aihpi/flux-fashion-lora

flux-fashion

The flux-fashion LoRA model generates high-quality, realistic clothing images from text descriptions. It was trained on the H&M Fashion Caption Dataset (12k) using the AI Toolkit. The LoRA is compatible with FLUX architectures, including Shuttle 3.1.

Prompt

Neutral Gray Background, Wide-angle, high quality, detailed, ultrarealistic photography, A beige linen shirt with short sleeves, a round neckline, and a subtle texture. The shirt has minimal stitching visible at the seams.

Prompt

Neutral Gray Background, Wide-angle, high quality, detailed, ultrarealistic photography, A yellow cotton blouse featuring short puff sleeves, gathered shoulders, and button-down front closure. It has two small pockets on either side.

Features

• Dataset: Fine-tuned on H&M Fashion Caption Dataset (12k)
• Architecture: Compatible with FLUX (e.g., Shuttle 3.1)
• Model Type: LoRA for text-to-image tasks.
• Base Model: black-forest-labs/FLUX.1-schnell.
• License: Apache-2.0.

Usage

Use this Model directly using Diffusers

from diffusers import DiffusionPipeline

pipe = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.1-schnell")
pipe.load_lora_weights("aihpi/flux-fashion-lora")

prompt = "Neutral Gray Background, Wide-angle, high quality, detailed, ultrarealistic photography, A beige linen shirt with short sleeves, a round neckline, and a subtle texture. The shirt has minimal stitching visible at the seams."
image = pipe(prompt).images[0]

Download model

Weights for this model are available in Safetensors format.

Download them in the Files & versions tab.