zju-pi/diff-sampler

An open-source toolbox for fast sampling of diffusion models. Official implementations of our works published in ICML, NeurIPS, CVPR, J. Stat. Mech.

44
/ 100
Emerging

This toolbox helps researchers rapidly generate high-quality outputs from diffusion models, like creating realistic images from text or analyzing complex data. It takes in a trained diffusion model and outputs generated samples much faster than traditional methods, allowing researchers to quickly test new ideas and compare different generation techniques. It's designed for researchers working on advanced generative AI.

360 stars.

Use this if you are a researcher developing or experimenting with diffusion models and need to generate samples quickly and efficiently to validate new algorithms or compare existing approaches.

Not ideal if you are an end-user simply looking to generate images with existing tools like Midjourney or DALL-E, or if you need to run inference on production systems without needing to compare different sampling algorithms.

generative-AI-research diffusion-models AI-model-development machine-learning-research image-generation
No Package No Dependents
Maintenance 6 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 12 / 25

How are scores calculated?

Stars

360

Forks

19

Language

Jupyter Notebook

License

Apache-2.0

Last pushed

Nov 25, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/zju-pi/diff-sampler"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.