ModelTC/TFMQ-DM

[CVPR 2024 Highlight & TPAMI 2025] This is the official PyTorch implementation of "TFMQ-DM: Temporal Feature Maintenance Quantization for Diffusion Models".

34
/ 100
Emerging

This project helps machine learning engineers and researchers optimize diffusion models for faster performance without extensive retraining. It takes existing pre-trained diffusion models, like Stable Diffusion or LDM, and quantizes them into a more efficient, smaller format. The output is a quantized model that generates high-quality images much faster than the original.

109 stars. No commits in the last 6 months.

Use this if you need to significantly speed up image generation from diffusion models and reduce their computational footprint without sacrificing output quality, particularly when deploying models on resource-constrained hardware.

Not ideal if you are looking for a tool to train new diffusion models from scratch or if your primary concern is fine-tuning models rather than optimizing their inference speed.

generative-AI image-synthesis model-optimization AI-deployment deep-learning-research
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 7 / 25

How are scores calculated?

Stars

109

Forks

5

Language

Jupyter Notebook

License

Apache-2.0

Last pushed

Sep 29, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/ModelTC/TFMQ-DM"

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