Furkan Gözükara

Image Folders Merger For Easy Comparison - Merge Images Side by Side - Useful to Compare Upscaling and Such Effect

Patreon exclusive posts index to find our scripts easily, Patreon scripts updates history to see which updates arrived to which scripts and amazing ...

20 New SDXL Fine Tuning Tests and Their Results (Better Workflow Obtained and Published)

I have been keep testing different scenarios with OneTrainer for Fine-Tuning SDXL on my relatively bad dataset. My training dataset is deliberately bad so that you can easily collect a better one and surpass my results. My dataset is bad because it lacks expressions, different distances, angles, different clothing and different backgrounds.

Patreon exclusive posts index to find our scripts easily, 2024-08-13 22:04:04 +0000 UTC View Post

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

Patreon exclusive posts index to find our scripts easily, Patreon scripts updates history to see which updates arrived to which scripts and amazing ...

BiRefNet State Of The Art Newest Very Best Background Batch Remover APP

BiRefNet is the very best state of the art newest published background removal open source model. It is way better than BRIA RMBG V1.4 that we knew as best.

Patreon exclusive posts index to find our scripts easily, Patreon scripts updates history to see which updates arri...

Batch size 30 AdamW vs Batch Size 1 Adafactor SDXL Training Comparison

I was hanging OneTrainer Discord yesterday and saw one of the very old and experienced user comment. He was saying AdamW is better than Adafactor. So I have asked his config which you can see here : https://gist.github.com/FurkanGozukara/5e9ee7d2b2070abb9a173dab342e1221

I have done my AdamW training with this config on RTX A6000 GPU on Massed Compute. Used batch size 30 since I had my regular 15 training images and every epoc...

FLUX Local & Cloud Tutorial With SwarmUI - FLUX: The Pioneering Open Source txt2img Model Outperforming Midjourney & Others - FLUX: The Anticipated SD3

🔗 Comprehensive Tutorial Video Link ▶️ https://youtu.be/bupRePUOA18

FLUX represents a groundbreaking achievement as the first open source txt2img model to genuinely surpass and generate superior quality images with enhanced prompt adherence compared to #Midjourney, Adobe Firefly, Leonardo Ai, Playground Ai, Stable Diffusion, SDXL, SD3, and Dall E3. #FLUX, developed by Black Forest Labs, boasts a team primarily consisting of the original #StableDiffusion creator...

Kling AI Video Has Now Been Released Globally (All Nations), Is Free to Use, and Is Absolutely Astonishing - Complete Guide

You've likely encountered those incredible AI-generated videos. Well, the moment has come. The renowned Kling AI is now accessible worldwide at no cost. In this instructional video, I'll guide you through the process of signing up for Kling AI for free using just an email address, and demonstrate its remarkable text-to-video animation, image-to-video animation, text-to-image, and image-to-image capabilities. This video will present unfiltered results, giving you an accurate understanding of the model's genuine quality and abilities, unlike t...

Real-Time Webcam DeepFake / Face Swapping with Rope Pearl Live - Simple Installation and Effortless Usage

Full Tutorial Link : https://youtu.be/whDt36YwEKQ

This video demonstrates the latest Deepfake / Face Swapping application, Rope Pearl, which now offers TensorRT support and real-time webcam processing capabilities. I'll guide you through the straightforward installation process for Rope Pearl Live on your computer and show you how to utilize its webcam Deepfake feature. The inst...

I Am Researching Multi-GPU Training Speed Difference

Rented this machine on Massed Compute to test Stable Diffusion XL training speed difference with Kohya SS GUI on a 8x A100 (SXM4) machine and see the difference of multi-GPU training SXM vs PCIe linked GPUs

Hopefully will update this post as I get more info.

Update 1

Single GPU works with Batch size 7 but more than 1 GPU fails

Reported Kohya : 2024-07-23 00:13:46 +0000 UTC View Post

Extracted LoRA Quick Test

I did a test for one of our supporters. Used one of my older quite a bit overtrained DreamBooth model

Extracted LoRA as you can see yields almost perfect quality. Yes subtly changed but you can get quality with more generations

LivePortrait Static Image to Video or Video to Video State of The Art AI Model

LivePortrait AI: Transform Static Photos into Talking Videos. Now Supports Video-to-Video Conversion and Superior Expression Transfer at Incredible Speed

A new tutorial is anticipated to showcase the latest changes and features in V3, which introduces Video-to-Video capability and other enhancements.

For those seeking a one-click installation of the LivePortrait open-source, zero-shot image-to-animation application on Windows for local use, this tutorial is essential. It introduces the cutting-edge image-to-animation open-source ...

We Got a Job Offer in SECourses Discord Channel Related to AI (Stable Diffusion)

This is kind of announcement sharing. I think the offer looks decent.

For who doesn’t know our channel here : https://discord.com/servers/software-engineering-courses-secourses-772774097734074388

The job offer is in ai-related-job-offers sub-channel

Excellent Tips for LoRA Training

Patreon exclusive posts index to find our scripts easily

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

Please also Star, Watch and Fork our 2024-07-19 12:24:34 +0000 UTC View Post

How to Get Installation Logs and How to Change Hugging Face Cache Folder

Patreon exclusive posts index to find our scripts easily

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

Please also Star, Watch and Fork our 2024-07-19 09:28:01 +0000 UTC View Post

Auto Windows Installer For Würstchen: Fast Diffusion for Image Generation

Patreon exclusive posts index to find our scripts easily

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

Please also Star, Watch and Fork our 2024-07-18 21:00:00 +0000 UTC View Post

Fooocus Stable Diffusion Web UI Kaggle NoteBook

Patreon exclusive posts index

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

Full tutorial video for Fooocus : https://youtu.be/jHTkVm2mcfs

How to use NGROK 2024-06-24 12:29:00 +0000 UTC View Post