icon-lab/SynDiff
Official PyTorch implementation of SynDiff described in the paper (https://arxiv.org/abs/2207.08208).
This tool helps medical imaging researchers or clinicians translate one type of medical image (like a T1-weighted MRI) into another (like a T2-weighted MRI) without needing paired examples for training. It takes existing medical images of different contrasts and generates new images that resemble a different contrast. This is useful for researchers studying different image modalities or clinicians who need to visualize data in a specific contrast when only another is available.
314 stars. No commits in the last 6 months.
Use this if you need to generate synthetic medical images of one contrast from another, especially when you don't have perfectly matched pairs of images for training.
Not ideal if you require absolute diagnostic accuracy from synthetic images or are working outside of medical imaging applications.
Stars
314
Forks
49
Language
Python
License
—
Category
Last pushed
May 27, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/icon-lab/SynDiff"
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.