THU-AccDiff/xslim
Official implementation of X-Slim(xslim): Accelerating diffusion model via Extreme-slimming Caching
This project helps machine learning engineers and researchers accelerate their diffusion models for image and video generation. By intelligently reusing past computations, it takes your diffusion model and outputs generated images or videos significantly faster. It is designed for those who work with large generative AI models and need to reduce inference time without sacrificing quality.
Use this if you are a machine learning engineer or researcher looking to drastically speed up the generation process of your diffusion models, especially for large-scale image or video synthesis tasks.
Not ideal if you are not working with diffusion models or if your primary concern is model size rather than inference speed.
Stars
8
Forks
—
Language
Python
License
—
Category
Last pushed
Feb 25, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/THU-AccDiff/xslim"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
FlorianFuerrutter/genQC
Generative Quantum Circuits
horseee/DeepCache
[CVPR 2024] DeepCache: Accelerating Diffusion Models for Free
Gen-Verse/MMaDA
MMaDA - Open-Sourced Multimodal Large Diffusion Language Models (dLLMs with block diffusion,...
kuleshov-group/mdlm
[NeurIPS 2024] Simple and Effective Masked Diffusion Language Model
Shark-NLP/DiffuSeq
[ICLR'23] DiffuSeq: Sequence to Sequence Text Generation with Diffusion Models