Flux 3 Klein Image LoRA Training
Collection
Experimental training adapter and logs for Flux 3 Klein Image • 9 items • Updated
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
- Training setup
- Domokun: three resolution controls
- A real-data-only training assistant
- Photo aesthetics with an assistant
- Progress and runtime notes
- Base-trained Domokun LoRAs on distilled Klein
Each chapter includes its settings, checkpoint links, and previews. The complete recipes and run manifest are available alongside them.
Campaign At A Glance
All eight runs completed. Final adapters and validation images are uploaded.
| Run | Final updates | Checkpoints | Final adapter |
|---|---|---|---|
| Domokun, 512px | 10,000 | 20 | Weights |
| Domokun, 1024px | 10,000 | 20 | Weights |
| Domokun, mixed 512px + 1024px | 10,000 | 20 | Weights |
| Training assistant | 30,000 | 30 | Weights |
| Photo 512px, native SDPA | 50,000 | 50 | Weights |
| Photo 1024px, native SDPA | 50,000 | 50 | Weights |
| Photo 512px, Kohaku-FA | 50,000 | 50 | Weights |
| Photo 1024px, Kohaku-FA | 50,000 | 50 | Weights |
Hub checkpoints verified 2026-10-17.
- Downloads last month
- -
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for SimpleTuner/flux-3-klein-image-LoRA-experiments
Base model
black-forest-labs/flux-3-image-klein