| <table style="border-collapse: collapse; border: 2px solid #ddd; width: 100%;"> | |
| <tr> | |
| <td style="border: 1px solid #ddd; padding: 3px; text-align: center; vertical-align: middle;"><a href="https://discord.com/servers/software-engineering-courses-secourses-772774097734074388"><img src="https://img.shields.io/discord/772774097734074388?label=Discord&logo=discord" alt="Discord"></a></td> | |
| <td style="border: 1px solid #ddd; padding: 3px; text-align: center; vertical-align: middle;"><a href="https://hits.seeyoufarm.com"><img src="https://hits.seeyoufarm.com/api/count/incr/badge.svg?url=https%3A%2F%2Fhuggingface.co%2FMonsterMMORPG%2FModel_Training_Experiments_As_A_Baseline&count_bg=%2379C83D&title_bg=%239E0F0F&icon=apachespark.svg&icon_color=%23E7E7E7&title=views&edge_flat=false" alt="Hits"></a></td> | |
| <td style="border: 1px solid #ddd; padding: 3px; text-align: center; vertical-align: middle;"><a href="https://www.patreon.com/SECourses"><img src="https://img.shields.io/badge/Patreon-Support%20Me-F2EB0E?style=for-the-badge&logo=patreon" alt="Patreon"></a></td> | |
| <td style="border: 1px solid #ddd; padding: 3px; text-align: center; vertical-align: middle;"><a href="https://www.buymeacoffee.com/DrFurkan"><img src="https://img.shields.io/badge/Buy%20Me%20a%20Coffee-ffdd00?style=for-the-badge&logo=buy-me-a-coffee&logoColor=black" alt="BuyMeACoffee"></a></td> | |
| <td style="border: 1px solid #ddd; padding: 3px; text-align: center; vertical-align: middle;"><a href="https://medium.com/@furkangozukara"><img src="https://img.shields.io/badge/Medium-Follow%20Me-800080?style=for-the-badge&logo=medium&logoColor=white" alt="Furkan Gözükara Medium"></a></td> | |
| <td style="border: 1px solid #ddd; padding: 3px; text-align: center; vertical-align: middle;"><a href="https://civitai.com/user/SECourses/articles"><img src="https://img.shields.io/static/v1?style=for-the-badge&message=Articles&color=4574E0&logo=Codio&logoColor=FFFFFF&label=CivitAI" alt="Codio"></a></td> | |
| </tr> | |
| <tr> | |
| <td style="border: 1px solid #ddd; padding: 3px; text-align: center; vertical-align: middle;"><a href="https://www.deviantart.com/monstermmorpg"><img src="https://img.shields.io/badge/DeviantArt-Follow%20Me-990000?style=for-the-badge&logo=deviantart&logoColor=white" alt="Furkan Gözükara DeviantArt"></a></td> | |
| <td style="border: 1px solid #ddd; padding: 3px; text-align: center; vertical-align: middle;"><a href="https://www.youtube.com/SECourses"><img src="https://img.shields.io/badge/YouTube-SECourses-C50C0C?style=for-the-badge&logo=youtube" alt="YouTube Channel"></a></td> | |
| <td style="border: 1px solid #ddd; padding: 3px; text-align: center; vertical-align: middle;"><a href="https://www.linkedin.com/in/furkangozukara/"><img src="https://img.shields.io/badge/LinkedIn-Follow%20Me-0077B5?style=for-the-badge&logo=linkedin&logoColor=white" alt="Furkan Gözükara LinkedIn"></a></td> | |
| <td style="border: 1px solid #ddd; padding: 3px; text-align: center; vertical-align: middle;"><a href="https://www.udemy.com/course/stable-diffusion-dreambooth-lora-zero-to-hero/?referralCode=E327407C9BDF0CEA8156"><img src="https://img.shields.io/static/v1?style=for-the-badge&message=Stable%20Diffusion%20Course&color=A435F0&logo=Udemy&logoColor=FFFFFF&label=Udemy" alt="Udemy"></a></td> | |
| <td style="border: 1px solid #ddd; padding: 3px; text-align: center; vertical-align: middle;"><a href="https://twitter.com/GozukaraFurkan"><img src="https://img.shields.io/badge/Twitter-Follow%20Me-1DA1F2?style=for-the-badge&logo=twitter&logoColor=white" alt="Twitter Follow Furkan Gözükara"></a></td> | |
| </tr> | |
| </table> | |
| # Model Training Experiments and Full Guide and Tutorial: Fine-Tuning vs LoRA Comparison | |
| This repository contains experimental results comparing Fine-Tuning/DreamBooth and LoRA training approaches. | |
| I am sharing how I trained this model with full details and even the dataset: please read entire post very carefully. | |
| This model is purely trained for educational and research purposes only for SFW and ethical image generation. | |
| The workflow and the config used in this tutorial can be used to train clothing, items, animals, pets, objects, styles, simply anything. | |
| The uploaded images have SwarmUI metadata and can be re-generated exactly. For generations FP16 model used but FP8 should yield almost same quality. Don't forget to have used yolo face masking model in prompts. | |
| ## How To Use | |
| Download model into diffusion_models of the SwarmUI. Then you need to use Clip-L and T5-XXL models as well. I recommend T5-XXL FP16 or Scaled FP8 version. | |
| A newest fully public tutorial here for how to use : https://youtu.be/-zOKhoO9a5s | |
| ## Additional Resources | |
| - Installers and Config Files : https://www.patreon.com/posts/112099700 | |
| - FLUX Fine-Tuning / DreamBooth Zero-to-Hero Tutorial : https://youtu.be/FvpWy1x5etM | |
| - FLUX LoRA Training Zero-to-Hero Tutorial : https://youtu.be/nySGu12Y05k) | |
| - Complete Dataset, Training Config Json Files and Testing Prompts : https://www.patreon.com/posts/114972274 | |
| - Click below link to download all trained LoRA and Fine-Tuning / DreamBooth checkpoints for free | |
| - https://huggingface.co/MonsterMMORPG/Model_Training_Experiments_As_A_Baseline/tree/main | |
| ## Environment Setup | |
| - Kohya GUI Version: `021c6f5ae3055320a56967284e759620c349aa56` | |
| - Torch: 2.5.1 | |
| - xFormers: 0.0.28.post3 | |
| ## Dataset Information | |
| - Resolution: 1024x1024 | |
| - Dataset Size: 28 images | |
| - Captions: "ohwx man" (nothing else) | |
| - Activation Token/Trigger Word: "ohwx man" | |
| ## Fine-Tuning / DreamBooth Experiment | |
| ### Configuration | |
| - Config File: `48GB_GPU_28200MB_6.4_second_it_Tier_1.json` | |
| - Training: Up to 200 epochs with consistent config | |
| - Optimal Result: Epoch 170 (subjective assessment) | |
| ### Results | |
| - [Realism Test Part 1](https://huggingface.co/MonsterMMORPG/Model_Training_Experiments_As_A_Baseline/blob/main/Dwayne_Fine_Tune_Realism_Test_Part1.jpg) | |
| - [Realism Test Part 2](https://huggingface.co/MonsterMMORPG/Model_Training_Experiments_As_A_Baseline/blob/main/Dwayne_Fine_Tune_Realism_Test_Part2.jpg) | |
| ## LoRA Experiment | |
| ### Configuration | |
| - Config File: `Rank_1_29500MB_8_85_Second_IT.json` | |
| - Training: Up to 200 epochs | |
| - Optimal Result: Epoch 160 (subjective assessment) | |
| ### Results | |
| - [LoRA Realism Test Part 1](https://huggingface.co/MonsterMMORPG/Model_Training_Experiments_As_A_Baseline/blob/main/Dwayne_LoRA_Realism_Test_Part1.jpg) | |
| - [LoRA Realism Test Part 2](https://huggingface.co/MonsterMMORPG/Model_Training_Experiments_As_A_Baseline/blob/main/Dwayne_LoRA_Realism_Test_Part2.jpg) | |
| ## Comparison Results | |
| ### LoRA Epochs Comparison | |
| - [LoRA 90 vs 160 vs Fine-Tuning 170 Comparison](https://huggingface.co/MonsterMMORPG/Model_Training_Experiments_As_A_Baseline/blob/main/LoRA_90_Epoch_vs_LoRA_160_Epoch_vs_Fine_Tuning_170_Epoch.jpg) | |
| ### Precision Testing | |
| Compared different precision formats in LoRA training: | |
| - FP8 vs FP16 vs FP32 LoRA configurations | |
| - [View Precision Comparison Grid](https://huggingface.co/MonsterMMORPG/Model_Training_Experiments_As_A_Baseline/blob/main/LoRA_Precision_FP8_vs_FP16_vs_FP32_Grid.jpg) | |
| ### Model Variant Analysis | |
| Tested various model variants with LoRA (FP32 Version): | |
| - FP8 FLUX DEV Base | |
| - FP8 Scaled | |
| - GGUF 8 | |
| - FLUX DEV | |
| - [View Model Variants Comparison Grid](https://huggingface.co/MonsterMMORPG/Model_Training_Experiments_As_A_Baseline/blob/main/Model_Variants_Tests_Grid.jpg) | |
| - Works best with FP16 DEV base model, then GGUF 8 base model and then FP8 raw base model and FP8 scaled model sometimes works better sometimes worse | |
| ### Key Observations | |
| - LoRA demonstrates excellent realism but shows more obvious overfitting when generating stylized images. | |
| - Fine-Tuning / DreamBooth is better than LoRA as expected. | |
| - FP8 almost yields perfect quality as FP32 with LoRA | |
| - I have used Kohya GUI to convert FP32 saved LoRAs into FP16 and FP8 | |
| - Here full public article : https://www.patreon.com/posts/115376830 | |
| ## Model Naming Convention | |
| ### Fine-Tuning Models | |
| - `Dwayne_Johnson_FLUX_Fine_Tuning-000010.safetensors` | |
| - 10 epochs | |
| - 280 steps (28 images × 10 epochs) | |
| - Batch size: 1 | |
| - Resolution: 1024x1024 | |
| - `Dwayne_Johnson_FLUX_Fine_Tuning-000020.safetensors` | |
| - 20 epochs | |
| - 560 steps (28 images × 20 epochs) | |
| - Batch size: 1 | |
| - Resolution: 1024x1024 | |
| ### LoRA Models | |
| - `Dwayne_Johnson_FLUX_LoRA-000010.safetensors` | |
| - 10 epochs | |
| - 280 steps (28 images × 10 epochs) | |
| - Batch size: 1 | |
| - Resolution: 1024x1024 | |
| - `Dwayne_Johnson_FLUX_LoRA-000020.safetensors` | |
| - 20 epochs | |
| - 560 steps (28 images × 20 epochs) | |
| - Batch size: 1 | |
| - Resolution: 1024x1024 | |
| ## Some Example Images - They have MetaData on CivitAI | |
| CivitAI : https://civitai.com/models/911087 | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |