Shah1st/skin-cancer-flux.1-dev-lora

Skin Cancer FLUX LoRA

This LoRA was trained on a dataset of skin cancer images to enable FLUX.1 models to generate realistic dermatoscopic images of skin lesions.

Usage

import torch
from diffusers import FluxPipeline

# Load the base model
pipeline = FluxPipeline.from_pretrained(
    "black-forest-labs/FLUX.1-dev", 
    torch_dtype=torch.bfloat16
)

# Load the LoRA weights
pipeline.load_lora_weights("Shah1st/skin-cancer-flux-dev-lora")  
pipeline = pipeline.to("cuda")

# Generate an image
prompt = "SKINCANCER: Dermatoscopic image of a common nevus with uniform dark brown coloration"
image = pipeline(
    prompt=prompt,
    num_inference_steps=28,  
    guidance_scale=3.5,     
    height=512,
    width=512,
).images[0]

License

This LoRA inherits the license of the base model: non-commercial for dev and Apache 2.0 for schnell.