WinfredGe/T2S
[IJCAI 2025] Official implementation of "T2S: High-resolution Time Series Generation with Text-to-Series Diffusion Models"
This project helps non-experts and professionals generate complex time series data using simple text descriptions. You input natural language describing desired temporal behaviors or system dynamics, and it outputs high-resolution, semantically aligned time series. This tool is designed for anyone needing to simulate system behavior, create synthetic data for analysis, or test systems under various conditions.
Use this if you need to quickly generate diverse time series data for simulations, prototyping, or stress testing, especially when traditional methods struggle with extreme scenarios or require deep expertise.
Not ideal if you primarily need to forecast future values based on existing time series data, rather than generating entirely new sequences from textual prompts.
Stars
71
Forks
9
Language
Python
License
Apache-2.0
Category
Last pushed
Oct 15, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/WinfredGe/T2S"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related models
monniert/dti-sprites
(ICCV 2021) Code for "Unsupervised Layered Image Decomposition into Object Prototypes" paper
Mukosame/AODA
Official implementation of "Adversarial Open Domain Adaptation for Sketch-to-Photo...
shashankvkt/AlignMixup_CVPR22
Official Implementation of AlignMixup - CVPR 2022
JinXins/Adversarial-AutoMixup
Official PyTorch(MMCV) implementation of “Adversarial AutoMixup” (ICLR 2024 spotlight)
ValentinKoch/SVDNA
The github repository of the paper "Noise Transfer for Unsupervised Domain Adaptation of Retinal...