Text-to-Image
Diffusers
lora
flux
flux-2
style

Minimal ID Style โ€” FLUX.2 Dev LoRA

A minimalist industrial design style LoRA trained on FLUX.2 [dev].

Trigger Word

Use minimal_id_style in your prompt to activate the style.

Example Prompts

  • a chair in minimal_id_style style, white background
  • a lamp, minimal_id_style, product photography

Training Details

  • Base model: FLUX.2 [dev]
  • Steps: 2000
  • Learning rate: 1e-4
  • Network rank / alpha: 48 / 48
  • Resolution: 512 / 768 / 1024
  • Optimizer: adamw8bit
  • Trained with: fal.ai FLUX.2 Trainer

Usage (diffusers)

```python from diffusers import FluxPipeline import torch

pipe = FluxPipeline.from_pretrained( "black-forest-labs/FLUX.2-dev", torch_dtype=torch.bfloat16 ).to("cuda")

pipe.load_lora_weights("luohedd/minimal_id_style")

image = pipe( "a chair in minimal_id_style style", num_inference_steps=28, guidance_scale=3.5 ).images[0] image.save("output.png") ```

License

This LoRA inherits the FLUX.2 [dev] Non-Commercial License. For commercial use, please refer to Black Forest Labs licensing terms.

Downloads last month
27
Inference Providers NEW

Model tree for luohedd/minimal_id_style

Adapter
(64)
this model