DEV Community

Cover image for Example Training Images Dataset, Trained Models, Grids and Full Training Configs, json files and more
Furkan Gözükara
Furkan Gözükara

Posted on

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 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

 

 

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.

Top comments (0)