Flux Super Portrait LoRA

🚀 Flux-Super-Portrait-LoRA

This is a text-to-image LoRA model that can generate high - quality super portraits. It provides specific image processing parameters and inference suggestions.

🚀 Quick Start

Installation and Setup

import torch
from pipelines import DiffusionPipeline

base_model = "black-forest-labs/FLUX.1-dev"
pipe = DiffusionPipeline.from_pretrained(base_model, torch_dtype=torch.bfloat16)

lora_repo = "strangerzonehf/Flux-Super-Portrait-LoRA"
trigger_word = "Super Portrait"  
pipe.load_lora_weights(lora_repo)

device = torch.device("cuda")
pipe.to(device)

Trigger Words

You should use Super Portrait to trigger the image generation.

✨ Features

This model offers the following features:

• Generate high - quality super portraits with various styles and details.
• Provide specific image processing parameters for fine - tuning.
• Recommend the best dimensions and inference steps for better results.

📦 Installation

The weights for this model are available in Safetensors format. You can Download them in the Files & versions tab.

💻 Usage Examples

Basic Usage

Use the following code to generate images:

import torch
from pipelines import DiffusionPipeline

base_model = "black-forest-labs/FLUX.1-dev"
pipe = DiffusionPipeline.from_pretrained(base_model, torch_dtype=torch.bfloat16)

lora_repo = "strangerzonehf/Flux-Super-Portrait-LoRA"
trigger_word = "Super Portrait"  
pipe.load_lora_weights(lora_repo)

device = torch.device("cuda")
pipe.to(device)

# Generate an image
prompt = "Super Portrait, A close-up portrait of a young man with dark brown eyes and dark brown eyebrows."
image = pipe(prompt).images[0]
image.save("generated_image.png")

📚 Documentation

Image Processing Parameters

Labeling

The labeling is done using florence2 - en (natural language & English).

Training Data

Total Images Used for Training: 19 [ Flat 4K ]

Best Dimensions & Inference

Inference Range

• Recommended Inference Steps: 30–35

📄 License

This model is under the creativeml-openrail-m license.