DEV Community

Furkan Gözükara profile picture

Furkan Gözükara

PhD Computer Engineer. Lecturer. AI, Technology, Science, Life, News, Tutorials, Guides, LLMs, Stable Diffusion, SDXL, LoRA, Training, TTS, Voice Cloning - https://www.linkedin.com/in/furkangozukara

Education

Computer Engineering PHD in Cukurova University

Work

Lecturer at SECourses

More expansive GPU doesn’t mean better always actually in many case in AI. Here a great example.

More expansive GPU doesn’t mean better always actually in many case in AI. Here a great example.

6
Comments 1
1 min read

Want to connect with Furkan Gözükara?

Create an account to connect with Furkan Gözükara. You can also sign in below to proceed if you already have an account.

Already have an account? Sign in
OneTrainer Fine Tuning vs Kohya SS DreamBooth & Huge Research of OneTrainer’s Masked Training

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

5
Comments
39 min read
Finding Best Training Hyper Parameters / Configuration Is Neither Cheap Nor Easy

Finding Best Training Hyper Parameters / Configuration Is Neither Cheap Nor Easy

5
Comments
1 min read
Full Tutorial : How to Clone a Smaller Boot Disk onto a Larger Disk for Free with Clonezilla & Delete Disk Partition

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

7
Comments
5 min read
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

5
Comments
22 min read
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

6
Comments
16 min read
A New Gold Tutorial For RunPod & Linux Users : How To Use Storage Network Volume In RunPod & Latest Version Of Automatic1111

A New Gold Tutorial For RunPod & Linux Users : How To Use Storage Network Volume In RunPod & Latest Version Of Automatic1111

5
Comments
4 min read
SUPIR Full Tutorial + 1 Click 12GB VRAM Windows & RunPod / Linux Installer + Batch Upscale + Comparison With Magnific

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

5
Comments
9 min read
Compared Stable Diffusion 3 with Dall-E3 and Results Are Mind Blowing - Prompt Following of SD3 is Next Level

Compared Stable Diffusion 3 with Dall-E3 and Results Are Mind Blowing - Prompt Following of SD3 is Next Level

6
Comments
1 min read
Full Workflow For Newbie Stable Diffusion Trainers For SD 1.5 Models & SDXL Models Training With DreamBooth & LoRA

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

Comments
12 min read
SORA : Unbelieve New Text To Video AI Model By OpenAI - 37 Demo Videos - Still Can’t Believe Real

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

6
Comments 1
16 min read
Sota Image Captioning Model Kosmos-2 Added To Our Image Captioning Scripts Arsenal

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

6
Comments
1 min read
Stable Cascade Prompt Following Is Amazing — This Model Has Huge Potential — High Resolutions Uses Lesser VRAM

Stable Cascade Prompt Following Is Amazing — This Model Has Huge Potential — High Resolutions Uses Lesser VRAM

5
Comments
3 min read
Comparison Of Blip2 Captioning Models With 1 Click Windows & RunPod Installer

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

6
Comments
3 min read
Beware When Buying M2 NVMe SSDs: Netac NV7000, Kioxia Exceria Plus G2, Kingston and Sandisk Compared

Beware When Buying M2 NVMe SSDs: Netac NV7000, Kioxia Exceria Plus G2, Kingston and Sandisk Compared

5
Comments
3 min read
How To Deploy A Pod On RunPod And Verify It Is Working

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

5
Comments 2
4 min read
How to make GPT-4 to write a good code for you

How to make GPT-4 to write a good code for you

6
Comments
2 min read
Next Level SD 1.5 Based Models Training - Took Me 70+ Empirical Trainings To Find Out

Next Level SD 1.5 Based Models Training - Took Me 70+ Empirical Trainings To Find Out

6
Comments
3 min read
Started empirically experimenting for finding the best training hyper parameters for Stable Diffusion 1.5 based models

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

5
Comments
1 min read
Comparison of Stable Diffusion XL (SDXL) 0.9 vs 1.0 For DreamBooth Training - Surprising Results

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

7
Comments 2
6 min read
1 Click Download 160 Very Best Stable Diffusion 1.5 Based (SD 1.5) Models

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

5
Comments
1 min read
Deepspeed Wheels For Windows

Deepspeed Wheels For Windows

5
Comments
1 min read
Instantly Transfer Face By Using IP-Adapter-FaceID: Full Tutorial & GUI For Windows, RunPod & Kaggle

Instantly Transfer Face By Using IP-Adapter-FaceID: Full Tutorial & GUI For Windows, RunPod & Kaggle

6
Comments
3 min read
Experimenting With OneTrainer - OneTrainer vs Kohya - Realism vs Stylization - Reg img effect

Experimenting With OneTrainer - OneTrainer vs Kohya - Realism vs Stylization - Reg img effect

5
Comments
1 min read
OneTrainer Stable Diffusion XL (SDXL) Fine Tuning Best Presets

OneTrainer Stable Diffusion XL (SDXL) Fine Tuning Best Presets

5
Comments
1 min read
How To Change Default Python On A Linux Machine

How To Change Default Python On A Linux Machine

5
Comments 2
1 min read
60 Generative AI Tutorials Stable Diffusion, SDXL, PixArt, Voice Cloning, LoRA, DreamBooth, Training, Fine Tuning

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

6
Comments
15 min read
Viral Paper Tested MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model

Viral Paper Tested MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model

5
Comments
3 min read
How To Use GPT-4 To Fix Video Transcription

How To Use GPT-4 To Fix Video Transcription

5
Comments
1 min read
Le Tour Jurassic Park with Stable Diffusion XL (SDXL) DreamBooth Training

Le Tour Jurassic Park with Stable Diffusion XL (SDXL) DreamBooth Training

5
Comments
3 min read
Generate Photos Of Yourself In Different Cities & Different Fancy Suits With SDXL DreamBooth Training For Free

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

8
Comments
5 min read
DreamBooth Training on SDXL Anime Model & Comparing Ground Truth Regularization Images Effect

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

5
Comments
9 min read
Tested 275 SDXL Prompt Styles of Fooocus on Automatic1111 SD Web UI With My For Realism Overtrained DreamBooth Model

Tested 275 SDXL Prompt Styles of Fooocus on Automatic1111 SD Web UI With My For Realism Overtrained DreamBooth Model

5
Comments
11 min read
275 Amazing Prompt Styles Of Fooocus For Automatic1111 SD Web UI

275 Amazing Prompt Styles Of Fooocus For Automatic1111 SD Web UI

5
Comments
1 min read
Comparison Between SDXL Full DreamBooth Training vs LoRA Training vs LoRA Extraction

Comparison Between SDXL Full DreamBooth Training vs LoRA Training vs LoRA Extraction

5
Comments
4 min read
Trained a new Stable Diffusion XL (SDXL) Base 1.0 DreamBooth model. Used my medium quality training images dataset.

Trained a new Stable Diffusion XL (SDXL) Base 1.0 DreamBooth model. Used my medium quality training images dataset.

6
Comments
2 min read
Essential AI Tools and Libraries: A Guide to Python, Git, C++ Compile Tools, FFmpeg, CUDA, PyTorch

Essential AI Tools and Libraries: A Guide to Python, Git, C++ Compile Tools, FFmpeg, CUDA, PyTorch

5
Comments
4 min read
Which Style Training Model Looking Best Do You Think?

Which Style Training Model Looking Best Do You Think?

5
Comments
1 min read
FreeInit : Bridging Initialization Gap in Video Diffusion Models - Utilizing AnimateDiff

FreeInit : Bridging Initialization Gap in Video Diffusion Models - Utilizing AnimateDiff

Comments
1 min read
When You Purchase A New Disk Make Sure To Verify They Are Actually New

When You Purchase A New Disk Make Sure To Verify They Are Actually New

Comments
1 min read
ChatGPT-4 Output Context Size Is Still Only 2048 Tokens!

ChatGPT-4 Output Context Size Is Still Only 2048 Tokens!

Comments
1 min read
Speed comparison between Torch + CUDA + xFormers versions and TensorRT vs xFormers for Stable Diffusion XL (SDXL)

Speed comparison between Torch + CUDA + xFormers versions and TensorRT vs xFormers for Stable Diffusion XL (SDXL)

Comments
1 min read
Google Gemini is really terrible against GPT-4

Google Gemini is really terrible against GPT-4

Comments
1 min read
Google Gemini AI 🤯 Full Video - The Only Competitor Against ChatGPT / GPT-4 - #1 On Benchmarks

Google Gemini AI 🤯 Full Video - The Only Competitor Against ChatGPT / GPT-4 - #1 On Benchmarks

Comments
3 min read
PIXART-α : First Open Source Rival to Midjourney - Better Than Stable Diffusion SDXL - Full Tutorial

PIXART-α : First Open Source Rival to Midjourney - Better Than Stable Diffusion SDXL - Full Tutorial

5
Comments
3 min read
Robocopy command that copies all files and folders from Folder A to Folder and How to cipher zero fill secure erase

Robocopy command that copies all files and folders from Folder A to Folder and How to cipher zero fill secure erase

Comments
3 min read
Massive 4K Resolution Woman & Man Class Ground Truth Stable Diffusion Regularization Images Dataset

Massive 4K Resolution Woman & Man Class Ground Truth Stable Diffusion Regularization Images Dataset

Comments
1 min read
Automate Testing of 115 Clip + 5 Caption Models to Find the Best Captions for Your Image Dataset

Automate Testing of 115 Clip + 5 Caption Models to Find the Best Captions for Your Image Dataset

Comments
1 min read
How To Do Stable Diffusion XL (SDXL) DreamBooth Training For Free - Utilizing Kaggle - Easy Tutorial

How To Do Stable Diffusion XL (SDXL) DreamBooth Training For Free - Utilizing Kaggle - Easy Tutorial

Comments
4 min read
Concept Sliders: LoRA Adaptors for Precise Control in Diffusion Models

Concept Sliders: LoRA Adaptors for Precise Control in Diffusion Models

Comments
3 min read
Mass Corrupt or Broken Images Finder / Mover Script

Mass Corrupt or Broken Images Finder / Mover Script

Comments
1 min read
Auto installer script for Fooocus Web UI on RunPod & Full Tutorial

Auto installer script for Fooocus Web UI on RunPod & Full Tutorial

Comments
1 min read
Gender Classifier - Low Colors & Multiple Face Remover - Stable Diffusion Training Images Preprocessor

Gender Classifier - Low Colors & Multiple Face Remover - Stable Diffusion Training Images Preprocessor

Comments
1 min read
State Of The Art (SOTA) — The Very Best Gender Classifier — 1 Click Install & Run

State Of The Art (SOTA) — The Very Best Gender Classifier — 1 Click Install & Run

Comments
1 min read
If you want to use ChatGPT — GPT-4 Classic version here how to use

If you want to use ChatGPT — GPT-4 Classic version here how to use

Comments
1 min read
This Is How I Prepare The Very Best Regularization / Classification Images Dataset For Stable Diffusion

This Is How I Prepare The Very Best Regularization / Classification Images Dataset For Stable Diffusion

Comments
1 min read
How to make your own GPT with new ChatGPT / GPT-4? Tutorial - Guide

How to make your own GPT with new ChatGPT / GPT-4? Tutorial - Guide

Comments
1 min read
The Very Best Workflow For SDXL DreamBooth / Full Fine Tuning With Text Encoder Training

The Very Best Workflow For SDXL DreamBooth / Full Fine Tuning With Text Encoder Training

Comments
1 min read
OpenAi’s new Consistency VAE is not good so far — tested by AUTOMATIC1111 himself

OpenAi’s new Consistency VAE is not good so far — tested by AUTOMATIC1111 himself

Comments
1 min read
🤯 Build Your Own Custom GPT with ChatGPT — Tutorial — Upload Document As A Knowledge Base — EASY

🤯 Build Your Own Custom GPT with ChatGPT — Tutorial — Upload Document As A Knowledge Base — EASY

Comments
2 min read
loading...