Kohya GUI: Convert FLUX, SD 3.5 & SDXL LoRAs to FP8 to Save Space
Converting a trained LoRA to FP8 with Kohya GUI shrinks a 2.5 GB FP32 file to 634 MB with almost the best quality, as the FP8 vs FP16 vs FP32 grid shows.

Highlights
How to convert your trained FLUX, Stable Diffusion 3.5, SDXL, SD 1.5 and other LoRAs into FP8 to save huge space, or save them as FP16 during training to halve the size with almost no quality loss. Links to the FLUX LoRA and fine tuning tutorials.
Video tutorial
Train FLUX on Your Own Photos With Just a 6 GB GPU: Full Fine-Tuning Course (Kohya, 2024) · chapters and summary
More videos: Train FLUX on Your Own Photos With Just 8GB VRAM: Kohya GUI LoRA Tutorial (2024, Windows)
Related

Musubi Tuner App: 1-Click LoRA & Fine-Tune Training With 435 Presets
SECourses Musubi Tuner trains LoRAs and full fine-tunes of Qwen Image, Wan 2.2, FLUX 2, Z Image and LTX 2.3 on Windows or cloud GPUs with 435 ready presets.

Kohya FLUX LoRA Training: Full Tutorial & Configs for Windows & Cloud
Kohya SS GUI FLUX LoRA training step by step, with the best optimized configs for 4 GB to 48 GB GPUs and a 68 minute Windows tutorial with 74 chapters.

Ostris AI-Toolkit 1-Click Installers: LoRA Training on Windows & Cloud
Ostris AI-Toolkit installs automatically on Windows, RunPod, SimplePod and Massed Compute and is now patched to train on custom single-file base models.
More in LoRA and Fine-Tuning Training: Kohya, Musubi Tuner, OneTrainer, AI Toolkit.