SDXL DreamBooth LoRA - sdxl-Bharat-lora

This is a LoRA (Low-Rank Adaptation) model trained with DreamBooth on Stable Diffusion XL.

Trigger Word

Bharat

Usage

from diffusers import StableDiffusionXLPipeline
import torch

pipe = StableDiffusionXLPipeline.from_pretrained(
    "stabilityai/stable-diffusion-xl-base-1.0",
    torch_dtype=torch.float16
).to("cuda")

pipe.load_lora_weights("Bharatgwl/sdxl-Bharat-lora")

prompt = "a photo of Bharat person, professional portrait, studio lighting"
image = pipe(prompt, num_inference_steps=30).images[0]
image.save("output.png")

Training Details

• Base Model: stabilityai/stable-diffusion-xl-base-1.0
• Training Steps: 800
• Learning Rate: 0.0001
• Resolution: 1024x1024
• Batch Size: 1
• Instance Prompt: a photo of Bharat person
• Images: 14