Furkan Gözükara
patreon
Example Training Images Dataset, Trained Models, Grids and Full Training Configs, json files and more
🕑 Added 2024-11-02 21:19:17 +0000 UTCModel 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 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
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
Comparison Results
Key Observations
LoRA demonstrates excellent realism but shows more obvious overfitting when generating stylized images.
Fine-Tuning / DreamBooth is better than LoRA as expected.
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
Training Images Dataset and Example Generated Images
You can find full resolution training dataset and more here : https://www.patreon.com/posts/perfect-quality-114972274
The dataset can be used to train Stable Diffusion 1.5 (SD 1.5), Stable Diffusion XL (SDXL), Stable Diffusion 3, Stable Diffusion 3.5 Medium (SD 3.5), Stable Diffusion 3.5 Large, FLUX, and such text to image models.
Comments
Furkan Gözükara
for 15-50 images i usually go up to 200 epochs and compare checkpoints. if you have like only 10 images go up to 300 epochs and compare checkpoints. dont change learning rate
Dmitrii
I see that you use 28 images with 170 epoch and 4e-06 learning rate Which gives 4760 steps in total What is your approach for a different amount of images? E.g I want to train on 10 images. If I use 170 epoch and same learning rate, I'll get only 1700 steps. Should I increase amount of epoch to 470 to get 4700 steps, or increase learning rate?
Furkan Gözükara
thank you so much
AiInfluence
Absolutely amazing work as always Doctor.
