ui-generator-prototype

📱 UI Generator Prototype – LoRA Fine-Tuned SDXL Model

A LoRA fine-tuned Stable Diffusion XL (SDXL) model designed to generate highly detailed mobile UI screens from natural language prompts. This prototype specializes in generating UIs with accurate layout structure, typography, color codes, padding, and spacing.

---

🚀 Model Summary

• Base Model: stabilityai/stable-diffusion-xl-base-1.0
• LoRA Adapter: Fine-tuned using Diffusers
• Domain: Mobile User Interfaces
• Dataset: 900+ captioned UI screenshots
  → aryanbaghel/ui-caption-padded
• Training Goal: Enhance SDXL’s ability to generate UI screens from structured descriptive prompts.

---

🧠 Use Cases

• Prototyping UI design ideas from prompts
• UX/UI design automation
• Visualizing layout sketches for mobile apps
• Creative ideation for product design teams

---

📦 How to Use

from diffusers import DiffusionPipeline
import torch

# Load base SDXL model
pipe = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", torch_dtype=torch.float16, use_safetensors=True, variant="fp16")
pipe.to("cuda")

# Load LoRA weights
pipe.load_lora_weights("aryanbaghel/ui-generator-prototype")

# Enable LoRA
pipe.fuse_lora()

# Generate a UI screen
prompt = "A mobile UI showing a hotel reservation screen with elegant typography and clean layout"
image = pipe(prompt=prompt).images[0]
image.save("output.png")
print("SUCCESS!")