Patreon
Home / Apps / Research, Comparisons and Experiments / Kohya FLUX LoRA Training Experiments: All 104 Trainings List

Kohya FLUX LoRA Training Experiments: All 104 Trainings Listed

FLUX LoRA training experiments run with Kohya on an 8x RTX A6000 RunPod machine, 3000 steps each, with every trained model listed and shared on Hugging Face.

lora trainingcomparisontraining configsrunpod
Kohya FLUX LoRA Training Experiments: All 104 Trainings Listed

Highlights

All the experiments done so far compare learning rates, BF16, FP16 and FP8 precisions, ranks, timestep sampling options, regularization images, T5 attention mask and resolutions up to 1536. The best configs were updated as the total reached 104 trainings and are shared in the Kohya FLUX LoRA posts.

Runs on: RunPod. Installers are 1-click and use an isolated Python environment, so they do not break other apps.
Where to get it: the full post is free on this Patreon post by Furkan Gözükara (SECourses). Published Sep 09, 2024.

Related

Qwen Image LoRA Training: Stage 1 Results and Pre-Made Configs

Qwen Image LoRA Training: Stage 1 Results and Pre-Made Configs

Qwen Image LoRA results from more than 35 Stage 1 trainings with SECourses Musubi Tuner; the published pre-made configs train on GPUs with as low as 6 GB.

FLUX 2 vs FLUX SRPO & New Kohya SS GUI Premium FLUX Training App

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 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.

More in Research, Comparisons and Experiments.