Furkan Gözükara

1-Click Automatic Installers for Hunyuan3D-1 Text to 3D and Image to 3D SOTA Model, Install on Windows, RunPod and Massed Compute

Patreon exclusive posts index to find our scripts easily, 2024-12-11 18:52:00 +0000 UTC View Post

How to Convert Your Trained FLUX, Stable Diffusion 3.5, SDXL and Other LoRAs Into FP8 and FP16 to Save Huge Space With Kohya GUI

Patreon exclusive posts index to find our scripts easily, 2024-12-10 10:01:00 +0000 UTC View Post

For who can't subscribe due to being blocked, payment restriction etc, I accept crypto and I will gift you membership via crypto coins

I recently found out that I can gift you membership here.

So I will accept any crypto payment and gift you membership if you are unable to subscribe via normal way.

Normal way subscription is of course the best action.

usdt : 0xc9b32f4a799372f828c9ac04655670738e7481c7 - E...

Simple prompt 2x latent upscaled FLUX - Fine Tuning / DreamBooth Images - Can be trained on as low as 6 GB GPUs - Each image 2048x2048 pixels

AI Photos of Yourself - Workflow Guide

Step 1: Initial Setup

• Follow any standard FLUX Fine-Tuning / DreamBooth tutorial of your choice

• You can also follow mine step by step : ...

  2024-12-09 00:16:22 +0000 UTC View Post

Solving CUDA and C++ Tools Compiling Errors Once and For All for Python AI Applications

If you are using AI applications and installed software like InsightFace, XPose which you need to compile on your PC, you know that accurate CUDA and C++ tools is a nightmare. This post will help you to understand the fundamental concepts and fix your issues...

SwarmUI Master Tutorial - Use Stable Diffusion 3.5 Large and FLUX model with Amazing Performance and more

In this public tutorial post I will share all the necessary stuff regarding how to use Stable Diffusion 3.5 Large, FLUX Dev, SD 1.5, SDXL, Stable Diffusion 3 and on your computer and also on the cloud (RunPod + Massed Compute).

=======

2024-12-03 22:55:00 +0000 UTC View Post

FLUX Tools Complete Tutorial with SwarmUI (as easy as Automatic1111 or Forge) : Outpainting, Inpainting, Redux Style Transfer + Re-Imagine + Combine Multiple Images, Depth and Canny

Tutorial Link : https://youtu.be/hewDdVJEqOQ

Tutorial resource link (public / no-paywall) : 2024-12-03 20:33:58 +0000 UTC View Post

System Resource Monitor - Monitor your RAM and VRAM usage live - useful to track resource usage of Apps - especially AI apps

Patreon exclusive posts index to find our scripts easily, 2024-11-23 00:10:09 +0000 UTC View Post

NVIDIA Labs developed SANA model weights and Gradio demo app published - 1-Click installers published

Official repo : https://github.com/NVlabs/Sana

1-Click Windows, RunPod, Massed Compute installers and free Kaggle notebook : 2024-11-22 21:11:08 +0000 UTC View Post

Kohya brought massive improvements to FLUX LoRA (as low as 4 GB GPUs) and DreamBooth / Fine-Tuning (as low as 6 GB GPUs) training

• You can download all configs and full instructions

  • > https://www.patreon.com/posts/112099700 - Fine Tuning post

  • > 2024-11-17 13:45:38 +0000 UTC View Post

Genmo Mochi 1 — SOTA Video Generation Model — Full Tutorial With SwarmUI — Locally Generate Amazing AI Videos for Free

Tutorial Link : https://youtu.be/iqBV7bCbDJY

Mochi 1 from Genmo is the newest state-of-the-art Open Source video generation model that you can use for free on your computer. This model is a breakthrough like the very first...

Hunyuan3D-1 - SOTA Open Source Text-to-3D and Image-to-3D - 1-Click Install and use both Locally on Windows and on Cloud - RunPod and Massed Compute

Hunyuan3D-1 - SOTA Open Source Text-to-3D and Image-to-3D - 1-Click Install and use both Locally on Windows and on Cloud - RunPod and Massed Compute

Installers are here : https://www.patreon.com/posts/115412205 2024-11-06 00:15:00 +0000 UTC View Post

Example Training Images Dataset, Trained Models, Grids and Full Training Configs, json files and more

Model Training Experiments and Full Guide and Tutorial: Fine-Tuning vs LoRA Comparison

You can download the model here : https://civitai.com/models/911087

This repository contains experimental r...

OmniGen 1-Click Automatic Installers for Windows, RunPod and Massed Compute - OmniGen is a unified image generation model that can generate a wide range of images from multi-modal prompts. It is designed to be simple, flexible, and easy to use.

Patreon exclusive posts index to find our scripts easily, 2024-11-02 19:16:47 +0000 UTC View Post

Perfect Quality Example Model Training Images Dataset - Can Be Used On FLUX, Stable Diffusion 3.5, 3, SDXL, SD 1.5 and Such

If you are looking for an example model training dataset that is properly prepared, to learn how to prepare and test, this is the dataset!

Patreon exclusive posts index 2024-11-01 17:16:00 +0000 UTC View Post

FLUX De-Distilled and Anti-Bleeding Fine-Tuning / DreamBooth & LoRA Training Experiments - Also Testing CFG Impact for Stylized Images

Patreon exclusive posts index to find our scripts easily, 2024-10-31 12:28:00 +0000 UTC View Post

62 Prompts tested on all experiments (fully public - open access - visit OLDEST COMMENT - all raw Grids shared) to find best Sampler + Scheduler for Stable Diffusion 3.5 Large - SD 3.5 Large FP16 vs Scaled FP8 compared - T5 XXL FP8 vs Scaled FP8 vs FP16 compared - FLUX FP16 vs Scaled FP8 compared

62 Prompts tested on all experiments to find best Sampler + Scheduler for Stable Diffusion 3.5 Large and SD 3.5 Large vs FLUX DEV > https://youtu.be/-zOKhoO9a5s

2024-10-26 12:45:00 +0000 UTC View Post

How To Convert 24 GB FP16 Fine Tuning / DreamBooth FLUX Checkpoints into 12 GB FP8 Checkpoints Tutorial

• As you already know, FLUX Fine Tuning / DreamBooth is yielding the very best results compared to FLUX LoRA training. Here a detailed public post about it : https://www.patreon.com/posts/113970485

  • 2024-10-14 20:43:44 +0000 UTC View Post

Huge FLUX LoRA vs Fine Tuning / DreamBooth Experiments Completed, Moreover Batch Size 1 vs 7 Fully Tested as Well, Not Only for Realism But Also for Stylization

• Full files and article : https://www.patreon.com/posts/112099700

• Huge FLUX LoRA vs Fine Tuning / DreamBooth Experiments Completed, Moreover Batch Size 1 vs 7 Fully Tested as Wel...

  2024-10-14 11:31:28 +0000 UTC View Post

Huge news for Kohya GUI - Now you can fully Fine Tune / DreamBooth FLUX Dev with as low as 6 GB GPUs without any quality loss compared to 48 GB GPUs - Moreover, Fine Tuning yields better results than any LoRA training could

Huge news for Kohya GUI - Now you can fully Fine Tune / DreamBooth FLUX Dev with as low as 6 GB GPUs without any quality loss compared to 48 GB GPUs - Moreover, Fine Tuning yields better results than any LoRA training could

Config Files

• I published all configs here ...

  2024-10-07 11:51:28 +0000 UTC View Post