FLUX.2 [klein] 9B Style LoRA Trainer: Training
Produce style-focused LoRA adapters on top of the FLUX.2 [klein] 9B architecture. Upload a ZIP dataset with training images and optional captions.
Produce style-focused LoRA adapters on top of the FLUX.2 [klein] 9B architecture. Upload a ZIP dataset with training images and optional captions.
About this model
FLUX.2 [klein] 9B Style LoRA Training is a training workflow for producing style-focused LoRA adapters on top of the FLUX.2 Klein 9B architecture. Upload a ZIP dataset containing images and optional text captions, specify a trigger word and step count, and receive downloadable safetensors model output with instant platform AIR deployment.
Cost analysis
| Provider | Cost | Notes |
|---|---|---|
| MuAPI | $4.00 per 1,000 steps ($0.004 / step) | Best price & high performance |
Best price & high performance
* Competitor pricing is estimated based on similar model architectures and usage tiers.
Configuration schema
| Parameter | Type | Description | Default |
|---|---|---|---|
| Dataset Zip URL | string | URL to ZIP archive containing training images and optional .txt caption files. | undefined |
| Trigger Word | string | Word or phrase used to activate the trained concept at inference time. | my_style |
| Training Steps | int | Total number of optimization steps to run during training. | 1000 |
| Learning Rate | float | Step size applied at each training update. | 0.00005 |
URL to ZIP archive containing training images and optional .txt caption files.
undefinedWord or phrase used to activate the trained concept at inference time.
my_styleTotal number of optimization steps to run during training.
1000Step size applied at each training update.
0.00005Developer documentation
Frequently asked