Royalvice/DocDiff
ACM Multimedia 2023: DocDiff: Document Enhancement via Residual Diffusion Models. Also contains 1597 red seals in Chinese scenes, along with their corresponding binary masks.
This helps professionals working with scanned or digital documents improve their quality. You input a document image that might be blurry, noisy, have watermarks, or old and faded, and it outputs a clearer, enhanced version, often with elements like watermarks or seals removed. It's designed for anyone managing or processing large volumes of documents, such as archivists, legal professionals, or data entry specialists.
338 stars. No commits in the last 6 months.
Use this if you need to quickly clean up and enhance document images for better readability, archiving, or further processing.
Not ideal if you're primarily looking to enhance natural scene photographs or require high-diversity image generation for creative tasks, as it's optimized for document characteristics.
Stars
338
Forks
32
Language
Python
License
MIT
Category
Last pushed
Aug 22, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/Royalvice/DocDiff"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
huggingface/diffusers
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.
bghira/SimpleTuner
A general fine-tuning kit geared toward image/video/audio diffusion models.
mcmonkeyprojects/SwarmUI
SwarmUI (formerly StableSwarmUI), A Modular Stable Diffusion Web-User-Interface, with an...
nateraw/stable-diffusion-videos
Create 🔥 videos with Stable Diffusion by exploring the latent space and morphing between text prompts
TheDesignFounder/DreamLayer
Benchmark diffusion models faster. Automate evals, seeds, and metrics for reproducible results.