README.md

metadata

title: CCTV Frame Restoration (Diffusion)
emoji: 🎥
colorFrom: blue
colorTo: purple
sdk: gradio
app_file: app.py
pinned: false

CCTV Frame Restoration with Diffusion Model

This demo is an AI-assisted development using Claude Sonnet 5.

Restores low-resolution, noisy, low-light CCTV/security camera frames using the pretrained Stable Diffusion x4 Upscaler (stabilityai/stable-diffusion-x4-upscaler).

Upload a low-quality frame, adjust the prompt/steps if you like, and get a 4x upscaled, denoised, sharpened result.

Note: Input images are resized so their longest side is ≤128px before upscaling, matching the resolution the model was trained on. For CPU inference, it may take 1-3 minutes per image.

UI snapshot