FLUX DreamBooth Checkpoints: Convert 24 GB FP16 to 12 GB FP8 Tutorial
FLUX fine tuning / DreamBooth checkpoints take 23.8 GB in FP16; Kohya GUI converts them to 11.9 GB FP8 with no visible quality loss in the grids.

Highlights
Screenshots show how to convert into FP8 with CUDA or CPU, with no difference between the two. The post also links why fine tuning beats LoRA training and the full Kohya fine tuning guide for GPUs with as little as 6 GB.
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 Fine Tuning / DreamBooth Training Tutorial: Windows & Cloud
Kohya FLUX full fine tuning / DreamBooth trains full checkpoints with configs for GPUs with as low as 8 GB VRAM, all using Torch Compile on Windows and Linux.

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.
More in LoRA and Fine-Tuning Training: Kohya, Musubi Tuner, OneTrainer, AI Toolkit.