FLUX Fine-Tuning vs LoRA: Example Dataset, Trained Models & Configs
FLUX fine-tuning / DreamBooth vs LoRA experiment shared in full: a 28-image dataset, Kohya configs, grids and every trained checkpoint free on Hugging Face.

Highlights
Includes the full training config json files, example training images, the model on CivitAI and realism test grids. Fine-tuning (best at epoch 170) beat LoRA (best at epoch 160), which overfits more on stylized images; the workflow also trains clothing, objects, pets and styles.
Video tutorial
Stable Diffusion 3.5 Large vs FLUX Dev: Which Makes Better Images? Compared on the Same Prompts · chapters and summary
More videos: Train FLUX on Your Own Photos With Just a 6 GB GPU: Full Fine-Tuning Course (Kohya, 2024), Train FLUX on Your Own Photos With Just 8GB VRAM: Kohya GUI LoRA Tutorial (2024, Windows)
Related

FLUX 2 vs FLUX SRPO & New Kohya SS GUI Premium FLUX Training App
FLUX 2 Pro compared with a trained FLUX SRPO model, plus the new Kohya trainer V35 that trains FLUX on GPUs with as little as 6 GB VRAM.

FLUX LoRA vs Fine Tuning / DreamBooth Comparison: Batch Size 1 vs 7
FLUX LoRA and Fine Tuning / DreamBooth compared with 15 and 256 training images at batch size 1 and 7, for both realism and stylization.

FLUX Full Fine Tuning vs LoRA Comparison: Less Overfitting & Bleeding
FLUX full fine tuning / DreamBooth gives way better results than LoRA training, as expected, with much less overfitting and bleeding.