SimpleTuner/flux-3-klein-image-LoRA-experiments

FLUX.3 Klein Image: A LoRA Experiment Journal

This journal follows three FLUX.3 Klein training experiments: learning Domokun at different resolutions, training a broad-data assistant LoRA, and using that assistant to finetune distilled Klein on photographic data.

The recipes build on the Qwen Image 2.1 experiments and their v3 training assistant.

Contents

1. Training setup
2. Domokun: three resolution controls
3. A real-data-only training assistant
4. Photo aesthetics with an assistant
5. Progress and runtime notes

Each chapter includes its settings, checkpoint links, and previews. The complete recipes and run manifest are available alongside them.

Campaign At A Glance

Run	Updates / target	Status
domokun-512	10,000 / 10,000	Complete
domokun-1024	10,000 / 10,000	Complete
domokun-512-1024	10,000 / 10,000	Complete
training-assistant-real-v3	30,000 / 30,000	Complete
photo-aesthetics-distilled-assisted-512	50,000 / 50,000	Complete
photo-aesthetics-distilled-assisted-1024	23,601 / 50,000	Training
photo-aesthetics-distilled-assisted-512-v2-kohaku-fa	6,511 / 50,000	Training
photo-aesthetics-distilled-assisted-1024-v2-kohaku-fa	0 / 50,000	Queued

Updated 2026-10-16T22:48:21.704875+00:00.

Training uses BF16 transformers and regional compilation. Checkpoint previews and settings are linked from each chapter.