[NeurIPS 2023] Official implementation of "PreDiff: Precipitation Nowcasting with Latent Diffusion Models"
active 2023-10-28 → 2026-03-01 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 856 days from 2023-10-28 to 2026-03-01. Pushes: 45 total, peak 10 in a day. Pull requests: 21 total, peak 2 in a day. Issues: 37 total, peak 3 in a day. Comments: 63 total, peak 6 in a day. Stars: 131 total, peak 4 in a day.
- Pushes
- Pull requests
- Issues
- Comments
- Stars
Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.
Top contributors
Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity
| Contributor | Contributions | Pushes | PRs | Comments |
|---|---|---|---|---|
| gaozhihan | 97 | 45 | 18 | 31 |
| zengrh3 | 10 | 0 | 0 | 7 |
| qwertyui20 | 9 | 0 | 0 | 4 |
| marctimjen | 6 | 0 | 0 | 2 |
| OswaldoBornemann | 5 | 0 | 0 | 3 |
| liuyi-461 | 4 | 0 | 3 | 1 |
| GexLoong | 3 | 0 | 0 | 3 |
| xiaochengfuhuo | 3 | 0 | 0 | 2 |
| earthpimp | 3 | 0 | 0 | 1 |
| hiuaaa | 2 | 0 | 0 | 0 |
| zhouy02 | 2 | 0 | 0 | 1 |
| bugsuse | 2 | 0 | 0 | 0 |
| Haozhouhao | 2 | 0 | 0 | 1 |
| VermicelliPencil | 2 | 0 | 0 | 2 |
| yyyujintang | 2 | 0 | 0 | 1 |
| JackChan1123 | 2 | 0 | 0 | 1 |
| funfunlsy | 2 | 0 | 0 | 0 |
| drmahes | 2 | 0 | 0 | 2 |
| forevergj | 1 | 0 | 0 | 1 |
| JiangZixun | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue comment#46GexLoong2026-01-09 14:30Pretrained model files 404
- Issue comment#37GexLoong2026-01-09 07:58Can everyone share the author's pre trained model?
- Issue comment#43GexLoong2026-01-08 03:03[Request] Pretrained model OneDrive links expired (404) — please re-upload
- Pull request#45liuyi-4612025-11-15 10:01
- Issue#43lyft10242025-11-03 08:16[Request] Pretrained model OneDrive links expired (404) — please re-upload
- Issue comment#42liuyi-4612025-10-17 16:17fix: 修改path.py支持自定义路径
- Pull request#42liuyi-4612025-10-17 16:16
- Pull request#42liuyi-4612025-10-17 16:15
- Issue#40gaozhihan2025-10-17 03:11LDM generate full of Noise
- Issue#40gaozhihan2025-10-17 03:11LDM generate full of Noise
- Issue#36funfunlsy2024-11-20 08:54Both training and inference will encounter NaN.
- Issue#39JiangZixun2024-11-15 08:21Question about the inference of PreDiff when using KnowledgeAlignment
- Issue#38hiuaaa2024-11-08 15:28dataset code
- Issue#38hiuaaa2024-11-07 06:24dataset code
- Issue#37jichongxing20232024-10-29 16:06Can everyone share the author's pre trained model?
- Issue#36funfunlsy2024-10-16 06:58Both training and inference will encounter NaN.
- Issue comment#9forevergj2024-07-30 03:08tested Prediff
- Issue#35Shirvin2024-07-30 01:17请问prediff论文中sevirlr所得到的评估指标是使用的哪些数据？能否提供数据id？
- Issue comment#34gaozhihan2024-07-04 06:29How much time will it take to train the model on a single A100?(The dataset size is 800*800, but we will shrink it to 200*200)
- Issue#34Crestina20012024-06-28 02:05How much time will it take to train the model on a single A100?(The dataset size is 800*800, but we will shrink it to 200*200)
- Issue comment#30gaozhihan2024-05-23 07:14About the knowledge control model
- Issue comment#31gaozhihan2024-05-23 07:06The model performance is greatly affected by long-tailed dataset
- Issue comment#32gaozhihan2024-05-23 06:58Timing to call .zero_grad()
- Pull request#33gaozhihan2024-05-23 06:56
- Pull request#33gaozhihan2024-05-23 06:56
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 131 stars here means stars gained during the window, not the repo's star count.