

A New Gold Tutorial For RunPod & Linux Users : How To Use Storage Network Volume In RunPod & Latest Version Of Automatic1111 With All ControlNet Models, InstantID & More

Tutorial Link > https://www.youtube.com/watch?v=8Qf4x3-DFf4

Join discord and tell me your discord username to get a special rank : 2024-03-24 23:13:21 +0000 UTC View Post

SUPIR is mind blowing - As you use, you get better of it, Comparison video generated via Gradio automatically - Juggernaut-XL_v9 works better with lower Text Guidance Scale

SUPIR is mind blowing - As you use, you get better of it, Comparison video generated via Gradio automatically - Juggernaut-XL_v9 works better with lower Text Guidance Scale

Download link : https://www.patreon.com/posts/supir-1-click-99176057

View Post

SUPIR Full Tutorial + 1 Click 12GB VRAM Windows & RunPod / Linux Installer + Batch Upscale + Comparison With Magnific - SUPIR Starts A New Era

Patreon exclusive posts index

Join discord and tell me your discord username to get a special rank : SECourses Discord

I have dedicated several days, working over 12 hours each day, on SUPIR (Scaling-UP Image Restoration), a cutting-ed...

View Post

Our 1 Click Windows, RunPod (Linux) and Free Kaggle Notebook Instant ID very Advanced Gradio APP Just Got Updated

InstantId is currently the state of the art, very best available workflow to generate stylized amazing images of people without any training.

You can download scripts from here : https://www.patreon.com/posts/97769887

It is literally 1 click install

Here interface of the app you can see all features we have

2024-02-24 00:45:58 +0000 UTC View Post

Stable Diffusion 3 (SD3 - SD 3) - By Stability AI

Stable Diffusion 3 by Stability AI official announced today. It looks like can follow prompts as good as Dall E3 with much better realism and we can fine tune hopefully when released.

Compared Stable Diffusion 3 with Dall E3 Prompt By Prompt In This Video Click To Watch 

https://youtu.be/DJxodszsERo View Post

Full Workflow For Newbie Stable Diffusion Trainers For SD 1.5 Models & SDXL Models Training With DreamBooth & LoRA

If you are new to Stable Diffusion and want to learn easily to train it with very best possible results, this article is prepared for this purpose with everything you need.

Patreon exclusive posts index

Join discord and tell me your discord username to get a special rank : 2024-02-17 01:11:42 +0000 UTC View Post

SORA : Unbelieve New Text To Video AI Model By OpenAI - 37 Demo Videos - Still Can't Believe Real

Patreon exclusive posts index

Join discord and tell me your discord username to get a special rank : SECourses Discord

Video Link : View Post

Sota Image Captioning Model Kosmos-2 Added To Our Scripts Arsenal

Patreon exclusive posts index

Join discord and tell me your discord username to get a special rank : SECourses Discord

Our Scripts arsenal here : 2024-02-15 01:42:40 +0000 UTC View Post

Stable Cascade Prompt Following Is Amazing — This Model Has Huge Potential — High Resolutions Uses Lesser VRAM & Still Very Fast — Check Comments For More Info — Tested 1536x1280 raw images

Patreon exclusive posts index

Join discord and tell me your discord username to get a special rank : SECourses Discord

You can download our scripts here : 2024-02-14 03:17:39 +0000 UTC View Post

Comparison Of Blip2 Captioning Models With 1 Click Windows & RunPod Installer

I have recently coded from a scratch Gradio app for the famous Blip2 captioning models.

1 Click auto installers with instructions are posted here : https://www.patreon.com/posts/sota-image-for-2-90744385

This post also have 1 click Windows & RunPod installers with Gradio interfaces suppor...

View Post

How To Deploy A Pod On RunPod And Verify It Is Working

Patreon exclusive posts index

Join discord and tell me your discord username to get a special rank : SECourses Discord

In this post I am going to show you how to select your template and setup your Pod accurately with the newest inter...

View Post

The Very Best OneTrainer Workflow & Config For SD 1.5 Based Models DreamBooth / Full Fine Tuning

Patreon exclusive posts index

Join discord and tell me your discord username to get a special rank : SECourses Discord

30 March 2024 Update:

Started empirically experimenting for finding the best training hyper parameters for Stable Diffusion 1.5 based models

  • Using Kohya SS GUI as trainer script.
  • Rented 8 GPU machine from RunPod and already doing 8 different trainings right now.
  • If you have any input / feedback / suggestion let me know please.

2024-01-25 00:00:56 +0000 UTC View Post

Comparison of Stable Diffusion XL (SDXL) 0.9 vs 1.0 For DreamBooth Training - Surprising Results


Patreon exclusive posts index

Join discord and tell me your discord username to get a special rank : SECourses Discord

You can download SDXL 0.9 from here : 2024-01-21 19:01:35 +0000 UTC View Post

1 Click Download 160 Very Best Stable Diffusion 1.5 Based (SD 1.5) Models

Join discord and tell me your discord username to get a special rank : SECourses Discord

Patreon exclusive posts index

Login or Register RunPod : https://runpod.io?ref...

View Post

Experimenting With OneTrainer - OneTrainer vs Kohya - Realism vs Stylization - Reg images vs No-Reg images


Experimenting With OneTrainer - OneTrainer vs Kohya - Realism vs Stylization - Reg images vs No-Reg images

I feel like reg images using in OneTrainer improved realism and also lessened the overfitting as expected

OneTrainer realism looks better than Kohya meanwhile Kohya generalization looks better

Download attached images to see full resolution

OneTrainer Stable Diffusion XL (SD...

View Post

60 Generative AI Tutorials Stable Diffusion, SDXL, PixArt, Kandinsky, DeepFloyd IF, Voice Cloning, LoRA, DreamBooth, Training, Fine Tuning

Our 6000+ members Discord : https://discord.com/servers/software-engineering-courses-secourses-772774097734074388

Our Patreon : https://www.patreon.com/SECourses

Our channel : 2024-01-02 01:33:32 +0000 UTC View Post

Viral Paper Tested MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model — Actual Full Tutorial With Released Code & Models

Patreon exclusive posts index

Join discord and tell me your discord username to get a special rank : SECourses Discord

🌟 Welcome to this comprehensive tutorial video where I guide you through the process of installing and using Magi...

View Post

Generate Photos Of Yourself In Different Cities & Different Fancy Suits With SDXL DreamBooth Training For Free

Patreon exclusive posts index

Join discord and tell me your discord username to get a special rank : SECourses Discord

To train this model I have used Stable Diffusion XL (SDXL) 1.0 Base model. I still find base model best for realism....

View Post

DreamBooth Training on SDXL Anime Model & Comparing Ground Truth Regularization Images Effect

Patreon exclusive posts index

Join discord and tell me your discord username to get a special rank : SECourses Discord

It was requested of me to test ground truth Regularization / Classification images effect during Stable Diffusion XL...

View Post

Batch Image Metadata Generator - Extremely Useful For Automatic1111 SD Web UI

Patreon exclusive posts index

Join discord and tell me your discord username to get a special rank : SECourses Discord

Let's say you want to see META data of the generated images quickly.

Loading them into the PNG info is both sl...

View Post