Sana Flux LoRA

🚀 Sana-Flux-LoRA

This LoRA model is designed for fans of Sana from Twice, enabling high - quality text - to - image generation.

🚀 Quick Start

Prerequisites

Ensure you have diffusers and torch installed.

Installation

No specific installation steps are provided in the original document.

Usage

You need to use the trigger word sanawiro to generate relevant images.

from diffusers import FluxPipeline
import torch

pipeline = FluxPipeline.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.bfloat16).to('cuda')
pipeline.load_lora_weights('WiroAI/Sana-Flux-LoRA', weight_name='sana_flux_lora.safetensors')
image = pipeline('sanawiro, A young woman with jet-black hair styled in loose waves, wearing a simple pastel pink dress. She stands in a blooming garden, surrounded by roses and soft sunlight. Her gentle smile and relaxed demeanor create a peaceful, elegant scene. Ultra-HD, realistic, with vibrant floral details and soft natural light.').images[0]
image.save("output.png")

✨ Features

• Text - to - Image Generation: Generate high - quality images based on text prompts.
• LoRA Integration: Works in combination with the base model black-forest-labs/FLUX.1-dev.

📚 Documentation

Model Details

Model Description

This LoRA is trained for anyone who like Sana from Twice.

• Developed by: [Wiro AI - ML Team]
• Shared by: Wiro AI

Trigger words

You should use sanawiro to trigger the image generation.

Civitai model link

civitai

📄 License

This model is under the flux-1-dev-non-commercial-license. You can view the full license details here.