P-RAJIV/cxr_stable_diffusion_v1_5_lora

🩻 CXR Stable Diffusion v1.5 LoRA

📌 Overview

This repository contains LoRA weights fine-tuned for generating chest X-ray images.

It must be used together with the base model: runwayml/stable-diffusion-v1-5

---

🚀 Usage

import torch
from diffusers import StableDiffusionPipeline

pipe = StableDiffusionPipeline.from_pretrained(
    "runwayml/stable-diffusion-v1-5",
    torch_dtype=torch.float16
).to("cuda")

pipe.load_lora_weights("P-RAJIV/cxr_stable_diffusion_v1_5_lora")

prompt = "Chest X-ray showing pleural effusion"

image = pipe(prompt).images[0]
image.save("output.png")

🧪 Example Prompts
"Normal chest X-ray"
"Chest X-ray showing cardiomegaly"
"Lung opacity in right lower lobe"
"Severe pneumonia chest radiograph"

⚠️ Limitations
Generated images are synthetic and not for clinical use
May produce anatomically inconsistent outputs
Performance depends heavily on prompt quality

📚 Training Details
Base Model: Stable Diffusion v1.5
Domain: Chest X-ray imaging
Fine-tuning: Text-to-image diffusion training

🧠 Intended Use
Research in medical imaging
Data augmentation
Diffusion model experimentation

❗ Disclaimer
This model is not intended for medical diagnosis or clinical decision-making.