Mythograph Atelier FLUX.2 Klein LoRA
This is a style LoRA for Mythograph Atelier, trained on 38 curated public-domain abstract images with synthetic captions.
Usage
- Training base model:
black-forest-labs/FLUX.2-klein-base-4B - Recommended inference model:
black-forest-labs/FLUX.2-klein-4B - Trigger word:
MYTHABS1 - Recommended negative prompt:
text, words, letters, signature, watermark, photorealism - Recommended inference steps:
4 - Recommended guidance scale: start with
1.0
The LoRA is intended to make FLUX render Mythograph Atelier prompts in a soft, abstract, worn, emotionally legible visual language.
Training Summary
- Dataset:
flux_lora_dataset, prepared as image/text-caption pairs - Images used: 38
- Training steps: 1,800
- LoRA rank/alpha: linear 128/64, conv 64/32
- Optimizer: AdamW 8-bit
- Precision: bf16
- Training-time transformer quantization was enabled only to reduce GPU memory use; the uploaded artifact is the LoRA checkpoint, not GGUF and not a quantized model export.