README.md

Model Training Experiments: Fine-Tuning vs LoRA Comparison

This repository contains experimental results comparing Fine-Tuning/DreamBooth and LoRA training approaches.

Additional Resources

• Installers and Config Files
• Fine Tuning Tutorial
• LoRA Tutorial
• Complete Dataset and Testing Prompts

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
• Realism Test Part 2

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
• LoRA Realism Test Part 2

Comparison Results

• LoRA 90 vs 160 vs Fine-Tuning 170 Comparison

Key Observations

LoRA demonstrates excellent realism but shows more obvious overfitting when generating stylized images.

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